[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-jvpoulos--causal-ml":3,"tool-jvpoulos--causal-ml":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},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,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},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",150037,2,"2026-04-10T23:33:47",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},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。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":76,"owner_website":79,"owner_url":80,"languages":76,"stars":81,"forks":82,"last_commit_at":83,"license":76,"difficulty_score":84,"env_os":85,"env_gpu":86,"env_ram":86,"env_deps":87,"category_tags":90,"github_topics":91,"view_count":10,"oss_zip_url":76,"oss_zip_packed_at":76,"status":17,"created_at":106,"updated_at":107,"faqs":108,"releases":109},2178,"jvpoulos\u002Fcausal-ml","causal-ml","Must-read papers and resources related to causal inference and machine (deep) learning","causal-ml 是一个专注于因果推断与机器学习交叉领域的开源知识库，旨在为研究者和开发者提供该方向的核心论文、代码资源及学习指南。它主要解决了当前 AI 领域在从“相关性分析”迈向“因果性理解”过程中，资料分散、前沿动态难以追踪的痛点。\n\n与传统机器学习工具不同，causal-ml 并非一个直接调用的算法库，而是一份精心整理的“必读清单”。其内容涵盖异质性处理效应估计、因果表示学习、半参数推断、策略学习以及因果推荐系统等关键主题，并延伸至社会科学、医疗健康等具体应用场景。独特的亮点在于其结构化的分类体系，不仅收录了从经典理论到 Transformer 等最新架构在因果估计中应用的顶会论文，还关联了相应的代码实现、基准数据集、课程资源及行业实践案例。\n\n这份资源特别适合从事因果机器学习研究的学者、希望将因果逻辑融入模型的数据科学家，以及对该前沿方向感兴趣的高级开发者使用。无论是想要快速把握领域全貌的初学者，还是寻求特定技术突破的资深专家，都能通过 causal-ml 高效地获取高质量信息，加速科研探索与技术落地进程。","# Must-read recent papers and resources on {Causal}∩{ML}\n\nContributions are welcome. Inspired by [GNNpapers](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGNNPapers).\n\n## [Content](#content)\n\n\u003Ctable>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#survey-papers\">1. Surveys\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr> \n\u003Ctr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#individual-treatment-effects\">2. Individual treatment effects\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctd> \u003Ca href=\"#heterogeneous-treatment-effects\">2.1. Heterogeneous treatment effects\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#static-data\">2.2. Static data\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#temporal-data\">2.3. Temporal data\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#representation-learning\">3. Representation learning\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#semiparametric-inference\">4. Semiparametric \u002F double robust inference\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#policy-learning\">5. Policy learning \u002F causal discovery\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#causal-recommendation\">6. Causal recommendation\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#causal-reinforcement-learning\">7. Causal reinforcement learning\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#causal-reinforcement-learning\">8. Feature selection in causal inference\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#applications\">9. Applications\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctd> \u003Ca href=\"#social-sciences\">9.1. Social Sciences\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#text\">9.2. Text\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#health\">9.3. Health\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#resources\">10. Resources\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr> \n    \u003Ctd> \u003Ca href=\"#workshops\">10.1. Workshops\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#proceedings\">10.2. Proceedings\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#code-libraries\">10.3. Code libraries\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#benchmark-datasets\">10.4. Benchmark datasets\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#courses\">10.5. Courses\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#industry\">10.6. Industry\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#groups\">10.7. Groups\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#lists\">10.8. Lists\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#books\">10.9. Books\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003C\u002Ftable>\n\n## [Survey papers](#content)\n\n1. **Causal Machine Learning: A Survey and Open Problems**, 2022. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.15475)\n\n    Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva.\n\t\n1. **A Unified Survey of Heterogeneous Treatment Effect Estimation and Uplift Modeling**, *ACM Computing Surveys*, 2022. [paper](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3466818)\n\n    Weijia Zhang, Jiuyong Li, Lin Liu.