[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-ML4Comm-Netw--Paper-with-Code-of-Wireless-communication-Based-on-DL":3,"tool-ML4Comm-Netw--Paper-with-Code-of-Wireless-communication-Based-on-DL":64},[4,17,27,35,44,52],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":10,"last_commit_at":41,"category_tags":42,"status":16},4292,"Deep-Live-Cam","hacksider\u002FDeep-Live-Cam","Deep-Live-Cam 是一款专注于实时换脸与视频生成的开源工具，用户仅需一张静态照片，即可通过“一键操作”实现摄像头画面的即时变脸或制作深度伪造视频。它有效解决了传统换脸技术流程繁琐、对硬件配置要求极高以及难以实时预览的痛点，让高质量的数字内容创作变得触手可及。\n\n这款工具不仅适合开发者和技术研究人员探索算法边界，更因其极简的操作逻辑（仅需三步：选脸、选摄像头、启动），广泛适用于普通用户、内容创作者、设计师及直播主播。无论是为了动画角色定制、服装展示模特替换，还是制作趣味短视频和直播互动，Deep-Live-Cam 都能提供流畅的支持。\n\n其核心技术亮点在于强大的实时处理能力，支持口型遮罩（Mouth Mask）以保留使用者原始的嘴部动作，确保表情自然精准；同时具备“人脸映射”功能，可同时对画面中的多个主体应用不同面孔。此外，项目内置了严格的内容安全过滤机制，自动拦截涉及裸露、暴力等不当素材，并倡导用户在获得授权及明确标注的前提下合规使用，体现了技术发展与伦理责任的平衡。",88924,"2026-04-06T03:28:53",[13,14,15,43],"视频",{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":23,"last_commit_at":50,"category_tags":51,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":53,"name":54,"github_repo":55,"description_zh":56,"stars":57,"difficulty_score":23,"last_commit_at":58,"category_tags":59,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,60,43,61,15,62,26,13,63],"数据工具","插件","其他","音频",{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":75,"owner_avatar_url":76,"owner_bio":77,"owner_company":78,"owner_location":78,"owner_email":78,"owner_twitter":78,"owner_website":78,"owner_url":79,"languages":78,"stars":80,"forks":81,"last_commit_at":82,"license":78,"difficulty_score":10,"env_os":83,"env_gpu":83,"env_ram":83,"env_deps":84,"category_tags":87,"github_topics":88,"view_count":23,"oss_zip_url":78,"oss_zip_packed_at":78,"status":16,"created_at":97,"updated_at":98,"faqs":99,"releases":100},4136,"ML4Comm-Netw\u002FPaper-with-Code-of-Wireless-communication-Based-on-DL","Paper-with-Code-of-Wireless-communication-Based-on-DL","无线与深度学习结合的论文代码整理\u002FPaper-with-Code-of-Wireless-communication-Based-on-DL","Paper-with-Code-of-Wireless-communication-Based-on-DL 是一个专注于整理“深度学习 + 无线通信”领域开源论文与代码的资源库。随着深度学习在通信研究中的广泛应用，许多前沿论文往往缺乏配套代码，导致复现困难、入门门槛高。该项目旨在解决这一痛点，系统性地收集并分类那些已公开源代码的高质量论文，涵盖物理层优化、资源分配、分布式学习、网络切片、物联网应用及安全通信等多个细分方向。\n\n它特别适合通信专业的研究生、高校科研人员以及从事相关算法开发的工程师使用。无论是希望快速了解领域动态，还是寻找可复现的基准模型进行二次开发，用户都能在这里找到有价值的参考实现。项目不仅提供论文链接和对应代码仓库地址，还持续通过自动化手段每日更新最新成果，并鼓励社区共同贡献缺失条目。其结构清晰、分类明确，兼具学术严谨性与工程实用性，是进入该交叉研究领域的高效起点。","For English reader,please refer to [English Version](https:\u002F\u002Fgithub.com\u002FIIT-Lab\u002FPaper-with-Code-of-Wireless-communication-Based-on-DL\u002Fblob\u002Fmaster\u002FEnglish%20version.md).\n\n随着深度学习的发展，使用深度学习解决相关通信领域问题的研究也越来越多。作为一名通信专业的研究生，如果实验室没有相关方向的代码积累，入门并深入一个新的方向会十分艰难。同时，大部分通信领域的论文不会提供开源代码，reproducible research比较困难。\n\u003Cbr>\n基于深度学习的通信论文这几年飞速增加，明显能感觉这些论文的作者更具开源精神。本项目专注于整理在通信中应用深度学习，并公开了相关源代码的论文。\n\u003Cbr>\n个人关注的领域和精力有限，这个列表不会那么完整。**如果你知道一些相关的开源论文，但不在此列表中，非常欢迎添加在issue当中**，为community贡献一份力量。欢迎交流^_^\n\u003Cbr>\n**温馨提示:watch相较于star更容易得到更新通知 。**\n\u003Cbr>\nTODO \n\n- [x] 按不同小方向分类\n- [x] 论文添加下载链接\n- [x] 增加更多相关论文代码\n  * 在[daily_arxiv](https:\u002F\u002Fgithub.com\u002Fzhuwenxing\u002Fdaily_arxiv)这个repo下会以daily为尺度更新`eess.SP`和`cs.IT`分类下开源的代码论文\n  * 该Repo通过爬虫+Github Action实现每日自动更新\n- [ ] 传统通信论文代码列表\n- [ ] “通信+DL”论文列表（引用较高，可以没有代码）\n\n\n## 目录 （Contents)\n\n- [Topics](#topics)\n  + [Machine\u002Fdeep learning for physical layer optimization](#physical-layer-optimization)\n  + [Resource, power and network optimization using machine learning techniques](#resource-and-network-optimization)\n  + [Distributed learning algorithms over communication networks](#distributed-learning-algorithms-over-communication-networks)\n  + [Multiple access scheduling  and routing using machine learning techniques](#multiple-access-scheduling--and-routing-using-machine-learning-techniques)\n  + [Machine learning for network slicing, network virtualization, and software-defined networking](#machine-learning-for--software-defined-networking)\n  + [Machine learning for emerging communication systems and applications (e.g., IoT, edge computing, caching, smart cities, vehicular networks, and localization)](#machine-learning-for-emerging-communication-systems-and-applications)\n  + [Secure machine learning over communication networks](#secure-machine-learning-over-communication-networks)\n\n\n\n\n## Topics\n\n### Physical layer optimization\n\n| Paper                                                        | Code                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[Online Meta-Learning For Hybrid Model-Based Deep Receivers](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.14359)|[meta-deepsic](https:\u002F\u002Fgithub.com\u002Ftomerraviv95\u002Fmeta-deepsic)|\n|[Gan-Based Joint Activity Detection and Channel Estimation For Grant-free Random Access](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.01731)|[jadce](https:\u002F\u002Fgithub.com\u002Fdeeeeeeplearning\u002Fjadce)|\n|[sionna: an open-source library for next-generation physical layer research](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.11854)|[sionna](https:\u002F\u002Fgithub.com\u002Fnvlabs\u002Fsionna)|\n|[Deep Learning Aided Robust Joint Channel Classification, Channel Estimation, and Signal Detection for Underwater Optical Communication](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9302692)|[UWOC-JCCESD](https:\u002F\u002Fgithub.com\u002FHuaiyin-Lu\u002FUWOC-JCCESD)|\n|[LoRD-Net: Unfolded Deep Detection Network with Low-Resolution Receivers](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.02993)|[LoRD-Net](https:\u002F\u002Fgithub.com\u002Fskhobahi\u002FLoRD-Net)|\n|[Deep Diffusion Models for Robust Channel Estimation](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.08177)|[diffusion-channels](https:\u002F\u002Fgithub.com\u002Futcsilab\u002Fdiffusion-channels)|\n|[A Channel Coding Benchmark for Meta-Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=DjzPaX8AT0z)|[MetaCC](https:\u002F\u002Fgithub.com\u002Fruihuili\u002FMetaCC)|\n|[On the Feasibility of Modeling OFDM Communication Signals with Unsupervised Generative Adversarial Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.05107)|[OFDM-GAN](https:\u002F\u002Fgithub.com\u002Fusnistgov\u002FOFDM-GAN)|\n|[Robust Learning-Based ML Detection for Massive MIMO Systems with One-Bit Quantized Signals](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9013332)|[LearningML](https:\u002F\u002Fgithub.com\u002FYunseong-Cho\u002FLearningML)|\n|[iterative error decimation for syndrome-based neural network decoders](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.00089)|[ied](https:\u002F\u002Fgithub.com\u002Fkamassury\u002Fied)|\n|[ko codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.12920)|[kocodes](https:\u002F\u002Fgithub.com\u002Fdeepcomm\u002Fkocodes)|\n|[Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01423)|[CDRN-channel-estimation-IRS](https:\u002F\u002Fgithub.com\u002FXML124\u002FCDRN-channel-estimation-IRS)|\n|[Model-Driven Deep Learning for MIMO Detection](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9018199)|[OAMP-Net](https:\u002F\u002Fgithub.com\u002Fhehengtao\u002FOAMP-Net)|\n|[Dilated Convolution based CSI Feedback Compression for Massive MIMO Systems](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.04043)|[DCRNet](https:\u002F\u002Fgithub.com\u002Frecusant7\u002FDCRNet)|\n|[Unsupervised Deep Learning for Massive MIMO Hybrid Beamforming](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.00038)|[HBF-Net](https:\u002F\u002Fgithub.com\u002FHamedHojatian\u002FHBF-Net)|\n|[CLNet: Complex Input Lightweight Neural Network designed for Massive MIMO CSI Feedback](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07507)|[CLNet](https:\u002F\u002Fgithub.com\u002FSIJIEJI\u002FCLNet)|\n|[Block Deep Neural Network-Based Signal Detector for Generalized Spatial Modulation](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.03612)|[B_DNN](https:\u002F\u002Fgithub.com\u002Fhasanabs\u002FB_DNN)|\n|[Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.13607)|[DL-ActiveLearning-BeamAlignment](https:\u002F\u002Fgithub.com\u002Ffoadsohrabi\u002FDL-ActiveLearning-BeamAlignment)|\n|[Data-Driven Deep Learning to Design Pilot and Channel Estimator for Massive MIMO](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9037126)|[Source-Code-X.Ma](https:\u002F\u002Fgithub.com\u002Fgaozhen16\u002FSource-Code-X.Ma)|\n|[Deep Learning Predictive Band Switching in Wireless Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05305)|[Bandswitch-DeepMIMO](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FBandswitch-DeepMIMO)|\n|[RE-MIMO: Recurrent and Permutation Equivariant Neural MIMO Detection](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.00140)|[RE-MIMO](https:\u002F\u002Fgithub.com\u002Fkrpratik\u002FRE-MIMO)|\n|[NOLD: A Neural-Network Optimized Low-Resolution Decoder for LDPC Codes](https:\u002F\u002Fgithub.com\u002FLeo-Chu\u002FNOLD\u002Fblob\u002Fmaster\u002FJCN20-DIV2-067.R2.pdf)|[NOLD](https:\u002F\u002Fgithub.com\u002FLeo-Chu\u002FNOLD)|\n|[A MIMO detector with deep learning in the presence of correlated interference](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8990045)|[project_dcnnmld](https:\u002F\u002Fgithub.com\u002Fskypitcher\u002Fproject_dcnnmld)|\n|[Deep Learning Driven Non-Orthogonal Precoding for Millimeter Wave Communications](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9082619)|[Deep-Learning-Driven-Non-Orthogonal-Precoding-for-Millimeter-Wave-Communications](https:\u002F\u002Fgithub.com\u002FJKLinUESTC\u002FDeep-Learning-Driven-Non-Orthogonal-Precoding-for-Millimeter-Wave-Communications)|\n|[Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9246287)|[DeepUnfolding_WMMSE](https:\u002F\u002Fgithub.com\u002Fhqyyqh888\u002FDeepUnfolding_WMMSE)|\n| [Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.08514.pdf)| [haoyye\u002FOFDM_DNN](https:\u002F\u002Fgithub.com\u002Fhaoyye\u002FOFDM_DNN)        |\n| [Automatic Modulation Classification: A Deep Learning Enabled Approach](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8454504) | [mengxiaomao](https:\u002F\u002Fgithub.com\u002Fmengxiaomao)\u002F[CNN_AMC](https:\u002F\u002Fgithub.com\u002Fmengxiaomao\u002FCNN_AMC) |\n| [Deep Architectures for Modulation Recognition](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.09197.pdf)              | [qieaaa \u002F Deep-Architectures-for-Modulation-Recognition](https:\u002F\u002Fgithub.com\u002Fqieaaa\u002FDeep-Architectures-for-Modulation-Recognition) |\n| [Deep-Waveform: A Learned OFDM Receiver Based on Deep Complex-Valued Convolutional Networkss](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9448141) | [zhongyuanzhao \u002F dl_ofdm](https:\u002F\u002Fgithub.com\u002Fzhongyuanzhao\u002Fdl_ofdm) |\n| [Joint Transceiver Optimization for Wireless Communication PHY with Convolutional NeuralNetwork](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.03242) | [hlz1992\u002FRadioCNN](https:\u002F\u002Fgithub.com\u002Fhlz1992\u002FRadioCNN)      |\n| [5G MIMO Data for Machine Learning: Application to Beam-Selection using Deep Learning](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10112564)| [lasseufpa](https:\u002F\u002Fgithub.com\u002Flasseufpa)\u002F[5gm-data](https:\u002F\u002Fgithub.com\u002Flasseufpa\u002F5gm-data) |\n|[A Two-Fold Group Lasso Based Lightweight Deep Neural Network for Automatic Modulation Classification](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9145050)|[Group-Sparse-DNN-for-AMC](https:\u002F\u002Fgithub.com\u002Ftjuxiaofeng\u002FGroup-Sparse-DNN-for-AMC)|\n|[Recursive CSI Quantization of Time-Correlated MIMO Channels by Deep Learning Classification](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.13560)|[MultiStage-Grassmannian-DNN](https:\u002F\u002Fgithub.com\u002FStefanSchwarzTUW\u002FMultiStage-Grassmannian-DNN)|\n| [Deep Learning for Massive MIMO CSI Feedback](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.08919.pdf)                  | [sydney222 \u002F Python_CsiNet](https:\u002F\u002Fgithub.com\u002Fsydney222\u002FPython_CsiNet) |\n| [Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning](http:\u002F\u002Farxiv.org\u002Fabs\u002F1904.03657) | [TianLin0509\u002FBF-design-with-DL](https:\u002F\u002Fgithub.com\u002FTianLin0509\u002FBF-design-with-DL)|\n| [An Introduction to Deep Learning for the Physical Layer](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1702.00832.pdf)     | [yashcao \u002F RTN-DL-for-physical-layer](https:\u002F\u002Fgithub.com\u002Fyashcao\u002FRTN-DL-for-physical-layer)\u003Cbr \u002F>[musicbeer \u002F Deep-Learning-for-the-Physical-Layer](https:\u002F\u002Fgithub.com\u002Fmusicbeer\u002FDeep-Learning-for-the-Physical-Layer)\u003Cbr \u002F>[helloMRDJ \u002F autoencoder-for-the-Physical-Layer](https:\u002F\u002Fgithub.com\u002FhelloMRDJ\u002Fautoencoder-for-the-Physical-Layer)|\n| [Deep MIMO Detection](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.01151.pdf)                                          | [neevsamuel](https:\u002F\u002Fgithub.com\u002Fneevsamuel)\u002F[DeepMIMODetection](https:\u002F\u002Fgithub.com\u002Fneevsamuel\u002FDeepMIMODetection) |\n| [Learning to Detect](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.07631.pdf)                                         | [neevsamuel](https:\u002F\u002Fgithub.com\u002Fneevsamuel)\u002F[LearningToDetect](https:\u002F\u002Fgithub.com\u002Fneevsamuel\u002FLearningToDetect) |\n| [An iterative BP-CNN architecture for channel decoding](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8259241)        | [liangfei-info](https:\u002F\u002Fgithub.com\u002Fliangfei-info)\u002F[Iterative-BP-CNN](https:\u002F\u002Fgithub.com\u002Fliangfei-info\u002FIterative-BP-CNN) |\n| [On Deep Learning-Based Channel Decoding](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1701.07738.pdf)| [gruberto\u002FDL-ChannelDecoding](https:\u002F\u002Fgithub.com\u002Fgruberto\u002FDL-ChannelDecoding) \u003Cbr\u002F>[Decoder-using-deep-learning](https:\u002F\u002Fgithub.com\u002FVivekRamalingamK\u002FDecoder-using-deep-learning)|\n| [Deep learning-based channel estimation for beamspace mmWave massive MIMO systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8353153)| [hehengtao](https:\u002F\u002Fgithub.com\u002Fhehengtao)\u002F[LDAMP_based-Channel-estimation](https:\u002F\u002Fgithub.com\u002Fhehengtao\u002FLDAMP_based-Channel-estimation) |\n| [Fast Deep Learning for Automatic Modulation Classification](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.05850.pdf)   | [dl4amc](https:\u002F\u002Fgithub.com\u002Fdl4amc)\u002F[source](https:\u002F\u002Fgithub.com\u002Fdl4amc\u002Fsource) |\n| [Deep Learning-Based Channel Estimation](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.05893.pdf)| [Mehran-Soltani](https:\u002F\u002Fgithub.com\u002FMehran-Soltani)\u002F[ChannelNet](https:\u002F\u002Fgithub.com\u002FMehran-Soltani\u002FChannelNet) |\n|[Sparsely Connected Neural Network for Massive MIMO Detection](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=8780959)|[MIMO_Detection](https:\u002F\u002Fgithub.com\u002FNobleLee\u002FMIMO_Detection)|\n| [Deepcode: Feedback Codes via Deep Learning](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1807.00801.pdf)                | https:\u002F\u002Fgithub.com\u002Fhyejikim1\u002FDeepcode\u003Cbr>https:\u002F\u002Fgithub.com\u002Fyihanjiang\u002Ffeedback_code |\n|[MIST: A Novel Training Strategy for Low-latency Scalable Neural Net Decoders](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.08990.pdf)|[MIST_CNN_Decoder](https:\u002F\u002Fgithub.com\u002Fkryashashwi\u002FMIST_CNN_Decoder)|\n|[Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8357902)|[modulation_classif](https:\u002F\u002Fgithub.com\u002FzeroXzero\u002Fmodulation_classif)|\n|[Learning Physical-Layer Communication with Quantized Feedback](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.09252.pdf)|[quantizedfeedback](https:\u002F\u002Fgithub.com\u002Fhenkwymeersch\u002Fquantizedfeedback)|\n|[Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.04448.pdf)|[RLdecoding](https:\u002F\u002Fgithub.com\u002Ffabriziocarpi\u002FRLdecoding)|\n|[Adaptive Neural Signal Detection for Massive MIMO](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04610)|[mehrdadkhani\u002FMMNet](https:\u002F\u002Fgithub.com\u002Fmehrdadkhani\u002FMMNet)|\n|[CNN-based Precoder and Combiner Design in mmWave MIMO Systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8710287)|[Deep_HybridBeamforming](https:\u002F\u002Fgithub.com\u002Fmeuseabe\u002FDeep_HybridBeamforming)|\n|[Sequential Convolutional Recurrent Neural Networks for Fast Automatic Modulation Classification](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.03050.pdf)|[coming soon](https:\u002F\u002Fgithub.com\u002Fkython)|\n|[Low-Precision Neural Network Decoding of Polar Codes](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8815542)|[low-precision-nnd](https:\u002F\u002Fgithub.com\u002FIgWod\u002Flow-precision-nnd)|\n|[Low-rank mmWave MIMO channel estimation in one-bit receivers](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.09141)|[Low-rank-MIMO-channel-estimation-from-one-bit-measurements](https:\u002F\u002Fgithub.com\u002Fnitinjmyers\u002FLow-rank-MIMO-channel-estimation-from-one-bit-measurements)|\n|[Deep Learning for Massive MIMO with 1-Bit ADCs: When More Antennas Need Fewer Pilots](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.06960)|[1-Bit-ADCs](https:\u002F\u002Fgithub.com\u002FYuZhang-GitHub\u002F1-Bit-ADCs)|\n|[Deep Learning for Direct Hybrid Precoding in Millimeter Wave Massive MIMO Systems](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.13212)|[DL-hybrid-precoder](https:\u002F\u002Fgithub.com\u002Flxf8519\u002FDL-hybrid-precoder)|\n|[Deep Learning-Based Detector for OFDM-IM](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8684894)|[DeepIM](https:\u002F\u002Fgithub.com\u002FThienVanLuong\u002FDeepIM)|\n|[Deep Learning for Channel Coding via Neural Mutual Information Estimation](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8815464)|[Wireless_encoding_with_MI_estimation](https:\u002F\u002Fgithub.com\u002FFritschek\u002FWireless_encoding_with_MI_estimation)|\n|[Learning the MMSE Channel Estimator](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.05674v3.pdf)|[learning-mmse-est](https:\u002F\u002Fgithub.com\u002Ftum-msv\u002Flearning-mmse-est)|\n|[Neural Network Aided SC Decoder for Polar Codes](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8780605)|[1_NND](https:\u002F\u002Fgithub.com\u002FBruceGaoo\u002F1_NND)|\n|[Exploiting Bi-Directional Channel Reciprocity in Deep Learning for Low Rate Massive MIMO CSI Feedback](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8638509)|[Bi-Directional-Channel-Reciprocity](https:\u002F\u002Fgithub.com\u002FDLinWL\u002FBi-Directional-Channel-Reciprocity)|\n|[Performance Evaluation of Channel Decoding With Deep Neural Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.00727.pdf)|[deep-neural-network-decoder](https:\u002F\u002Fgithub.com\u002Flevylv\u002Fdeep-neural-network-decoder)|\n|[Decoder-in-the-Loop: Genetic Optimization-based LDPC Code Design](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.03128)|[Genetic-Algorithm-based-LDPC-Code-Design](https:\u002F\u002Fgithub.com\u002FAhmedElkelesh\u002FGenetic-Algorithm-based-LDPC-Code-Design)|\n|[Benchmarking End-to-end Learning of MIMO Physical-Layer Communication](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.09718)|[DeepLearning_MIMO](https:\u002F\u002Fgithub.com\u002FJSChalmers\u002FDeepLearning_MIMO)|\n|[Learned Conjugate Gradient Descent Network for Massive MIMO Detection](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03814)|[LcgNet](https:\u002F\u002Fgithub.com\u002FYiWei0129\u002FLcgNet)|\n|[Trainable Projected Gradient Detector for Massive Overloaded MIMO Channels: Data-driven Tuning Approach](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.10044)|[overloaded_MIMO](https:\u002F\u002Fgithub.com\u002Fwadayama\u002Foverloaded_MIMO)|\n|[Deep Soft Interference Cancellation for MIMO Detection](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9054732)|[DeepSIC](https:\u002F\u002Fgithub.com\u002Fnirshlezinger1\u002FDeepSIC)|\n|[Deep unfolding of the weighted MMSE algorithm](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.08448.pdf)|[WMMSE-deep-unfolding](https:\u002F\u002Fgithub.com\u002Flpkg\u002FWMMSE-deep-unfolding)|\n|[Deep Learning for Direction of Arrival Estimation via Emulation of Large Antenna Arrays](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.13824)|[DoA with DNN via Emulation of Antenna Arrays](https:\u002F\u002Fgitlab.com\u002Fmiriyugl\u002Fdoa-with-dnn-via-emulation-of-antenna-arrays)|\n|[Acquiring Measurement Matrices via Deep Basis Persuit for Sparse Channel Estimation in mmWave Massive MIMO Systems](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.05177)|[DeepBP-AE](https:\u002F\u002Fgithub.com\u002FPengxia-Wu\u002FDeepBP-AE)|\n|[Deep Learning for SVD and Hybrid Beamforming](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9130130)|[DL_SVD_BF](https:\u002F\u002Fwww.dropbox.com\u002Fsh\u002Fv0gs7ba0qq5x168\u002FAACyqRoCz5m3fhpF-azkbn3Qa?dl=0)|\n|[Neural Mutual Information Estimation for Channel Coding: State-of-the-Art Estimators, Analysis, and Performance Comparison](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.16015)|[Reverse-Jensen_MI_estimation](https:\u002F\u002Fgithub.com\u002FFritschek\u002FReverse-Jensen_MI_estimation)|\n|[Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO Systems](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.12265)|[Codes-for-Deep-Transfer-Learning-Based-Downlink-Channel-Prediction-for-FDD-Massive-MIMO-Systems](https:\u002F\u002Fgithub.com\u002Fyangyuwenyang\u002FCodes-for-Deep-Transfer-Learning-Based-Downlink-Channel-Prediction-for-FDD-Massive-MIMO-Systems)|\n|[Channel Estimation for One-Bit Multiuser Massive MIMO Using Conditional GAN](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.11435)|[Channel_Estimation_cGAN](https:\u002F\u002Fgithub.com\u002FYudiDong\u002FChannel_Estimation_cGAN)|\n|[A Model-Driven Deep Learning Method for Normalized Min-Sum LDPC Decoding](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9145237)|[A-Model-Driven-Deep-Learning-Method-for-Normalized-Min-Sum-LDPC-Decoding](https:\u002F\u002Fgithub.com\u002Ftjuxiaofeng\u002FA-Model-Driven-Deep-Learning-Method-for-Normalized-Min-Sum-LDPC-Decoding)|\n|[Complex-Valued Convolutions for Modulation Recognition using Deep Learning](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9145469)|[Complex_Convolutions](https:\u002F\u002Fgithub.com\u002FJakobKrzyston\u002FComplex_Convolutions)|\n|[Generative Adversarial Estimation of Channel Covariance in Vehicular Millimeter Wave Systems](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.02208)|[GAN-cov-matrix](https:\u002F\u002Fgithub.com\u002Flxf8519\u002FGAN-cov-matrix)|\n|[Deep Learning for Beamspace Channel Estimation in Millimeter-Wave Massive MIMO Systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9207745)|[Simulation Codes](http:\u002F\u002Foa.ee.tsinghua.edu.cn\u002Fdailinglong\u002Fpublications\u002Fpublications.html)|\n|[Deep Learning for Polar Codes over Flat Fading Channels](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8669025)|[polarOverFlatFading](https:\u002F\u002Fgithub.com\u002Fade-irawan\u002FpolarOverFlatFading)|\n|[Aggregated Network for Massive MIMO CSI Feedback](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.06618)|[ACRNet](https:\u002F\u002Fgithub.com\u002FKylin9511\u002FACRNet)|\n| [Convolutional Radio Modulation Recognition Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1602.04105.pdf)          | [chrisruk](https:\u002F\u002Fgithub.com\u002Fchrisruk)\u002F[cnn](https:\u002F\u002Fgithub.com\u002Fchrisruk\u002Fcnn)\u003Cbr \u002F>[qieaaa \u002F Singal-CNN](https:\u002F\u002Fgithub.com\u002Fqieaaa\u002FSingal-CNN) |\n| [Turbo Autoencoder: Deep learning based channel code for point-to-point communication channels](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.03038.pdf)  | [yihanjiang](https:\u002F\u002Fgithub.com\u002Fyihanjiang)\u002F[turboae](https:\u002F\u002Fgithub.com\u002Fyihanjiang\u002Fturboae) |\n|[Multi-resolution CSI Feedback with deep learning in Massive MIMO System](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.14322)|[CRNet](https:\u002F\u002Fgithub.com\u002FKylin9511\u002FCRNet)|\n|[Spatio-Temporal Representation with Deep Recurrent Network in MIMO CSI Feedback](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8951228)|[ConvlstmCsiNet](https:\u002F\u002Fgithub.com\u002FAries-LXY\u002FConvlstmCsiNet)|\n|[Learn to Compress CSI and Allocate Resources in Vehicular Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.04685)|[Learn-CompressCSI-RA-V2X-Code](https:\u002F\u002Fgithub.com\u002FCooperLWang\u002FLearn-CompressCSI-RA-V2X-Code)|\n|[Deep Learning for TDD and FDD Massive MIMO: Mapping Channels in Space and Frequency](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.03761.pdf)|[DL-Massive-MIMO](https:\u002F\u002Fgithub.com\u002Fmalrabeiah\u002FDL-Massive-MIMO)|\n|[Deep UL2DL: Channel Knowledge Transfer from Uplink to Downlink](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.07518)|[UL2DL](https:\u002F\u002Fgithub.com\u002Fsafarisadegh\u002FUL2DL)|\n|[Towards Optimally Efficient Tree Search with Deep Temporal Difference Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.02420)|[hats](https:\u002F\u002Fgithub.com\u002Fskypitcher\u002Fhats)|\n|[Enabling Large Intelligent Surfaces with Compressive Sensing and Deep Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.10136)|[LIS-DeepLearning](https:\u002F\u002Fgithub.com\u002FAbdelrahman-Taha\u002FLIS-DeepLearning)|\n|[A CNN-Based End-to-End Learning Framework Towards Intelligent Communication Systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8755977)|[Deepcom](https:\u002F\u002Fgithub.com\u002FZhangKaiyao\u002FDeepcom)|\n| [Communication Algorithms via Deep Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.09317) | [yihanjiang](https:\u002F\u002Fgithub.com\u002Fyihanjiang)\u002F[commviadl](https:\u002F\u002Fgithub.com\u002Fyihanjiang\u002FSequential-RNN-Decoder) |\n|[Learning to Communicate in a Noisy Environment](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.09630)|[echo](https:\u002F\u002Fgithub.com\u002Fml4wireless\u002Fecho)|\n|[Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.09945)|[meta-autoencoder](https:\u002F\u002Fgithub.com\u002Fkclip\u002Fmeta-autoencoder)|\n|[Deep energy autoencoder for noncoherent multicarrier MU-SIMO systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9036067)|[energy_autoencoder](https:\u002F\u002Fgithub.com\u002FThienVanLuong\u002Fenergy_autoencoder)|\n|[Deep Channel Learning For Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.11085)|[deepChannelLearning4RIS](https:\u002F\u002Fgithub.com\u002Fmeuseabe\u002FdeepChannelLearning4RIS)|\n|[Deep learning based end-to-end wireless communication systems with conditional GAN as unknown channel](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.02551.pdf)|[End2End_GAN](https:\u002F\u002Fgithub.com\u002Fhaoyye\u002FEnd2End_GAN)|\n|[RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.09002)|[RadioUNet](https:\u002F\u002Fgithub.com\u002FRonLevie\u002FRadioUNet)|\n|[Deep learning aided multicarrier systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9271932)|[multicarrier_autoencoder](https:\u002F\u002Fgithub.com\u002FThienVanLuong\u002Fmulticarrier_autoencoder)|\n\n### Resource and network optimization \n| Paper                                                        | Code                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[Resource Allocation based on Graph Neural Networks in Vehicular Communications](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9322537)|[Globecom2020-ResourceAllocationGNN](https:\u002F\u002Fgithub.com\u002FCoolzyh\u002FGlobecom2020-ResourceAllocationGNN)|\n|[An Unsupervised Deep Unrolling Framework for Constrained Optimization Problems in Wireless Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.08994)|[USRMNet-HWGCN](https:\u002F\u002Fgithub.com\u002Fsoulven\u002Fusrmnet-hwgcn)|\n|[Power Allocation for Wireless Federated Learning using Graph Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.07480)|[WirelessFL-PDGNet](https:\u002F\u002Fgithub.com\u002Fbl166\u002Fwirelessfl-pdgnet)|\n|[Delay-Oriented Distributed Scheduling Using Graph Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.07017)|[gcn-dql](https:\u002F\u002Fgithub.com\u002Fzhongyuanzhao\u002Fgcn-dql)|\n|[Deep Learning Based MAC via Joint Channel Access and Rate Adaptation](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.10307)|[Wireless-Signal-Strength-on-2.4GHz-WSS24-dataset](https:\u002F\u002Fgithub.com\u002Fpostman511\u002FWireless-Signal-Strength-on-2.4GHz-WSS24-dataset)|\n|[wireless link scheduling via graph representation learning: a comparative study of different supervision levels](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.01722)|[LinkSchedulingGNNs_SupervisionStudy](https:\u002F\u002Fgithub.com\u002Fnavid-naderi\u002FLinkSchedulingGNNs_SupervisionStudy)|\n|[Distributed Scheduling using Graph Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.09430)|[distgcn](https:\u002F\u002Fgithub.com\u002Fzhongyuanzhao\u002Fdistgcn)|\n|[DeepBeam: Deep Waveform Learning for Coordination-Free Beam Management in mmWave Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.14350)|[deepbeam](https:\u002F\u002Fgithub.com\u002Fwineslab\u002Fdeepbeam)|\n|[Graph Embedding-Based Wireless Link Scheduling With Few Training Samples](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.02871)|[graph_embedding_link_scheduling](https:\u002F\u002Fgithub.com\u002Fmengyuan-lee\u002Fgraph_embedding_link_scheduling)|\n| [Energy Efficiency in Reinforcement Learning for Wireless Sensor Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1812.02538.pdf)| [mkoz71 \u002F Energy-Efficiency-in-Reinforcement-Learning](https:\u002F\u002Fgithub.com\u002Fmkoz71\u002FEnergy-Efficiency-in-Reinforcement-Learning) |\n| [Learning to optimize: Training deep neural networks for wireless resource management](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.09412)| [Haoran-S \u002F DNN_WMMSE](https:\u002F\u002Fgithub.com\u002FHaoran-S\u002FDNN_WMMSE) |\n| [Implications of Decentralized Q-learning Resource Allocation in Wireless Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1705.10508.pdf) | [wn-upf \u002F decentralized_qlearning_resource_allocation_in_wns](https:\u002F\u002Fgithub.com\u002Fwn-upf\u002Fdecentralized_qlearning_resource_allocation_in_wns) |\n| [Deep Q-Learning for Self-Organizing Networks Fault Management and Radio Performance Improvement](https:\u002F\u002Farxiv.org\u002Fabs\u002F1707.02329) | [farismismar \u002F Deep-Q-Learning-SON-Perf-Improvement](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FDeep-Q-Learning-SON-Perf-Improvement) |\n| [Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.03269.pdf) | [farismismar \u002F Q-Learning-Power-Control](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FQ-Learning-Power-Control) |\n| [Deep Learning for Optimal Energy-Efficient Power Control in Wireless Interference Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1812.06920.pdf) | [bmatthiesen \u002F deep-EE-opt](https:\u002F\u002Fgithub.com\u002Fbmatthiesen\u002Fdeep-EE-opt) |\n| [Actor-Critic-Based Resource Allocation for Multi-modal Optical Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8644190) | [BoyuanYan \u002F Actor-Critic-Based-Resource-Allocation-for-Multimodal-Optical-Networks](https:\u002F\u002Fgithub.com\u002FBoyuanYan\u002FActor-Critic-Based-Resource-Allocation-for-Multimodal-Optical-Networks)|\n| [Transmit Power Control Using Deep Neural Network for Underlay Device-to-Device Communication](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8428396) | [seotaijiya](https:\u002F\u002Fgithub.com\u002Fseotaijiya)\u002F[TPC_D2D](https:\u002F\u002Fgithub.com\u002Fseotaijiya\u002FTPC_D2D) |\n|[Power Allocation in Multi-Cell Networks Using Deep Reinforcement Learning](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8690757)|[qfnet](https:\u002F\u002Fgithub.com\u002Fkangcp\u002Fqfnet)|\n|[Deep Learning in Downlink Coordinated Multipoint in New Radio Heterogeneous Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1812.03421.pdf)|[DL-CoMP-Machine-Learning](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FDL-CoMP-Machine-Learning)|\n|[Deep Reinforcement Learning for Resource Allocation in V2V Communications](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.00968)|https:\u002F\u002Fgithub.com\u002Fhaoyye\u002FResourceAllocationReinforcementLearning|\n| [AIF: An Artificial Intelligence Framework for Smart Wireless Network Management](http:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8119495\u002Fmetrics) | [caogang](https:\u002F\u002Fgithub.com\u002Fcaogang)\u002F[WlanDqn](https:\u002F\u002Fgithub.com\u002Fcaogang\u002FWlanDqn) |\n| [Deep-Learning-Power-Allocation-in-Massive-MIMO](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.03640)              | [lucasanguinetti \u002F Deep-Learning-Power-Allocation-in-Massive-MIMO](https:\u002F\u002Fgithub.com\u002Flucasanguinetti\u002FDeep-Learning-Power-Allocation-in-Massive-MIMO) |\n|[Machine Learning meets Stochastic Geometry: Determinantal Subset Selection for Wireless Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.00504)|[DPPL](https:\u002F\u002Fgithub.com\u002Fstochastic-geometry\u002FDPPL)|\n|[Learning Based Power Control for mmWave Massive MIMO against Jamming](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8647173)|[Learning-Based-Power-Control-for-mmWave-Massive-MIMO-against-Jamming](https:\u002F\u002Fgithub.com\u002Fxiaozhch5\u002FLearning-Based-Power-Control-for-mmWave-Massive-MIMO-against-Jamming)|\n|[Towards Optimal Power Control via Ensembling Deep Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.10025)|[PCNet-ePCNet](https:\u002F\u002Fgithub.com\u002FShenGroup\u002FPCNet-ePCNet)|\n|[A Graph Neural Network Approach for Scalable Wireless Power Control](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1907.08487.pdf)|[Globecom2019](https:\u002F\u002Fgithub.com\u002Fyshenaw\u002FGlobecom2019)|\n|[Mobility-Aware Centralized Reinforcement Learning for Dynamic Resource Allocation in HetNets](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F335159543_Mobility-Aware_Centralized_Reinforcement_Learning_for_Dynamic_Resource_Allocation_in_HetNets)|[UARA](https:\u002F\u002Fgithub.com\u002FLiuJieShane\u002FUARA)|\n|[Intelligent Resource Allocation in Wireless Communications Systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8961912)|[IRAWCS](https:\u002F\u002Fgithub.com\u002Fseotaijiya\u002FIRAWCS)|\n|[Learning Combinatorial Optimization Algorithms over Graphs](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.01665)|[graph_comb_opt](https:\u002F\u002Fgithub.com\u002FHanjun-Dai\u002Fgraph_comb_opt.git)|\n|[Extending the RISC-V ISA for Efficient RNN-based 5G Radio Resource Management](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12877)|[RNNASIP](https:\u002F\u002Fgithub.com\u002Fandrire\u002FRNNASIP)|\n|[Power Allocation in Multi-user Cellular Networks With Deep Q Learning Approach](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.02979)|[PA_ICC](https:\u002F\u002Fgithub.com\u002Fmengxiaomao\u002FPA_ICC)|\n|[Power Allocation in Multi-User Cellular Networks: Deep Reinforcement Learning Approaches](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.07159)|[PA_TWC](https:\u002F\u002Fgithub.com\u002Fmengxiaomao\u002FPA_TWC)|\n|[Unfolding WMMSE using Graph Neural Networks for Efficient Power Allocation](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.10812)|[Unrolled-WMMSE](https:\u002F\u002Fgithub.com\u002FArCho48\u002FUnrolled-WMMSE)|\n|[Deep Actor-Critic Learning for Distributed Power Control in Wireless Mobile Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.06681)|[Power-Control-asilomar](https:\u002F\u002Fgithub.com\u002Fsinannasir\u002FPower-Control-asilomar)|\n|[Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.07632)|[GNN-Resource-Management](https:\u002F\u002Fgithub.com\u002Fyshenaw\u002FGNN-Resource-Management)|\n|[Contrastive Self-Supervised Learning for Wireless Power Control](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11909)|[ContrastiveSSL_WirelessPowerControl](https:\u002F\u002Fgithub.com\u002Fnavid-naderi\u002FContrastiveSSL_WirelessPowerControl)|\n|[No-Pain No-Gain: DRL Assisted Optimization in Energy-Constrained CR-NOMA Networks](https:\u002F\u002Fgithub.com\u002Fzhiguo-ding\u002FCRNOMA_DDPG\u002Fblob\u002Fmain\u002Fpaper.pdf)|[CRNOMA_DDPG](https:\u002F\u002Fgithub.com\u002Fzhiguo-ding\u002FCRNOMA_DDPG)|\n|[Multicell Power Control under Rate Constraints with Deep Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.03655)|[SRnet-and-SRNet-Heu-for-power-control](https:\u002F\u002Fgithub.com\u002FLeeyyhh\u002FSRnet-and-SRNet-Heu-for-power-control)|\n|[Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.02900)|[Sub6-Preds-mmWave](https:\u002F\u002Fgithub.com\u002Fmalrabeiah\u002FSub6-Preds-mmWave)|\n|[Wireless link adaptation - a hybrid data-driven and model-based approach](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9154263)|[LinkAdaptationCSI](https:\u002F\u002Fgithub.com\u002Flpkg\u002FLinkAdaptationCSI)|\n|[Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.07782)|[ICASSP2021](https:\u002F\u002Fgithub.com\u002FHaoran-S\u002FICASSP2021)|\n| [DeepNap: Data-Driven Base Station Sleeping Operations through Deep Reinforcement Learning](http:\u002F\u002Fnetwork.ee.tsinghua.edu.cn\u002Fniulab\u002Fwp-content\u002Fuploads\u002F2018\u002F10\u002Fdeepnap_CCN.pdf) | [zaxliu](https:\u002F\u002Fgithub.com\u002Fzaxliu)\u002F[deepnap](https:\u002F\u002Fgithub.com\u002Fzaxliu\u002Fdeepnap) | \n|[No-Pain No-Gain: DRL Assisted Optimization in Energy-Constrained