\n\n1. **Toward Causal Representation Learning**, *IEEE*, 2021. [paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9363924)\n    \n    Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio.\n\n1. **A Survey of Learning Causality with Data: Problems and Methods**, *ACM*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.09337)\n    \n    Ruocheng Guo, Lu Cheng, Jundong Li, P. Richard Hahn, Huan Liu.\n\n1. **Machine learning and causal inference for policy evaluation**, *KDD*, 2015. [paper](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=2785466)\n    \n    Susan Athey.\n\n## [Individual treatment effects](#content) \n\n### [Heterogeneous treatment effects](#content)  \n\n1. **Can Transformers be Strong Treatment Effect Estimators?**, *arxiv*, 2022. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01336) [code](https:\u002F\u002Fgithub.com\u002Fhlzhang109\u002FTransTEE)\n\n    Yi-Fan Zhang, Hanlin Zhang, Zachary C. Lipton, Li Erran Li, Eric P. Xing.\n\n1. **Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms**, *AISTATS*, 2021. [paper](https:\u002F\u002Fproceedings.mlr.press\u002Fv130\u002Fcurth21a.html)\n    \n    Alicia Curth, Mihaela van der Schaar.\n\n1. **Causal Effect Inference for Structured Treatments**, *NeurIPS*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.01939) [code](https:\u002F\u002Fgithub.com\u002FJeanKaddour\u002FSIN)\n    \n    Jean Kaddour, Yuchen Zhu, Qi Liu, Matt J. Kusner, Ricardo Silva.\n\t\n1. **Treatment Effect Estimation with Disentangled Latent Factors**, *AAAI*, 2021. [paper](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17304) [code](https:\u002F\u002Fgithub.com\u002FWeijiaZhang24\u002FTEDVAE)\n    \n    Weijia Zhang, Lin Liu, Jiuyong Li.\n\n1. **Generic Machine Learning Inference on Heterogenous Treatment Effects in Randomized Experiments**, *arXiv*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.04802)\n\n    Victor Chernozhukov, Mert Demirer, Esther Duflo, Iván Fernández-Val.\n\n1. **Quasi-Oracle Estimation of Heterogeneous Treatment Effects**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.04912)\n\n    Xinkun Nie, Stefan Wager.\n\n1. **Generalized Random Forests**, *Annals of Statistics*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1610.01271)\n\n    Susan Athey, Julie Tibshirani, Stefan Wager.\n\n1. **Machine Learning Estimation of Heterogeneous Treatment Effects with Instruments**, *NeurIPS*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.10176)\n    \n    Vasilis Syrgkanis, Victor Lei, Miruna Oprescu, Maggie Hei, Keith Battocchi, Greg Lewis.\n\n1. **Orthogonal Random Forest for Causal Inference**, *PMLR*, 2019. [paper](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Foprescu19a.html)\n\n    Miruna Oprescu, Vasilis Syrgkanis, Zhiwei Steven Wu.\n\n1. **Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning**, *PNAS*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.03461)\n\n    Sören R. Künzel, Jasjeet S. Sekhon, Peter J. Bickel, Bin Yu.\n\n1. **Machine Learning Analysis of Heterogeneity in the Effect of Student Mindset Interventions**, *Observational Studies*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.05975)\n    \n    Fredrik D. Johansson.\n\n1. **Estimation and Inference of Heterogeneous Treatment Effects using Random Forests**, *JASA*, 2018. [paper](https:\u002F\u002Famstat.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F01621459.2017.1319839#.XaPLBeZKhhE)\n    \n    Stefan Wager, Susan Athey.\n\n1. **Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design**, *PMLR*, 2018. [paper](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Falaa18a.html)\n    \n    Ahmed Alaa, Mihaela Schaar.\n\n1. **Transfer Learning for Estimating Causal Effects using Neural Networks**, *arXiv*, 2018. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.07804)\n\n    Sören R. Künzel, Bradly C. Stadie, Nikita Vemuri, Varsha Ramakrishnan, Jasjeet S. Sekhon, Pieter Abbeel.\n\n1. **Recursive partitioning for heterogeneous causal effects**, *PNAS*, 2016. [paper](https:\u002F\u002Fwww.pnas.org\u002Fcontent\u002F113\u002F27\u002F7353)\n    \n    Susan Athey, Guido Imbens.\n\n1. **Machine Learning Methods for Estimating Heterogeneous Causal Effects**, *ArXiv*, 2015. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1504.01132v1)\n\n    Susan Athey, Guido W. Imbens.\n\n\n### [Static data](#content) \n\n1. **VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments**, *ICLR*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.07861)  [code](https:\u002F\u002Fgithub.com\u002Flushleaf\u002Fvarying-coefficient-net-with-functional-tr)\n\n    Lizhen Nie, Mao Ye, Qiang Liu, Dan Nicolae.