CR-NOMA Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2104.06007.pdf)|[CRNOMA_DDPG](https:\u002F\u002Fgithub.com\u002Fzhiguo-ding\u002FCRNOMA_DDPG)|\n\n### Distributed learning algorithms over communication networks\n| Paper                                                        | Code                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[A Scalable Federated Multi-agent Architecture for Networked Connected Communication Network](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.00506)|[Fed-MF-MAL](https:\u002F\u002Fgithub.com\u002Fpaperflight\u002FFed-MF-MAL)|\n|[Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.10282)|[RIS-FL](https:\u002F\u002Fgithub.com\u002Fliuhang1994\u002FRIS-FL)|\n|[Decentralized Statistical Inference with Unrolled Graph Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.01555)|[Learning-based-DOP-Framework](https:\u002F\u002Fgithub.com\u002FIrisWangHe\u002FLearning-based-DOP-Framework)|\n|[Decentralized Scheduling for Cooperative Localization with Deep Reinforcement Learning](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8701533)|[DeepRLVehicularLocalization](https:\u002F\u002Fgithub.com\u002Fhenkwymeersch\u002FDeepRLVehicularLocalization)|\n|[Deep Reinforcement Learning for Distributed Dynamic MISO Downlink-Beamforming Coordination](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9123956)|[DRL_for_DDBC](https:\u002F\u002Fgithub.com\u002FJungangGe\u002FDRL_for_DDBC)|\n| [Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.07394) | [swordest](https:\u002F\u002Fgithub.com\u002Fswordest)\u002F[mec_drl](https:\u002F\u002Fgithub.com\u002Fswordest\u002Fmec_drl) |\n|[Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.13067.pdf)|[FEDL](https:\u002F\u002Fgithub.com\u002Fnhatminh\u002FFEDL)|\n|[Federated Learning over Wireless Networks: Optimization Model Design and Analysis](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8737464)|[OnDevAI](https:\u002F\u002Fgithub.com\u002Fnhatminh\u002FOnDevAI)|\n|[Deep Deterministic Policy Gradient (DDPG)-Based Energy Harvesting Wireless Communications](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8731635)|[Energy-Harvesting-DDPG](https:\u002F\u002Fgithub.com\u002FCrQiu\u002FEnergy-Harvesting-DDPG-)|\n[A joint learning and communications framework for federated learning over wireless networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.07972.pdf)|[Wireless-FL](https:\u002F\u002Fgithub.com\u002Fmzchen0\u002FWireless-FL)|\n\n### Multiple access scheduling  and routing using machine learning techniques\n| Paper                                                        | Code                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[Distributive Dynamic Spectrum Access Through Deep Reinforcement Learning: A Reservoir Computing-Based Approach](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8474348)|[DQN_RC_DSA_IOT2019](https:\u002F\u002Fgithub.com\u002Fhaohsuan2918\u002FDQN_RC_DSA_IOT2019)|\n|[Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8303773)|[DynamicMultiChannelRL](https:\u002F\u002Fgithub.com\u002FGulatiAditya\u002FDynamicMultiChannelRL)|\n| [Deep multi-user reinforcement learning for dynamic spectrum access in multichannel wireless networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8254101)| [shkrwnd](https:\u002F\u002Fgithub.com\u002Fshkrwnd)\u002F[Deep-Reinforcement-Learning-for-Dynamic-Spectrum-Access](https:\u002F\u002Fgithub.com\u002Fshkrwnd\u002FDeep-Reinforcement-Learning-for-Dynamic-Spectrum-Access) |\n|[Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8303773)|[DynamicMultiChannelRL](https:\u002F\u002Fgithub.com\u002FGulatiAditya\u002FDynamicMultiChannelRL)|\n|[Reinforcement Learning Based Scheduling Algorithm for Optimizing Age of Information in Ultra Reliable Low Latency Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8969641)|[AoI_RL](https:\u002F\u002Fgithub.com\u002Faelgabli\u002FAoI_RL)|\n|[Enhancing WiFi Multiple Access Performance with Federated Deep Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07019)|[FLDRL-in-Wireless-Communication](https:\u002F\u002Fgithub.com\u002FMauriyin\u002FFLDRL-in-Wireless-Communication)|\n|[A Clustering Approach to Wireless Scheduling](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9154271)|[A_Clustering_Approach_to_Wireless_Scheduling](https:\u002F\u002Fgithub.com\u002Fwilltop\u002FA_Clustering_Approach_to_Wireless_Scheduling)|\n|[Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8665952)|[DLMA](https:\u002F\u002Fgithub.com\u002FYidingYu\u002FDLMA)|\n| [A deep-reinforcement learning approach for software-defined networking routing optimization](https:\u002F\u002Farxiv.org\u002Fabs\u002F1709.07080) | [knowledgedefinednetworking \u002F a-deep-rl-approach-for-sdn-routing-optimization](https:\u002F\u002Fgithub.com\u002Fknowledgedefinednetworking\u002Fa-deep-rl-approach-for-sdn-routing-optimization) |\n| [Spatial deep learning for wireless scheduling](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.01486)               | [willtop](https:\u002F\u002Fgithub.com\u002Fwilltop)\u002F[Spatial_DeepLearning_Wireless_Scheduling](https:\u002F\u002Fgithub.com\u002Fwilltop\u002FSpatial_DeepLearning_Wireless_Scheduling) |\n| [Transformer based Online Bayesian Neural Networks for Grant Free Uplink Access in CRAN with Streaming Variational Inference](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9540910)               | [CRAN_MIMO_VI](https:\u002F\u002Fgithub.com\u002Fjhanilesh96\u002FCRAN_MIMO_VI) |\n\n### Machine learning for  software-defined networking\n| Paper                                                        | Code                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n| [DELMU: A Deep Learning Approach to Maximising the Utility of Virtualised Millimetre-Wave Backhauls](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-19945-6_10)| [ruihuili \u002F DELMU](https:\u002F\u002Fgithub.com\u002Fruihuili\u002FDELMU)        |\n|[ns-3 meets OpenAI Gym: The Playground for Machine Learning in Networking Research](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.03943.pdf)|[ns3-gym](https:\u002F\u002Fgithub.com\u002Ftkn-tub\u002Fns3-gym)|\n\n### Machine learning for emerging communication systems and applications\n| Paper                                                        | Code                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[Deep Reinforcement Learning with Communication Transformer for Adaptive Live Streaming in Wireless Edge Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9605672)|[SACCT](https:\u002F\u002Fgithub.com\u002FwsyCUHK\u002FSACCT)|\n|[Dependent Task Offloading for Edge Computing based on Deep Reinforcement Learning](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9627763)|[RLTaskOffloading](https:\u002F\u002Fgithub.com\u002Flinkpark\u002FRLTaskOffloading)|\n|[Fast Adaptive Computation Offloading in Edge Computing based on Meta Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.02033)|[metarl-offloading](https:\u002F\u002Fgithub.com\u002Flinkpark\u002Fmetarl-offloading)|\n|[Lyapunov-guided Deep Reinforcement Learning for Stable Online Computation Offloading in Mobile-Edge Computing Networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9449944)|[LyDROO](https:\u002F\u002Fgithub.com\u002Frevenol\u002FLyDROO)|\n|[Proactive and AoI-aware Failure Recovery for Stateful NFV-enabled Zero-Touch 6G Networks: Model-Free DRL Approach](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.03817)|[ZT-PFR](https:\u002F\u002Fgithub.com\u002Fwildsky95\u002FZT-PFR)|\n|[Multi-UAV Path Planning for Wireless Data Harvesting with Deep Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.12461)|[uav_data_harvesting](https:\u002F\u002Fgithub.com\u002Fhbayerlein\u002Fuav_data_harvesting)|\n|[Spectrum sharing in vehicular networks based on multi-agent reinforcement learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.02910)|[MARLspectrumSharingV2X](https:\u002F\u002Fgithub.com\u002FAlexVic\u002FMARLspectrumSharingV2X)|\n|[An Open-Source Framework for Adaptive Traffic Signal Control](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.00395.pdf)|[docwza\u002Fsumolights](https:\u002F\u002Fgithub.com\u002Fdocwza\u002Fsumolights)|\n|[CSI-based Positioning in Massive MIMO systems using Convolutional Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.11523)|[MaMIMO_CSI_with_CNN_positioning](https:\u002F\u002Fgithub.com\u002Fsibrendebast\u002FMaMIMO_CSI_with_CNN_positioning)|\n|[BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9145068)|[BottleNetPlusPlus](https:\u002F\u002Fgithub.com\u002Fshaojiawei07\u002FBottleNetPlusPlus)|\n|[Deep reinforcement learning for online computation offloading in wireless powered mobile-edge computing networks](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8771176\u002F)|[DROO](https:\u002F\u002Fgithub.com\u002Frevenol\u002FDROO)|\n|[MaMIMO CSI-based positioning using CNNs: Peeking inside the black box](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.04581)|[inside-the-black-box](https:\u002F\u002Fgithub.com\u002Fsibrendebast\u002Finside-the-black-box)|\n|[Graph Neural Network for Large-Scale Network Localization](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11653)|[GNN-For-localization](https:\u002F\u002Fgithub.com\u002FYanzongzi\u002FGNN-For-localization)|\n|[Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.02033)|[metarl-offloading](https:\u002F\u002Fgithub.com\u002Flinkpark\u002Fmetarl-offloading)|\n|[RF-based Direction Finding of UAVs Using DNN](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.01154)|https:\u002F\u002Fgithub.com\u002FLahiruJayasinghe\u002FDeepDOA|\n### Secure machine learning over communication networks\n| Paper                                                        | Code                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n| [Physical Adversarial Attacks Against End-to-End Autoencoder Communication Systems](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.08391)| https:\u002F\u002Fgithub.com\u002Fmeysamsadeghi\u002FSecurity-and-Robustness-of-Deep-Learning-in-Wireless-Communication-Systems |\n|[Deep Learning for the Gaussian Wiretap Channel](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8761681)|[NN_GWTC](https:\u002F\u002Fgithub.com\u002FFritschek\u002FNN_GWTC)|\n\n\n\n# \"通信+DL\"论文（无代码)\u002FPaper List Without Code\n说明：论文主要来源于arxiv中[Signal Processing](https:\u002F\u002Farxiv.org\u002Flist\u002Feess.SP\u002Frecent)和[Information Theory](https:\u002F\u002Farxiv.org\u002Flist\u002Fcs.IT\u002Frecent)\n* [Robust Data Detection for MIMO Systems with One-Bit ADCs: A Reinforcement Learning Approach](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.12546.pdf)\n* [Distributed Power Control for Large Energy Harvesting Networks: A Multi-Agent Deep Reinforcement Learning Approach](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.00601.pdf)\n* [Machine Learning for Wireless Communication Channel Modeling: An Overview](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11277-019-06275-4)\n* [Sum Spectral Efficiency Maximization in Massive MIMO Systems: Benefits from Deep Learning](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.08163.pdf)\n\n# 数据集\u002FDatabase\n* [Wireless-Signal-Strength-on-2.4GHz-WSS24-dataset](https:\u002F\u002Fgithub.com\u002Fpostman511\u002FWireless-Signal-Strength-on-2.4GHz-WSS24-dataset):A Dataset For RSSI Analysis\n* [MetaCC](https:\u002F\u002Fgithub.com\u002Fruihuili\u002FMetaCC):[A Channel Coding Benchmark for Meta-Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=DjzPaX8AT0z)\n* [thymio-radio-map](https:\u002F\u002Fgithub.com\u002Farthurgassner\u002Fthymio-radio-map): [OpenCSI: An Open-Source Dataset for Indoor Localization Using CSI-Based Fingerprinting](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.07963)\n* [The DeepMIMO Dataset](http:\u002F\u002Fdeepmimo.net\u002F) and  the corresponding paper [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.06435)\n* [RAYMOBTIME](https:\u002F\u002Fwww.lasse.ufpa.br\u002Fraymobtime\u002F):Raymobtime is a methodology for collecting realistic datasets for simulating wireless communications. It uses ray-tracing and 3D scenarios with mobility and time evolution, for obtaining consistency over time, frequency and space. \n* [MASSIVE MIMO CSI MEASUREMENTS](https:\u002F\u002Fhomes.esat.kuleuven.be\u002F~sdebast\u002Fcsi_measurements.html)\n* [SM-CsiNet+ and PM-CsiNet+](https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1_lAMLk_5k1Z8zJQlTr5NRnSD6ACaNRtj?usp=sharing):来自论文[Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.06007.pdf)\n* [An open online real modulated dataset](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1biDooH6E81Toxa2u4D3p2g):来自论文[Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.04297.pdf)。\n  > To the best of our knowledge,this is the first open dataset of real modulated signals\n  > for wireless communication systems.\n* [RF DATASETS FOR MACHINE LEARNING](https:\u002F\u002Fwww.deepsig.io\u002Fdatasets)\n* [open datase](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1rS143bEDaOTEiCneXE67dg#list\u002Fpath=%2F):来自论文[Signal Demodulation With Machine Learning\nMethods for Physical Layer Visible Light\nCommunications: Prototype Platform,\nOpen Dataset, and Algorithms](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=8661606&tag=1)\n  >The dataset is collected in real physical environment, and the channel suffers from many factors such as limited LED bandwidth, multi-reflection,spurious or continuous jamming, etc.\n# 学者个人主页\u002FResearcher Homepage\n* [Dr. Zhen Gao ( 高 镇 )](https:\u002F\u002Fgaozhen16.eu.org\u002F):\n  - Wireless Communications\n  - Channel Estimation of mmWave\u002FTHz Hybrid Massive MIMO\n  - Sparse Signal Processing\n  - Deep Learning based Solutions in Wireless Systems\n* [Ahmed Alkhateeb](http:\u002F\u002Fwww.aalkhateeb.net\u002Findex.html):Research Interests\n  - Millimeter Wave and Massive MIMO Communication\n  - Vehicular and Drone Communication Systems\n  - Applications of Machine Learning in Wireless Communication\n  - Building Mobile Communication Systems that Work in Reality!\n* [Emil Björnson](https:\u002F\u002Febjornson.com\u002Fresearch\u002F):\n  He performs research on multi-antenna communications, Massive MIMO, radio resource allocation, energy-efficient communications, and network design. \n* [Leo-Chu](https:\u002F\u002Fgithub.com\u002FLeo-Chu):His research interests are in the theoretical and algorithmic studies in random matrix theory, nonconvex optimization, deep learning, as well as their applications in wireless communications, bioengineering, and smart grid.\n# 有用的网页和材料\u002FUseful Websites and Materials\n* [Graph-based Deep Learning for Communication Networks: A Survey](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.02533): [GNN-Communication-Networks](https:\u002F\u002Fgithub.com\u002Fjwwthu\u002FGNN-Communication-Networks)\n* [机器学习和通信结合论文列表\u002FResearch Library ](https:\u002F\u002Fmlc.committees.comsoc.org\u002Fresearch-library\u002F)\n* [Best Readings in Machine Learning in Communications](https:\u002F\u002Fwww.comsoc.org\u002Fpublications\u002Fbest-readings\u002Fmachine-learning-communications)\n* [Communication Systems, Linköping University, LIU](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCOrjRoYJPqGiR1SZvU3xcYQ\u002Fvideos)\n* [Codes for Intelligent reflecting surface (IRS)](https:\u002F\u002Fgithub.com\u002Fken0225\u002FRIS_Codes_Collection)\n* [awesome-ml4co](https:\u002F\u002Fgithub.com\u002FThinklab-SJTU\u002Fawesome-ml4co):a list of papers that utilize machine learning technologies to solve combinatorial optimization problems.\n* [Simulation Code from comsoc](https:\u002F\u002Fmlc.committees.comsoc.org\u002Fpapers-with-code\u002F)\n\n\u003Cbr>贡献者\u002FContributors：\n* WxZhu:\n  - [Github](https:\u002F\u002Fgithub.com\u002Fzhuwenxing)  \n  - Email:wenxingzhu@shu.edu.cn\n* [LinTian](https:\u002F\u002Fgithub.com\u002FTianLin0509)\n* [HongtaiChen](https:\u002F\u002Fgithub.com\u002FHongtaiChen)\n* [yihanjiang](https:\u002F\u002Fgithub.com\u002Fyihanjiang)\n* wu huaming:\n  - Email:whming@tju.edu.cn\n\n\u003Cbr>版本更新\u002FVersion Update：\n\n1. 第一版完成\u002FFirst Version：2019-02-21\n2. 分类整理及链接补全\u002FFirst Version: 2021-04-14 via [Yokoxue](https:\u002F\u002Fgithub.com\u002Fyokoxue)\n","对于英文读者，请参阅[英文版](https:\u002F\u002Fgithub.com\u002FIIT-Lab\u002FPaper-with-Code-of-Wireless-communication-Based-on-DL\u002Fblob\u002Fmaster\u002FEnglish%20version.md)。\n\n随着深度学习的发展，使用深度学习解决相关通信领域问题的研究也越来越多。作为一名通信专业的研究生，如果实验室没有相关方向的代码积累，入门并深入一个新的方向会十分艰难。同时，大部分通信领域的论文不会提供开源代码，reproducible research比较困难。\n\u003Cbr>\n基于深度学习的通信论文这几年飞速增加，明显能感觉这些论文的作者更具开源精神。本项目专注于整理在通信中应用深度学习，并公开了相关源代码的论文。\n\u003Cbr>\n个人关注的领域和精力有限，这个列表不会那么完整。**如果你知道一些相关的开源论文，但不在此列表中，非常欢迎添加在issue当中**，为community贡献一份力量。欢迎交流^_^\n\u003Cbr>\n**温馨提示:watch相较于star更容易得到更新通知 。**\n\u003Cbr>\nTODO \n\n- [x] 按不同小方向分类\n- [x] 论文添加下载链接\n- [x] 增加更多相关论文代码\n  * 在[daily_arxiv](https:\u002F\u002Fgithub.com\u002Fzhuwenxing\u002Fdaily_arxiv)这个repo下会以daily为尺度更新`eess.SP`和`cs.IT`分类下开源的代码论文\n  * 该Repo通过爬虫+Github Action实现每日自动更新\n- [ ] 传统通信论文代码列表\n- [ ] “通信+DL”论文列表（引用较高，可以没有代码）\n\n\n## 目录 （Contents)\n\n- [Topics](#topics)\n  + [Machine\u002Fdeep learning for physical layer optimization](#physical-layer-optimization)\n  + [Resource, power and network optimization using machine learning techniques](#resource-and-network-optimization)\n  + [Distributed learning algorithms over communication networks](#distributed-learning-algorithms-over-communication-networks)\n  + [Multiple access scheduling  and routing using machine learning techniques](#multiple-access-scheduling--and-routing-using-machine-learning-techniques)\n  + [Machine learning for network slicing, network virtualization, and software-defined networking](#machine-learning-for--software-defined-networking)\n  + [Machine learning for emerging communication systems and applications (e.g., IoT, edge computing, caching, smart cities, vehicular networks, and localization)](#machine-learning-for-emerging-communication-systems-and-applications)\n  + [Secure machine learning over communication networks](#secure-machine-learning-over-communication-networks)\n\n\n\n\n## Topics\n\n### Physical layer optimization\n\n| 论文                                                        | 代码                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[混合模型深度接收机的在线元学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.14359)|[meta-deepsic](https:\u002F\u002Fgithub.com\u002Ftomerraviv95\u002Fmeta-deepsic)|\n|[基于GAN的免调度随机接入联合活动检测与信道估计](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.01731)|[jadce](https:\u002F\u002Fgithub.com\u002Fdeeeeeeplearning\u002Fjadce)|\n|[sionna：用于下一代物理层研究的开源库](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.11854)|[sionna](https:\u002F\u002Fgithub.com\u002Fnvlabs\u002Fsionna)|\n|[深度学习辅助的水下光通信鲁棒联合信道分类、信道估计和信号检测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9302692)|[UWOC-JCCESD](https:\u002F\u002Fgithub.com\u002FHuaiyin-Lu\u002FUWOC-JCCESD)|\n|[LoRD-Net：低分辨率接收机中的展开式深度检测网络](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.02993)|[LoRD-Net](https:\u002F\u002Fgithub.com\u002Fskhobahi\u002FLoRD-Net)|\n|[用于鲁棒信道估计的深度扩散模型](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.08177)|[diffusion-channels](https:\u002F\u002Fgithub.com\u002Futcsilab\u002Fdiffusion-channels)|\n|[元学习的信道编码基准](https:\u002F\u002Fopenreview.net\u002Fforum?id=DjzPaX8AT0z)|[MetaCC](https:\u002F\u002Fgithub.com\u002Fruihuili\u002FMetaCC)|\n|[无监督生成对抗网络建模OFDM通信信号的可行性研究](https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.05107)|[OFDM-GAN](https:\u002F\u002Fgithub.com\u002Fusnistgov\u002FOFDM-GAN)|\n|[针对单比特量化信号的大规模MIMO系统的鲁棒学习型ML检测](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9013332)|[LearningML](https:\u002F\u002Fgithub.com\u002FYunseong-Cho\u002FLearningML)|\n|[基于迭代误差消减的基于校验码的神经网络译码器](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.00089)|[ied](https:\u002F\u002Fgithub.com\u002Fkamassury\u002Fied)|\n|[ko codes：通过深度学习为可靠无线通信发明非线性编解码方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.12920)|[kocodes](https:\u002F\u002Fgithub.com\u002Fdeepcomm\u002Fkocodes)|\n|[智能反射面辅助多用户通信中的信道估计深度残差学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.01423)|[CDRN-channel-estimation-IRS](https:\u002F\u002Fgithub.com\u002FXML124\u002FCDRN-channel-estimation-IRS)|\n|[面向MIMO检测的模型驱动深度学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9018199)|[OAMP-Net](https:\u002F\u002Fgithub.com\u002Fhehengtao\u002FOAMP-Net)|\n|[基于扩张卷积的海量MIMO系统CSI反馈压缩](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.04043)|[DCRNet](https:\u002F\u002Fgithub.com\u002Frecusant7\u002FDCRNet)|\n|[面向海量MIMO混合波束赋形的无监督深度学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.00038)|[HBF-Net](https:\u002F\u002Fgithub.com\u002FHamedHojatian\u002FHBF-Net)|\n|[CLNet：专为海量MIMO CSI反馈设计的复数输入轻量级神经网络](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07507)|[CLNet](https:\u002F\u002Fgithub.com\u002FSIJIEJI\u002FCLNet)|\n|[基于块深度神经网络的一般空间调制信号检测器](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.03612)|[B_DNN](https:\u002F\u002Fgithub.com\u002Fhasanabs\u002FB_DNN)|\n|[毫米波初始对齐的自适应波束赋形深度主动学习方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.13607)|[DL-ActiveLearning-BeamAlignment](https:\u002F\u002Fgithub.com\u002Ffoadsohrabi\u002FDL-ActiveLearning-BeamAlignment)|\n|[数据驱动的深度学习用于设计海量MIMO的导频与信道估计算法](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9037126)|[Source-Code-X.Ma](https:\u002F\u002Fgithub.com\u002Fgaozhen16\u002FSource-Code-X.Ma)|\n|[无线网络中基于深度学习的预测性频段切换](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05305)|[Bandswitch-DeepMIMO](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FBandswitch-DeepMIMO)|\n|[RE-MIMO：循环且排列等变的神经MIMO检测](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.00140)|[RE-MIMO](https:\u002F\u002Fgithub.com\u002Fkrpratik\u002FRE-MIMO)|\n|[NOLD：LDPC码的神经网络优化低分辨率译码器](https:\u002F\u002Fgithub.com\u002FLeo-Chu\u002FNOLD\u002Fblob\u002Fmaster\u002FJCN20-DIV2-067.R2.pdf)|[NOLD](https:\u002F\u002Fgithub.com\u002FLeo-Chu\u002FNOLD)|\n|[在相关干扰存在下的深度学习MIMO检测器](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8990045)|[project_dcnnmld](https:\u002F\u002Fgithub.com\u002Fskypitcher\u002Fproject_dcnnmld)|\n|[深度学习驱动的毫米波通信非正交预编码](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9082619)|[Deep-Learning-Driven-Non-Orthogonal-Precoding-for-Millimeter-Wave-Communications](https:\u002F\u002Fgithub.com\u002FJKLinUESTC\u002FDeep-Learning-Driven-Non-Orthogonal-Precoding-for-Millimeter-Wave-Communications)|\n|[迭代算法诱导的深度展开神经网络：多用户MIMO系统的预编码设计](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9246287)|[DeepUnfolding_WMMSE](https:\u002F\u002Fgithub.com\u002Fhqyyqh888\u002FDeepUnfolding_WMMSE)|\n| [深度学习在OFDM系统信道估计和信号检测中的作用](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.08514.pdf)| [haoyye\u002FOFDM_DNN](https:\u002F\u002Fgithub.com\u002Fhaoyye\u002FOFDM_DNN)        |\n| [自动调制识别：一种基于深度学习的方法](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8454504) | [mengxiaomao](https:\u002F\u002Fgithub.com\u002Fmengxiaomao)\u002F[CNN_AMC](https:\u002F\u002Fgithub.com\u002Fmengxiaomao\u002FCNN_AMC) |\n| [用于调制识别的深度架构](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.09197.pdf)              | [qieaaa \u002F Deep-Architectures-for-Modulation-Recognition](https:\u002F\u002Fgithub.com\u002Fqieaaa\u002FDeep-Architectures-for-Modulation-Recognition) |\n| [Deep-Waveform：基于深度复值卷积网络的OFDM接收机](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9448141) | [zhongyuanzhao \u002F dl_ofdm](https:\u002F\u002Fgithub.com\u002Fzhongyuanzhao\u002Fdl_ofdm) |\n| [利用卷积神经网络进行无线通信物理层的收发机联合优化](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.03242) | [hlz1992\u002FRadioCNN](https:\u002F\u002Fgithub.com\u002Fhlz1992\u002FRadioCNN)      |\n| [用于机器学习的5G MIMO数据：应用于基于深度学习的波束选择](https:\u002F\u002Fpar.nsf.gov\u002Fservlets\u002Fpurl\u002F10112564)| [lasseufpa](https:\u002F\u002Fgithub.com\u002Flasseufpa)\u002F[5gm-data](https:\u002F\u002Fgithub.com\u002Flasseufpa\u002F5gm-data) |\n|[基于两重分组套索的轻量级深度神经网络用于自动调制识别](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9145050)|[Group-Sparse-DNN-for-AMC](https:\u002F\u002Fgithub.com\u002Ftjuxiaofeng\u002FGroup-Sparse-DNN-for-AMC)|\n|[利用深度学习分类递归量化时序相关的MIMO信道CSI](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.13560)|[MultiStage-Grassmannian-DNN](https:\u002F\u002Fgithub.com\u002FStefanSchwarzTUW\u002FMultiStage-Grassmannian-DNN)|\n| [深度学习用于海量MIMO CSI反馈](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.08919.pdf)                  | [sydney222 \u002F Python_CsiNet](https:\u002F\u002Fgithub.com\u002Fsydney222\u002FPython_CsiNet) |\n| [利用深度学习设计大规模天线阵列的波束赋形](http:\u002F\u002Farxiv.org\u002Fabs\u002F1904.03657) | [TianLin0509\u002FBF-design-with-DL](https:\u002F\u002Fgithub.com\u002FTianLin0509\u002FBF-design-with-DL)|\n| [物理层深度学习导论](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1702.00832.pdf)     | [yashcao \u002F RTN-DL-for-physical-layer](https:\u002F\u002Fgithub.com\u002Fyashcao\u002FRTN-DL-for-physical-layer)\u003Cbr \u002F>[musicbeer \u002F Deep-Learning-for-the-Physical-Layer](https:\u002F\u002Fgithub.com\u002Fmusicbeer\u002FDeep-Learning-for-the-Physical-Layer)\u003Cbr \u002F>[helloMRDJ \u002F autoencoder-for-the-Physical-Layer](https:\u002F\u002Fgithub.com\u002FhelloMRDJ\u002Fautoencoder-for-the-Physical-Layer)|\n| [深度MIMO检测](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.01151.pdf)                                          | [neevsamuel](https:\u002F\u002Fgithub.com\u002Fneevsamuel)\u002F[DeepMIMODetection](https:\u002F\u002Fgithub.com\u002Fneevsamuel\u002FDeepMIMODetection) |\n| [学习检测](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.07631.pdf)                                         | [neevsamuel](https:\u002F\u002Fgithub.com\u002Fneevsamuel)\u002F[LearningToDetect](https:\u002F\u002Fgithub.com\u002Fneevsamuel\u002FLearningToDetect) |\n| [用于信道解码的迭代BP-CNN架构](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8259241)        | [liangfei-info](https:\u002F\u002Fgithub.com\u002Fliangfei-info)\u002F[Iterative-BP-CNN](https:\u002F\u002Fgithub.com\u002Fliangfei-info\u002FIterative-BP-CNN) |\n| [关于基于深度学习的信道解码](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1701.07738.pdf)| [gruberto\u002FDL-ChannelDecoding](https:\u002F\u002Fgithub.com\u002Fgruberto\u002FDL-ChannelDecoding) \u003Cbr\u002F>[Decoder-using-deep-learning](https:\u002F\u002Fgithub.com\u002FVivekRamalingamK\u002FDecoder-using-deep-learning)|\n| [基于深度学习的波束域毫米波海量MIMO系统的信道估计](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8353153)| [hehengtao](https:\u002F\u002Fgithub.com\u002Fhehengtao)\u002F[LDAMP_based-Channel-estimation](https:\u002F\u002Fgithub.com\u002Fhehengtao\u002FLDAMP_based-Channel-estimation) |\n| [快速深度学习用于自动调制识别](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.05850.pdf)   | [dl4amc](https:\u002F\u002Fgithub.com\u002Fdl4amc)\u002F[source](https:\u002F\u002Fgithub.com\u002Fdl4amc\u002Fsource) |\n| [基于深度学习的信道估计](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.05893.pdf)| [Mehran-Soltani](https:\u002F\u002Fgithub.com\u002FMehran-Soltani)\u002F[ChannelNet](https:\u002F\u002Fgithub.com\u002FMehran-Soltani\u002FChannelNet) |\n|[稀疏连接的神经网络用于海量MIMO检测](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=8780959)|[MIMO_Detection](https:\u002F\u002Fgithub.com\u002FNobleLee\u002FMIMO_Detection)|\n| [Deepcode：通过深度学习实现反馈编码](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1807.00801.pdf)                | https:\u002F\u002Fgithub.com\u002Fhyejikim1\u002FDeepcode\u003Cbr>https:\u002F\u002Fgithub.com\u002Fyihanjiang\u002Ffeedback_code |\n|[MIST：一种新颖的训练策略，用于低延迟可扩展的神经网络译码器](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.08990.pdf)|[MIST_CNN_Decoder](https:\u002F\u002Fgithub.com\u002Fkryashashwi\u002FMIST_CNN_Decoder)|\n|[分布式低成本频谱传感器的无线信号分类深度学习模型](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8357902)|[modulation_classif](https:\u002F\u002Fgithub.com\u002FzeroXzero\u002Fmodulation_classif)|\n|[通过量化反馈学习物理层通信](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.09252.pdf)|[quantizedfeedback](https:\u002F\u002Fgithub.com\u002Fhenkwymeersch\u002Fquantizedfeedback)|\n|[用于信道编码的强化学习：学习位翻转译码](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.04448.pdf)|[RLdecoding](https:\u002F\u002Fgithub.com\u002Ffabriziocarpi\u002FRLdecoding)|\n|[面向海量MIMO的自适应神经信号检测](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04610)|[mehrdadkhani\u002FMMNet](https:\u002F\u002Fgithub.com\u002Fmehrdadkhani\u002FMMNet)|\n|[基于CNN的毫米波MIMO系统预编码器和组合器设计](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8710287)|[Deep_HybridBeamforming](https:\u002F\u002Fgithub.com\u002Fmeuseabe\u002FDeep_HybridBeamforming)|\n|[顺序卷积循环神经网络用于快速自动调制识别](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.03050.pdf)|[coming soon](https:\u002F\u002Fgithub.com\u002Fkython)|\n|[极化码的低精度神经网络译码](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8815542)|[low-precision-nnd](https:\u002F\u002Fgithub.com\u002FIgWod\u002Flow-precision-nnd)|\n|[在单比特接收机中进行低秩毫米波MIMO信道估计](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.09141)|[Low-rank-MIMO-channel-estimation-from-one-bit-measurements](https:\u002F\u002Fgithub.com\u002Fnitinjmyers\u002FLow-rank-MIMO-channel-estimation-from-one-bit-measurements)|\n|[面向配备1比特ADC的海量MIMO的深度学习：更多天线需要更少的导频](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.06960)|[1-Bit-ADCs](https:\u002F\u002Fgithub.com\u002FYuZhang-GitHub\u002F1-Bit-ADCs)|\n|[毫米波海量MIMO系统中直接混合预编码的深度学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.13212)|[DL-hybrid-precoder](https:\u002F\u002Fgithub.com\u002Flxf8519\u002FDL-hybrid-precoder)|\n|[用于OFDM-IM的深度学习检测器](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8684894)|[DeepIM](https:\u002F\u002Fgithub.com\u002FThienVanLuong\u002FDeepIM)|\n|[通过神经互信息估计进行信道编码的深度学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8815464)|[Wireless_encoding_with_MI_estimation](https:\u002F\u002Fgithub.com\u002FFritschek\u002FWireless_encoding_with_MI_estimation)|\n|[学习MMSE信道估计器](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.05674v3.pdf)|[learning-mmse-est](https:\u002F\u002Fgithub.com\u002Ftum-msv\u002Flearning-mmse-est)|\n|[神经网络辅助的极化码SC译码器](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8780605)|[1_NND](https:\u002F\u002Fgithub.com\u002FBruceGaoo\u002F1_NND)|\n|[利用双向信道互易性在深度学习中实现低速率海量MIMO CSI反馈](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8638509)|[Bi-Directional-Channel-Reciprocity](https:\u002F\u002Fgithub.com\u002FDLinWL\u002FBi-Directional-Channel-Reciprocity)|\n|[深度神经网络译码性能评估](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.00727.pdf)|[deep-neural-network-decoder](https:\u002F\u002Fgithub.com\u002Flevylv\u002Fdeep-neural-network-decoder)|\n|[闭环译码器：基于遗传算法的LDPC码设计](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.03128)|[Genetic-Algorithm-based-LDPC-Code-Design](https:\u002F\u002Fgithub.com\u002FAhmedElkelesh\u002FGenetic-Algorithm-based-LDPC-Code-Design)|\n|[MIMO物理层通信端到端学习的基准测试](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.09718)|[DeepLearning_MIMO](https:\u002F\u002Fgithub.com\u002FJSChalmers\u002FDeepLearning_MIMO)|\n|[为海量MIMO检测设计的学习共轭梯度下降网络](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03814)|[LcgNet](https:\u002F\u002Fgithub.com\u002FYiWei0129\u002FLcgNet)|\n|[可训练的投影梯度检测器用于超载海量MIMO信道：数据驱动的调优方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.10044)|[overloaded_MIMO](https:\u002F\u002Fgithub.com\u002Fwadayama\u002Foverloaded_MIMO)|\n|[用于MIMO检测的深度软干扰消除](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9054732)|[DeepSIC](https:\u002F\u002Fgithub.com\u002Fnirshlezinger1\u002FDeepSIC)|\n|[加权MMSE算法的深度展开](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.08448.pdf)|[WMMSE-deep-unfolding](https:\u002F\u002Fgithub.com\u002Flpkg\u002FWMMSE-deep-unfolding)|\n|[通过模拟大型天线阵列进行到达方向估计的深度学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.13824)|[DoA with DNN via Emulation of Antenna Arrays](https:\u002F\u002Fgitlab.com\u002Fmiriyugl\u002Fdoa-with-dnn-via-emulation-of-antenna-arrays)|\n|[通过深度基追踪获取测量矩阵，用于毫米波海量MIMO系统的稀疏信道估计](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.05177)|[DeepBP-AE](https:\u002F\u002Fgithub.com\u002FPengxia-Wu\u002FDeepBP-AE)|\n|[用于奇异值分解和混合波束赋形的深度学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9130130)|[DL_SVD_BF](https:\u002F\u002Fwww.dropbox.com\u002Fsh\u002Fv0gs7ba0qq5x168\u002FAACyqRoCz5m3fhpF-azkbn3Qa?dl=0)|\n|[用于信道编码的神经互信息估计：最先进的估计器、分析及性能比较](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.16015)|[Reverse-Jensen_MI_estimation](https:\u002F\u002Fgithub.com\u002FFritschek\u002FReverse-Jensen_MI_estimation)|\n|[基于深度迁移学习的FDD海量MIMO系统下行链路信道预测](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.12265)|[Codes-for-Deep-Transfer-Learning-Based-Downlink-Channel-Prediction-for-FDD-Massive-MIMO-Systems](https:\u002F\u002Fgithub.com\u002Fyangyuwenyang\u002FCodes-for-Deep-Transfer-Learning-Based-Downlink-Channel-Prediction-for-FDD-Massive-MIMO-Systems)|\n|[利用条件GAN进行单比特多用户海量MIMO的信道估计](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.11435)|[Channel_Estimation_cGAN](https:\u002F\u002Fgithub.com\u002FYudiDong\u002FChannel_Estimation_cGAN)|\n|[面向归一化最小和LDPC解码的模型驱动深度学习方法](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9145237)|[A-Model-Driven-Deep-Learning-Method-for-Normalized-Min-Sum-LDPC-Decoding](https:\u002F\u002Fgithub.com\u002Ftjuxiaofeng\u002FA-Model-Driven-Deep-Learning-Method-for-Normalized-Min-Sum-LDPC-Decoding)|\n|[用于深度学习调制识别的复值卷积](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9145469)|[Complex_Convolutions](https:\u002F\u002Fgithub.com\u002FJakobKrzyston\u002FComplex_Convolutions)|\n|[车载毫米波系统中信道协方差的生成对抗估计](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.02208)|[GAN-cov-matrix](https:\u002F\u002Fgithub.com\u002Flxf8519\u002FGAN-cov-matrix)|\n|[用于毫米波海量MIMO系统的波束域信道估计的深度学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9207745)|[Simulation Codes](http:\u002F\u002Foa.ee.tsinghua.edu.cn\u002Fdailinglong\u002Fpublications\u002Fpublications.html)|\n|[平坦衰落信道上极化码的深度学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8669025)|[polarOverFlatFading](https:\u002F\u002Fgithub.com\u002Fade-irawan\u002FpolarOverFlatFading)|\n|[面向海量MIMO CSI反馈的聚合网络](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.06618)|[ACRNet](https:\u002F\u002Fgithub.com\u002FKylin9511\u002FACRNet)|\n| [卷积无线电调制识别网络](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1602.04105.pdf)          | [chrisruk](https:\u002F\u002Fgithub.com\u002Fchrisruk)\u002F[cnn](https:\u002F\u002Fgithub.com\u002Fchrisruk\u002Fcnn)\u003Cbr \u002F>[qieaaa \u002F Singal-CNN](https:\u002F\u002Fgithub.com\u002Fqieaaa\u002FSingal-CNN) |\n| [涡轮自动编码器：基于深度学习的点对点通信信道编码](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.03038.pdf)  | [yihanjiang](https:\u002F\u002Fgithub.com\u002Fyihanjiang)\u002F[turboae](https:\u002F\u002Fgithub.com\u002Fyihanjiang\u002Fturboae) |\n|[在海量MIMO系统中使用深度学习进行多分辨率CSI反馈](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.14322)|[CRNet](https:\u002F\u002Fgithub.com\u002FKylin9511\u002FCRNet)|\n|[在MIMO CSI反馈中使用深度循环网络进行时空表示](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8951228)|[ConvlstmCsiNet](https:\u002F\u002Fgithub.com\u002FAries-LXY\u002FConvlstmCsiNet)|\n|[学习在车载网络中压缩CSI并分配资源](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.04685)|[Learn-CompressCSI-RA-V2X-Code](https:\u002F\u002Fgithub.com\u002FCooperLWang\u002FLearn-CompressCSI-RA-V2X-Code)|\n|[深度学习用于TDD和FDD海量MIMO：在空间和频率上映射信道](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.03761.pdf)|[DL-Massive-MIMO](https:\u002F\u002Fgithub.com\u002Fmalrabeiah\u002FDL-Massive-MIMO)|\n|[深度UL2DL：从上行链路到下行链路的信道知识转移](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.07518)|[UL2DL](https:\u002F\u002Fgithub.com\u002Fsafarisadegh\u002FUL2DL)|\n|[通过深度时序差分学习实现最优效率的树搜索](https:\u002F\u002Farxiv.org\u002Fabs\u002F2101.02420)|[hats](https:\u002F\u002Fgithub.com\u002Fskypitcher\u002Fhats)|\n|[利用压缩感知和深度学习赋能大型智能表面](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.10136)|[LIS-DeepLearning](https:\u002F\u002Fgithub.com\u002FAbdelrahman-Taha\u002FLIS-DeepLearning)|\n|[基于CNN的端到端学习框架，迈向智能通信系统](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8755977)|[Deepcom](https:\u002F\u002Fgithub.com\u002FZhangKaiyao\u002FDeepcom)|\n| [通过深度学习实现通信算法](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.09317) | [yihanjiang](https:\u002F\u002Fgithub.com\u002Fyihanjiang)\u002F[commviadl](https:\u002F\u002Fgithub.com\u002Fyihanjiang\u002FSequential-RNN-Decoder) |\n|[在噪声环境中学习通信](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.09630)|[echo](https:\u002F\u002Fgithub.com\u002Fml4wireless\u002Fecho)|\n|[元学习通信：针对衰落信道的快速端到端训练](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.09945)|[meta-autoencoder](https:\u002F\u002Fgithub.com\u002Fkclip\u002Fmeta-autoencoder)|\n|[用于非相干多载波MU-SIMO系统的深度能量自编码器](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9036067)|[energy_autoencoder](https:\u002F\u002Fgithub.com\u002FThienVanLuong\u002Fenergy_autoencoder)|\n|[面向大型智能表面辅助毫米波海量MIMO系统的深度信道学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.11085)|[deepChannelLearning4RIS](https:\u002F\u002Fgithub.com\u002Fmeuseabe\u002FdeepChannelLearning4RIS)|\n|[以条件GAN作为未知信道的深度学习端到端无线通信系统](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.02551.pdf)|[End2End_GAN](https:\u002F\u002Fgithub.com\u002Fhaoyye\u002FEnd2End_GAN)|\n|[RadioUNet：利用卷积神经网络快速估算无线电信号图](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.09002)|[RadioUNet](https:\u002F\u002Fgithub.com\u002FRonLevie\u002FRadioUNet)|\n|[深度学习辅助的多载波系统](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9271932)|[multicarrier_autoencoder](https:\u002F\u002Fgithub.com\u002FThienVanLuong\u002Fmulticarrier_autoencoder)|\n\n### 资源与网络优化 \n| 论文                                                        | 代码                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[基于图神经网络的车载通信资源分配](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9322537)|[Globecom2020-ResourceAllocationGNN](https:\u002F\u002Fgithub.com\u002FCoolzyh\u002FGlobecom2020-ResourceAllocationGNN)|\n|[无线网络中约束优化问题的无监督深度展开框架](https:\u002F\u002Farxiv.org\u002Fabs\u002F2201.08994)|[USRMNet-HWGCN](https:\u002F\u002Fgithub.com\u002Fsoulven\u002Fusrmnet-hwgcn)|\n|[利用图神经网络进行无线联邦学习的功率分配](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.07480)|[WirelessFL-PDGNet](https:\u002F\u002Fgithub.com\u002Fbl166\u002Fwirelessfl-pdgnet)|\n|[基于图神经网络的时延导向分布式调度](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.07017)|[gcn-dql](https:\u002F\u002Fgithub.com\u002Fzhongyuanzhao\u002Fgcn-dql)|\n|[基于深度学习的MAC：联合信道接入与速率自适应](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.10307)|[Wireless-Signal-Strength-on-2.4GHz-WSS24-dataset](https:\u002F\u002Fgithub.com\u002Fpostman511\u002FWireless-Signal-Strength-on-2.4GHz-WSS24-dataset)|\n|[通过图表示学习进行无线链路调度：不同监督水平的比较研究](https:\u002F\u002Farxiv.org\u002Fabs\u002F2110.01722)|[LinkSchedulingGNNs_SupervisionStudy](https:\u002F\u002Fgithub.com\u002Fnavid-naderi\u002FLinkSchedulingGNNs_SupervisionStudy)|\n|[使用图神经网络的分布式调度](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.09430)|[distgcn](https:\u002F\u002Fgithub.com\u002Fzhongyuanzhao\u002Fdistgcn)|\n|[DeepBeam：用于毫米波网络中无协调波束管理的深度波形学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.14350)|[deepbeam](https:\u002F\u002Fgithub.com\u002Fwineslab\u002Fdeepbeam)|\n|[基于图嵌入的无线链路调度：少量训练样本场景](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.02871)|[graph_embedding_link_scheduling](https:\u002F\u002Fgithub.com\u002Fmengyuan-lee\u002Fgraph_embedding_link_scheduling)|\n| [强化学习在无线传感器网络中的能效优化](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1812.02538.pdf)| [mkoz71 \u002F Energy-Efficiency-in-Reinforcement-Learning](https:\u002F\u002Fgithub.com\u002Fmkoz71\u002FEnergy-Efficiency-in-Reinforcement-Learning) |\n| [学习优化：训练深度神经网络用于无线资源管理](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.09412)| [Haoran-S \u002F DNN_WMMSE](https:\u002F\u002Fgithub.com\u002FHaoran-S\u002FDNN_WMMSE) |\n| [无线网络中去中心化Q学习资源分配的影响](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1705.10508.pdf) | [wn-upf \u002F decentralized_qlearning_resource_allocation_in_wns](https:\u002F\u002Fgithub.com\u002Fwn-upf\u002Fdecentralized_qlearning_resource_allocation_in_wns) |\n| [用于自组织网络故障管理和无线性能提升的深度Q学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1707.02329) | [farismismar \u002F Deep-Q-Learning-SON-Perf-Improvement](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FDeep-Q-Learning-SON-Perf-Improvement) |\n| [用于室内小基站VoLTE闭环功率控制的Q学习算法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.03269.pdf) | [farismismar \u002F Q-Learning-Power-Control](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FQ-Learning-Power-Control) |\n| [用于无线干扰网络中最优能效功率控制的深度学习](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1812.06920.pdf) | [bmatthiesen \u002F deep-EE-opt](https:\u002F\u002Fgithub.com\u002Fbmatthiesen\u002Fdeep-EE-opt) |\n| [基于演员-评论家的多模态光网络资源分配](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8644190) | [BoyuanYan \u002F Actor-Critic-Based-Resource-Allocation-for-Multimodal-Optical-Networks](https:\u002F\u002Fgithub.com\u002FBoyuanYan\u002FActor-Critic-Based-Resource-Allocation-for-Multimodal-Optical-Networks)|\n| [利用深度神经网络进行D2D通信的发射功率控制](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8428396) | [seotaijiya](https:\u002F\u002Fgithub.com\u002Fseotaijiya)\u002F[TPC_D2D](https:\u002F\u002Fgithub.com\u002Fseotaijiya\u002FTPC_D2D) |\n|[利用深度强化学习进行多小区网络功率分配](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8690757)|[qfnet](https:\u002F\u002Fgithub.com\u002Fkangcp\u002Fqfnet)|\n|[新空口异构网络中下行协作多点传输的深度学习](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1812.03421.pdf)|[DL-CoMP-Machine-Learning](https:\u002F\u002Fgithub.com\u002Ffarismismar\u002FDL-CoMP-Machine-Learning)|\n|[用于V2V通信资源分配的深度强化学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.00968)|https:\u002F\u002Fgithub.com\u002Fhaoyye\u002FResourceAllocationReinforcementLearning|\n| [AIF：智能无线网络管理的人工智能框架](http:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8119495\u002Fmetrics) | [caogang](https:\u002F\u002Fgithub.com\u002Fcaogang)\u002F[WlanDqn](https:\u002F\u002Fgithub.com\u002Fcaogang\u002FWlanDqn) |\n| [大规模MIMO中的深度学习功率分配](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.03640)              | [lucasanguinetti \u002F Deep-Learning-Power-Allocation-in-Massive-MIMO](https:\u002F\u002Fgithub.com\u002Flucasanguinetti\u002FDeep-Learning-Power-Allocation-in-Massive-MIMO) |\n|[机器学习与随机几何：无线网络中的行列式子集选择](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.00504)|[DPPL](https:\u002F\u002Fgithub.com\u002Fstochastic-geometry\u002FDPPL)|\n|[针对干扰的毫米波大规模MIMO学习型功率控制](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=8647173)|[Learning-Based-Power-Control-for-mmWave-Massive-MIMO-against-Jamming](https:\u002F\u002Fgithub.com\u002Fxiaozhch5\u002FLearning-Based-Power-Control-for-mmWave-Massive-MIMO-against-Jamming)|\n|[通过集成深度神经网络实现最优功率控制](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.10025)|[PCNet-ePCNet](https:\u002F\u002Fgithub.com\u002FShenGroup\u002FPCNet-ePCNet)|\n|[面向可扩展无线功率控制的图神经网络方法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1907.08487.pdf)|[Globecom2019](https:\u002F\u002Fgithub.com\u002Fyshenaw\u002FGlobecom2019)|\n|[面向HetNets动态资源分配的移动性感知集中式强化学习](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F335159543_Mobility-Aware_Centralized_Reinforcement_Learning_for_Dynamic_Resource_Allocation_in_HetNets)|[UARA](https:\u002F\u002Fgithub.com\u002FLiuJieShane\u002FUARA)|\n|[无线通信系统中的智能资源分配](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8961912)|[IRAWCS](https:\u002F\u002Fgithub.com\u002Fseotaijiya\u002FIRAWCS)|\n|[基于图的组合优化算法学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.01665)|[graph_comb_opt](https:\u002F\u002Fgithub.com\u002FHanjun-Dai\u002Fgraph_comb_opt.git)|\n|[为高效RNN-based 5G无线资源管理扩展RISC-V ISA](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12877)|[RNNASIP](https:\u002F\u002Fgithub.com\u002Fandrire\u002FRNNASIP)|\n|[采用深度Q学习方法的多用户蜂窝网络功率分配](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.02979)|[PA_ICC](https:\u002F\u002Fgithub.com\u002Fmengxiaomao\u002FPA_ICC)|\n|[多用户蜂窝网络功率分配：深度强化学习方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.07159)|[PA_TWC](https:\u002F\u002Fgithub.com\u002Fmengxiaomao\u002FPA_TWC)|\n|[利用图神经网络展开WMMSE以实现高效功率分配](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.10812)|[Unrolled-WMMSE](https:\u002F\u002Fgithub.com\u002FArCho48\u002FUnrolled-WMMSE)|\n|[用于无线移动网络分布式功率控制的深度演员-评论家学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.06681)|[Power-Control-asilomar](https:\u002F\u002Fgithub.com\u002Fsinannasir\u002FPower-Control-asilomar)|\n|[用于可扩展无线资源管理的图神经网络：架构设计与理论分析](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.07632)|[GNN-Resource-Management](https:\u002F\u002Fgithub.com\u002Fyshenaw\u002FGNN-Resource-Management)|\n|[无线功率控制的对比自监督学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11909)|[ContrastiveSSL_WirelessPowerControl](https:\u002F\u002Fgithub.com\u002Fnavid-naderi\u002FContrastiveSSL_WirelessPowerControl)|\n|[不劳无获：能量受限CR-NOMA网络中的DRL辅助优化](https:\u002F\u002Fgithub.com\u002Fzhiguo-ding\u002FCRNOMA_DDPG\u002Fblob\u002Fmain\u002Fpaper.pdf)|[CRNOMA_DDPG](https:\u002F\u002Fgithub.com\u002Fzhiguo-ding\u002FCRNOMA_DDPG)|\n|[基于深度学习的多小区速率约束下功率控制](https:\u002F\u002Farxiv.org\u002Fabs\u002F2012.03655)|[SRnet-and-SRNet-Heu-for-power-control](https:\u002F\u002Fgithub.com\u002FLeeyyhh\u002FSRnet-and-SRNet-Heu-for-power-control)|\n|[利用Sub-6GHz信道进行毫米波波束和遮挡预测的深度学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.02900)|[Sub6-Preds-mmWave](https:\u002F\u002Fgithub.com\u002Fmalrabeiah\u002FSub6-Preds-mmWave)|\n|[无线链路适配——一种混合数据驱动与模型驱动的方法](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=9154263)|[LinkAdaptationCSI](https:\u002F\u002Fgithub.com\u002Flpkg\u002FLinkAdaptationCSI)|\n|[在周期性动态环境中持续优化无线资源的学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.07782)|[ICASSP2021](https:\u002F\u002Fgithub.com\u002FHaoran-S\u002FICASSP2021)|\n| [DeepNap：通过深度强化学习实现的数据驱动基站休眠操作](http:\u002F\u002Fnetwork.ee.tsinghua.edu.cn\u002Fniulab\u002Fwp-content\u002Fuploads\u002F2018\u002F10\u002Fdeepnap_CCN.pdf) | [zaxliu](https:\u002F\u002Fgithub.com\u002Fzaxliu)\u002F[deepnap](https:\u002F\u002Fgithub.com\u002Fzaxliu\u002Fdeepnap) | \n|[不劳无获：能量受限CR-NOMA网络中的DRL辅助优化](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2104.06007.pdf)|[CRNOMA_DDPG](https:\u002F\u002Fgithub.com\u002Fzhiguo-ding\u002FCRNOMA_DDPG)|\n\n### 通信网络上的分布式学习算法\n| 论文                                                        | 代码                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[面向联网通信网络的可扩展联邦多智能体架构](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.00506)|[Fed-MF-MAL](https:\u002F\u002Fgithub.com\u002Fpaperflight\u002FFed-MF-MAL)|\n|[可重构智能表面赋能的联邦学习：一种统一的通信-学习设计方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.10282)|[RIS-FL](https:\u002F\u002Fgithub.com\u002Fliuhang1994\u002FRIS-FL)|\n|[基于展开图神经网络的去中心化统计推断](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.01555)|[Learning-based-DOP-Framework](https:\u002F\u002Fgithub.com\u002FIrisWangHe\u002FLearning-based-DOP-Framework)|\n|[基于深度强化学习的协作定位去中心化调度](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8701533)|[DeepRLVehicularLocalization](https:\u002F\u002Fgithub.com\u002Fhenkwymeersch\u002FDeepRLVehicularLocalization)|\n|[用于分布式动态MISO下行波束成形协调的深度强化学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9123956)|[DRL_for_DDBC](https:\u002F\u002Fgithub.com\u002FJungangGe\u002FDRL_for_DDBC)|\n| [面向多用户移动边缘计算的去中心化计算卸载：一种深度强化学习方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F1812.07394) | [swordest](https:\u002F\u002Fgithub.com\u002Fswordest)\u002F[mec_drl](https:\u002F\u002Fgithub.com\u002Fswordest\u002Fmec_drl) |\n|[无线网络上的联邦学习：收敛性分析与资源分配](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.13067.pdf)|[FEDL](https:\u002F\u002Fgithub.com\u002Fnhatminh\u002FFEDL)|\n|[无线网络上的联邦学习：优化模型设计与分析](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8737464)|[OnDevAI](https:\u002F\u002Fgithub.com\u002Fnhatminh\u002FOnDevAI)|\n|[基于深度确定性策略梯度（DDPG）的能量采集无线通信](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8731635)|[Energy-Harvesting-DDPG](https:\u002F\u002Fgithub.com\u002FCrQiu\u002FEnergy-Harvesting-DDPG-)|\n[无线网络上联邦学习的联合学习与通信框架](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.07972.pdf)|[Wireless-FL](https:\u002F\u002Fgithub.com\u002Fmzchen0\u002FWireless-FL)|\n\n### 基于机器学习技术的多址接入调度与路由\n| 论文                                                        | 代码                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[通过深度强化学习实现分布式动态频谱接入：基于储备池计算的方法](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8474348)|[DQN_RC_DSA_IOT2019](https:\u002F\u002Fgithub.com\u002Fhaohsuan2918\u002FDQN_RC_DSA_IOT2019)|\n|[用于无线网络中动态多信道接入的深度强化学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8303773)|[DynamicMultiChannelRL](https:\u002F\u002Fgithub.com\u002FGulatiAditya\u002FDynamicMultiChannelRL)|\n| [用于多信道无线网络中动态频谱接入的深度多用户强化学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8254101)| [shkrwnd](https:\u002F\u002Fgithub.com\u002Fshkrwnd)\u002F[Deep-Reinforcement-Learning-for-Dynamic-Spectrum-Access](https:\u002F\u002Fgithub.com\u002Fshkrwnd\u002FDeep-Reinforcement-Learning-for-Dynamic-Spectrum-Access) |\n|[用于无线网络中动态多信道接入的深度强化学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8303773)|[DynamicMultiChannelRL](https:\u002F\u002Fgithub.com\u002FGulatiAditya\u002FDynamicMultiChannelRL)|\n|[基于强化学习的调度算法，用于优化超可靠低时延网络中的信息年龄](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8969641)|[AoI_RL](https:\u002F\u002Fgithub.com\u002Faelgabli\u002FAoI_RL)|\n|[利用联邦深度强化学习提升WiFi多址接入性能](https:\u002F\u002Farxiv.org\u002Fabs\u002F2102.07019)|[FLDRL-in-Wireless-Communication](https:\u002F\u002Fgithub.com\u002FMauriyin\u002FFLDRL-in-Wireless-Communication)|\n|[无线调度的聚类方法](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9154271)|[A_Clustering_Approach_to_Wireless_Scheduling](https:\u002F\u002Fgithub.com\u002Fwilltop\u002FA_Clustering_Approach_to_Wireless_Scheduling)|\n|[用于异构无线网络的深度强化学习多址接入](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8665952)|[DLMA](https:\u002F\u002Fgithub.com\u002FYidingYu\u002FDLMA)|\n| [用于软件定义网络路由优化的深度强化学习方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F1709.07080) | [knowledgedefinednetworking \u002F a-deep-rl-approach-for-sdn-routing-optimization](https:\u002F\u002Fgithub.com\u002Fknowledgedefinednetworking\u002Fa-deep-rl-approach-for-sdn-routing-optimization) |\n| [用于无线调度的空间深度学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.01486)               | [willtop](https:\u002F\u002Fgithub.com\u002Fwilltop)\u002F[Spatial_DeepLearning_Wireless_Scheduling](https:\u002F\u002Fgithub.com\u002Fwilltop\u002FSpatial_DeepLearning_Wireless_Scheduling) |\n| [基于Transformer的在线贝叶斯神经网络，用于CRAN中基于流式变分推断的免授权上行接入](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9540910)               | [CRAN_MIMO_VI](https:\u002F\u002Fgithub.com\u002Fjhanilesh96\u002FCRAN_MIMO_VI) |\n\n### 软件定义网络中的机器学习\n| 论文                                                        | 代码                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n| [DELMU：一种最大化虚拟化毫米波回传效用的深度学习方法](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-19945-6_10)| [ruihuili \u002F DELMU](https:\u002F\u002Fgithub.com\u002Fruihuili\u002FDELMU)        |\n|[ns-3遇见OpenAI Gym：网络研究中机器学习的游乐场](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.03943.pdf)|[ns3-gym](https:\u002F\u002Fgithub.com\u002Ftkn-tub\u002Fns3-gym)|\n\n### 面向新兴通信系统与应用的机器学习\n| 论文                                                        | 代码                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n|[基于通信Transformer的深度强化学习在无线边缘网络中的自适应直播流](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9605672)|[SACCT](https:\u002F\u002Fgithub.com\u002FwsyCUHK\u002FSACCT)|\n|[基于深度强化学习的边缘计算中依赖性任务卸载](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9627763)|[RLTaskOffloading](https:\u002F\u002Fgithub.com\u002Flinkpark\u002FRLTaskOffloading)|\n|[基于元强化学习的边缘计算中快速自适应计算卸载](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.02033)|[metarl-offloading](https:\u002F\u002Fgithub.com\u002Flinkpark\u002Fmetarl-offloading)|\n|[李雅普诺夫引导的深度强化学习在移动边缘计算网络中的稳定在线计算卸载](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9449944)|[LyDROO](https:\u002F\u002Fgithub.com\u002Frevenol\u002FLyDROO)|\n|[面向有状态NFV支持的零接触6G网络的主动且考虑AoI的故障恢复：无模型强化学习方法](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.03817)|[ZT-PFR](https:\u002F\u002Fgithub.com\u002Fwildsky95\u002FZT-PFR)|\n|[利用深度强化学习进行无线数据采集的多无人机路径规划](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.12461)|[uav_data_harvesting](https:\u002F\u002Fgithub.com\u002Fhbayerlein\u002Fuav_data_harvesting)|\n|[基于多智能体强化学习的车联网频谱共享](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.02910)|[MARLspectrumSharingV2X](https:\u002F\u002Fgithub.com\u002FAlexVic\u002FMARLspectrumSharingV2X)|\n|[自适应交通信号控制的开源框架](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.00395.pdf)|[docwza\u002Fsumolights](https:\u002F\u002Fgithub.com\u002Fdocwza\u002Fsumolights)|\n|[基于卷积神经网络的Massive MIMO系统中CSI定位](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.11523)|[MaMIMO_CSI_with_CNN_positioning](https:\u002F\u002Fgithub.com\u002Fsibrendebast\u002FMaMIMO_CSI_with_CNN_positioning)|\n|[BottleNet++：设备-边缘协同推理系统中特征压缩的端到端方法](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9145068)|[BottleNetPlusPlus](https:\u002F\u002Fgithub.com\u002Fshaojiawei07\u002FBottleNetPlusPlus)|\n|[基于深度强化学习的无线供电移动边缘计算网络中的在线计算卸载](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8771176\u002F)|[DROO](https:\u002F\u002Fgithub.com\u002Frevenol\u002FDROO)|\n|[使用CNN的MaMIMO CSI定位：窥探黑箱内部](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.04581)|[inside-the-black-box](https:\u002F\u002Fgithub.com\u002Fsibrendebast\u002Finside-the-black-box)|\n|[用于大规模网络定位的图神经网络](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11653)|[GNN-For-localization](https:\u002F\u002Fgithub.com\u002FYanzongzi\u002FGNN-For-localization)|\n|[基于元强化学习的边缘计算中快速自适应任务卸载](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.02033)|[metarl-offloading](https:\u002F\u002Fgithub.com\u002Flinkpark\u002Fmetarl-offloading)|\n|[使用DNN的基于射频的无人机方向估计](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.01154)|https:\u002F\u002Fgithub.com\u002FLahiruJayasinghe\u002FDeepDOA|\n### 通信网络上的安全机器学习\n| 论文                                                        | 代码                                                         |\n| ------------------------------------------------------------ | ------------------------------------------------------------ |\n| [针对端到端自动编码器通信系统的物理对抗攻击](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.08391)| https:\u002F\u002Fgithub.com\u002Fmeysamsadeghi\u002FSecurity-and-Robustness-of-Deep-Learning-in-Wireless-Communication-Systems |\n|[用于高斯窃听信道的深度学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8761681)|[NN_GWTC](https:\u002F\u002Fgithub.com\u002FFritschek\u002FNN_GWTC)|\n\n\n\n# “通信+DL”论文（无代码)\u002FPaper List Without Code\n说明：论文主要来源于arxiv中[Signal Processing](https:\u002F\u002Farxiv.org\u002Flist\u002Feess.SP\u002Frecent)和[Information Theory](https:\u002F\u002Farxiv.org\u002Flist\u002Fcs.IT\u002Frecent)\n* [具有单比特ADC的MIMO系统鲁棒数据检测：一种强化学习方法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.12546.pdf)\n* [大型能量采集网络的分布式功率控制：一种多智能体深度强化学习方法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.00601.pdf)\n* [用于无线通信信道建模的机器学习：综述](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11277-019-06275-4)\n* [Massive MIMO系统中总频谱效率最大化：深度学习带来的益处](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.08163.pdf)\n\n# 数据集\u002FDatabase\n* [Wireless-Signal-Strength-on-2.4GHz-WSS24-dataset](https:\u002F\u002Fgithub.com\u002Fpostman511\u002FWireless-Signal-Strength-on-2.4GHz-WSS24-dataset): 用于RSSI分析的数据集\n* [MetaCC](https:\u002F\u002Fgithub.com\u002Fruihuili\u002FMetaCC): 面向元学习的信道编码基准测试平台（[A Channel Coding Benchmark for Meta-Learning](https:\u002F\u002Fopenreview.net\u002Fforum?id=DjzPaX8AT0z)）\n* [thymio-radio-map](https:\u002F\u002Fgithub.com\u002Farthurgassner\u002Fthymio-radio-map): OpenCSI：基于CSI指纹的室内定位开源数据集（[OpenCSI: An Open-Source Dataset for Indoor Localization Using CSI-Based Fingerprinting](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.07963)）\n* [The DeepMIMO Dataset](http:\u002F\u002Fdeepmimo.net\u002F) 及其相关论文 [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.06435)\n* [RAYMOBTIME](https:\u002F\u002Fwww.lasse.ufpa.br\u002Fraymobtime\u002F): Raymobtime是一种用于模拟无线通信的、可收集真实场景数据的方法。它结合了射线追踪技术与包含移动性和时间演化的三维场景，以实现时间、频率和空间上的一致性。\n* [MASSIVE MIMO CSI MEASUREMENTS](https:\u002F\u002Fhomes.esat.kuleuven.be\u002F~sdebast\u002Fcsi_measurements.html)\n* [SM-CsiNet+ 和 PM-CsiNet+] (https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1_lAMLk_5k1Z8zJQlTr5NRnSD6ACaNRtj?usp=sharing): 来自论文 [Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.06007.pdf)\n* [一个开放的在线真实调制信号数据集](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1biDooH6E81Toxa2u4D3p2g): 来自论文 [Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.04297.pdf)。\n  > 据我们所知，这是首个面向无线通信系统的公开真实调制信号数据集。\n* [RF DATASETS FOR MACHINE LEARNING](https:\u002F\u002Fwww.deepsig.io\u002Fdatasets)\n* [开放数据集](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1rS143bEDaOTEiCneXE67dg#list\u002Fpath=%2F): 来自论文 [Signal Demodulation With Machine Learning Methods for Physical Layer Visible Light Communications: Prototype Platform, Open Dataset, and Algorithms](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=8661606&tag=1)\n  > 该数据集是在真实的物理环境中采集的，信道受到多种因素影响，如LED带宽受限、多径反射、干扰或持续性阻塞等。\n# 学者个人主页\u002FResearcher Homepage\n* [Dr. Zhen Gao (高镇)](https:\u002F\u002Fgaozhen16.eu.org\u002F):\n  - 无线通信\n  - 毫米波\u002F太赫兹混合大规模MIMO信道估计\n  - 稀疏信号处理\n  - 基于深度学习的无线系统解决方案\n* [Ahmed Alkhateeb](http:\u002F\u002Fwww.aalkhateeb.net\u002Findex.html): 研究兴趣\n  - 毫米波与大规模MIMO通信\n  - 车载及无人机通信系统\n  - 机器学习在无线通信中的应用\n  - 构建真正可用的移动通信系统！\n* [Emil Björnson](https:\u002F\u002Febjornson.com\u002Fresearch\u002F):\n  他的研究方向包括多天线通信、大规模MIMO、无线资源分配、能效通信以及网络设计。\n* [Leo-Chu](https:\u002F\u002Fgithub.com\u002FLeo-Chu): 他的研究兴趣集中在随机矩阵理论、非凸优化、深度学习的理论与算法研究，以及这些技术在无线通信、生物工程和智能电网中的应用。\n# 有用的网页和材料\u002FUseful Websites and Materials\n* [基于图的深度学习在通信网络中的应用综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.02533): [GNN-Communication-Networks](https:\u002F\u002Fgithub.com\u002Fjwwthu\u002FGNN-Communication-Networks)\n* [机器学习与通信结合论文列表\u002FResearch Library ](https:\u002F\u002Fmlc.committees.comsoc.org\u002Fresearch-library\u002F)\n* [通信领域机器学习最佳阅读推荐](https:\u002F\u002Fwww.comsoc.org\u002Fpublications\u002Fbest-readings\u002Fmachine-learning-communications)\n* [林雪平大学通信系统课程视频](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCOrjRoYJPqGiR1SZvU3xcYQ\u002Fvideos)\n* [智能反射面（IRS）相关代码](https:\u002F\u002Fgithub.com\u002Fken0225\u002FRIS_Codes_Collection)\n* [awesome-ml4co](https:\u002F\u002Fgithub.com\u002FThinklab-SJTU\u002Fawesome-ml4co): 一份利用机器学习技术解决组合优化问题的论文列表。\n* [来自comsoc的仿真代码](https:\u002F\u002Fmlc.committees.comsoc.org\u002Fpapers-with-code\u002F)\n\n\u003Cbr>贡献者\u002FContributors：\n* WxZhu:\n  - [Github](https:\u002F\u002Fgithub.com\u002Fzhuwenxing)  \n  - 邮箱：wenxingzhu@shu.edu.cn\n* [LinTian](https:\u002F\u002Fgithub.com\u002FTianLin0509)\n* [HongtaiChen](https:\u002F\u002Fgithub.com\u002FHongtaiChen)\n* [yihanjiang](https:\u002F\u002Fgithub.com\u002Fyihanjiang)\n* wu huaming:\n  - 邮箱：whming@tju.edu.cn\n\n\u003Cbr>版本更新\u002FVersion Update：\n\n1. 第一版完成\u002FFirst Version：2019年2月21日\n2. 分类整理及链接补全\u002FFirst Version: 2021年4月14日，由[Yokoxue](https:\u002F\u002Fgithub.com\u002Fyokoxue)完成","# Paper-with-Code-of-Wireless-communication-Based-on-DL 快速上手指南\n\n本项目并非一个单一的独立软件工具，而是一个**基于深度学习的无线通信开源论文与代码索引库**。它整理了物理层优化、资源分配、网络切片等方向的经典论文及其对应的 GitHub 代码实现。\n\n本指南将指导你如何利用该列表找到适合的代码项目，并完成本地环境的搭建与运行。\n\n## 环境准备\n\n由于列表中每个子项目（如 `sionna`, `LoRD-Net`, `CsiNet` 等）的技术栈略有不同，但绝大多数基于 Python 和深度学习框架。建议准备以下通用环境：\n\n*   **操作系统**: Linux (Ubuntu 18.04\u002F20.04 推荐), macOS, 或 Windows (WSL2 推荐)\n*   **Python 版本**: 3.7 - 3.9 (多数通信领域深度学习项目在此范围兼容性最好)\n*   **核心依赖**:\n    *   PyTorch 或 TensorFlow\u002FKeras (根据具体论文代码要求选择)\n    *   NumPy, SciPy, Matplotlib\n    *   Git\n*   **硬件建议**: 带有 CUDA 支持的 NVIDIA GPU (用于加速模型训练与仿真)\n\n> **提示**: 建议在开始之前安装 `conda` (Miniconda\u002FAnaconda)，以便为不同的论文代码创建隔离的虚拟环境。\n\n## 安装步骤\n\n由于本项目是索引列表，你需要先选择一个具体的子项目（例如物理层信道估计方向的 `Python_CsiNet`），然后按照以下步骤操作。\n\n### 1. 克隆目标代码仓库\n在 [Topics](#topics) 列表中找到你感兴趣的论文对应的 Code 链接。以 `Deep Learning for Massive MIMO CSI Feedback` 为例：\n\n```bash\n# 创建并进入项目目录\ngit clone https:\u002F\u002Fgithub.com\u002Fsydney222\u002FPython_CsiNet.git\ncd Python_CsiNet\n```\n\n### 2. 创建虚拟环境 (推荐)\n使用 conda 创建独立的 Python 环境，避免依赖冲突。\n\n```bash\nconda create -n comm_dl python=3.8\nconda activate comm_dl\n```\n\n### 3. 安装依赖\n大多数项目会在根目录提供 `requirements.txt`。如果没有，通常只需安装基础的深度学习框架。\n\n**方案 A：如果有 requirements.txt**\n```bash\n# 推荐使用国内镜像源加速安装 (如清华源)\npip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n**方案 B：手动安装基础依赖 (若无配置文件)**\n```bash\n# 根据项目文档选择 PyTorch 或 TensorFlow\n# 示例：安装 PyTorch (CPU 版本，如有 GPU 请去 pytorch.org 获取对应 CUDA 命令)\npip install torch torchvision torchaudio -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n\n# 安装通用科学计算库\npip install numpy scipy matplotlib h5py -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 基本使用\n\n以下以 `Python_CsiNet` (Massive MIMO 信道状态信息反馈) 为例，展示如何运行一个典型的通信深度学习代码。其他项目流程类似，请参考各自 README 中的具体参数说明。\n\n### 1. 数据准备\n许多通信项目需要生成仿真数据或下载预处理数据集。查看项目中是否有数据生成脚本。\n\n```bash\n# 示例：运行数据生成脚本 (具体文件名请以项目实际为准)\npython generate_data.py\n```\n*注：部分项目会在首次运行时自动下载数据，或需要在代码中修改数据集路径。*\n\n### 2. 训练模型\n使用提供的训练脚本开始模型训练。通常需要指定超参数（如信噪比 SNR、批量大小 batch_size 等）。\n\n```bash\n# 示例：启动训练\npython train.py --snr 20 --epochs 100\n```\n\n### 3. 评估与测试\n训练完成后，运行测试脚本验证模型性能（如 NMSE, BLER 等指标）。\n\n```bash\n# 示例：运行测试\npython test.py --weights weights\u002Fbest_model.h5\n```\n\n### 4. 探索更多方向\n回到本索引库，你可以尝试其他热门方向：\n*   **调制识别 (AMC)**: 搜索 `CNN_AMC` 或 `Deep-Architectures-for-Modulation-Recognition`\n*   **信道解码**: 搜索 `Deepcode` 或 `Iterative-BP-CNN`\n*   **波束成形**: 搜索 `BF-design-with-DL`\n\n> **交流贡献**: 如果你发现了新的开源论文代码未收录在此列表中，欢迎前往原 GitHub 仓库提交 Issue 进行补充。","某通信实验室的硕士研究生正致力于研究“基于深度学习的鲁棒信道估计”，试图复现一篇顶会论文中的扩散模型算法以验证其在低信噪比下的性能。\n\n### 没有 Paper-with-Code-of-Wireless-communication-Based-on-DL 时\n- **检索效率极低**：需要在 arXiv、IEEE Xplore 等多个平台手动筛选海量论文，难以快速定位到同时具备“开源代码”和“高相关性”的研究成果。\n- **复现门槛过高**：找到的多数高质量论文未公开代码，或代码散落在作者个人主页甚至已失效，导致无法验证算法有效性，陷入“纸上谈兵”的困境。\n- **方向摸索盲目**：缺乏系统性的分类指引，不清楚物理层优化、资源调度等细分领域有哪些成熟的基线模型（Baseline），容易在过时的方法上浪费时间。\n- **环境配置困难**：即便找到代码，往往缺少明确的依赖说明或数据集链接，配置仿真环境（如 Sionna 库）需耗费数周时间排查错误。\n\n### 使用 Paper-with-Code-of-Wireless-communication-Based-on-DL 后\n- **精准直达目标**：通过\"Physical layer optimization\"分类直接锁定《Deep Diffusion Models for Robust Channel Estimation》及其对应的 `diffusion-channels` 仓库，秒级获取论文与代码链接。\n- **复现流程顺畅**：直接克隆经过验证的开源项目，利用仓库中完整的训练脚本和预训练模型，将原本需要一个月的复现周期缩短至三天。\n- **技术视野开阔**：借助清晰的目录结构，快速对比了 LoRD-Net、MetaCC 等不同架构的优劣，迅速确立了适合当前课题的改进切入点。\n- **生态工具赋能**：顺藤摸瓜发现并集成了列表中推荐的 `sionna` 开源库，解决了底层信号处理模块的构建难题，专注于核心算法创新。\n\nPaper-with-Code-of-Wireless-communication-Based-on-DL 将通信与深度学习交叉领域的碎片化资源转化为结构化知识，极大地降低了科研入门门槛并加速了可复现研究的落地。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FML4Comm-Netw_Paper-with-Code-of-Wireless-communication-Based-on-DL_56536347.png","ML4Comm-Netw","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FML4Comm-Netw_e94fbc31.png","",null,"https:\u002F\u002Fgithub.com\u002FML4Comm-Netw",2232,675,"2026-04-05T04:37:50","未说明",{"notes":85,"python":83,"dependencies":86},"本项目是一个论文与代码的索引列表（Awesome List），而非单一的独立软件工具。它整理了多个基于深度学习的无线通信开源项目链接。具体的运行环境需求（如操作系统、GPU、Python 版本及依赖库）因列表中包含的各个子项目（如 Sionna, CsiNet, OAMP-Net 等）而异，用户需点击对应论文的代码链接，查阅各子项目的 README 以获取详细的安装和运行要求。",[],[13],[89,90,91,92,93,94,95,96],"wireless-communication","deep-learning","channel-estimation","mimo","machine-learning","power-control","communication-systems","mimo-systems","2026-03-27T02:49:30.150509","2026-04-06T12:16:00.770423",[],[]]