\n\n1. **Learning Counterfactual Representations for Estimating Individual Dose-Response Curves**, *AAAI*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00981) [code](https:\u002F\u002Fgithub.com\u002Fd909b\u002Fdrnet)\n\n    Patrick Schwab, Lorenz Linhardt, Stefan Bauer, Joachim M. Buhmann, Walter Karlen.\n\n1. **Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks**, *NeurIPS*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12326) [code](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FSCIGAN)\n\n    Ioana Bica, James Jordon, Mihaela van der Schaar.\n\n1. **Learning Individual Causal Effects from Networked Observational Data**, *WSDM*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03485) [code](https:\u002F\u002Fgithub.com\u002Frguo12\u002Fnetwork-deconfounder-wsdm20)\n\n    Ruocheng Guo, Jundong Li, Huan Liu.\n\n1. **Learning Overlapping Representations for the Estimation of Individualized Treatment Effects**, *AISTATS*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.04754)\n\n    Yao Zhang, Alexis Bellot, Mihaela van der Schaar.\n\n1. **Adapting Neural Networks for the Estimation of Treatment Effects**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.02120) [code](http:\u002F\u002Fgithub.com\u002Fclaudiashi57\u002Fdragonnet)\n    \n    Claudia Shi, David M. Blei, Victor Veitch.\n\n1. **Program Evaluation and Causal Inference with High-Dimensional Data**, *arXiv*, 2018. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1311.2645)\n    \n    Alexandre Belloni, Victor Chernozhukov, Ivan Fernández-Val, Christian Hansen.    \n\n1. **GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets**, *ICLR*, 2018. [paper](https:\u002F\u002Fopenreview.net\u002Fpdf?id=ByKWUeWA-) [code](https:\u002F\u002Fgithub.com\u002Fjsyoon0823\u002FGANITE)\n    \n    Jinsung Yoon, James Jordon, Mihaela van der Schaar.\n\n1. **Estimation of Individual Treatment Effect in Latent Confounder Models via Adversarial Learning**, *arXiv*, 2018. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.08943)\n    \n    Changhee Lee, Nicholas Mastronarde, Mihaela van der Schaar.\n\n1. **Deep IV: A Flexible Approach for Counterfactual Prediction**, *PMLR*, 2017. [paper](http:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Fhartford17a.html)\n    \n    Uri Shalit, Fredrik D. Johansson, David Sontag.\n\n1. **Causal Effect Inference with Deep Latent-Variable Models**, *arXiv*, 2017. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.08821) [code](https:\u002F\u002Fgithub.com\u002FAMLab-Amsterdam\u002FCEVAE)\n    \n    Christos Louizos, Uri Shalit, Joris Mooij, David Sontag, Richard Zemel, Max Welling.\n\n1. **Estimating individual treatment effect: generalization bounds and algorithms**, *PMLR*, 2017. [paper](http:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Fshalit17a.html) [code](https:\u002F\u002Fgithub.com\u002Fclinicalml\u002Fcfrnet)\n    \n    Uri Shalit, Fredrik D. Johansson, David Sontag.\n\n### [Temporal data](#content) \n\n1. **Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders**, *ICML*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00450) [code](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FTime-Series-Deconfounder)\n\n    Ioana Bica, Ahmed M. Alaa, Mihaela van der Schaar.\n\n1. **Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations**, *ICLR*, 2020. [paper](https:\u002F\u002Fopenreview.net\u002Fpdf?id=BJg866NFvB) [code](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FCounterfactual-Recurrent-Network)\n\n    Ioana Bica, Ahmed M. Alaa, James Jordon, Mihaela van der Schaar.\n\n1. **Generative Learning of Counterfactual for Synthetic Control Applications in Econometrics**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.07178)\n    \n    Chirag Modi, Uros Seljak.\n\n1. **Robust Synthetic Control**, *JMLR*, 2019. [paper](http:\u002F\u002Fwww.jmlr.org\u002Fpapers\u002Fvolume19\u002F17-777.pdf)\n    \n    Muhammad Amjad, Devavrat Shah, Dennis Shen.\n\n1. **ArCo: An artificial counterfactual approach for high-dimensional panel time-series data**, *Journal of Econometrics*, 2018. [paper](https:\u002F\u002Fpapers.ssrn.com\u002Fsol3\u002Fpapers.cfm?abstract_id=2823687)\n    \n    Carlos Carvalho, Ricardo Masini, Marcelo C. Medeiros.\n\n1. **Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks**, *NIPS*, 2018. [paper](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7977-forecasting-treatment-responses-over-time-using-recurrent-marginal-structural-networks) [code](https:\u002F\u002Fgithub.com\u002Fsjblim\u002Frmsn_nips_2018)\n    \n    Sonali Parbhoo, Stefan Bauer, Patrick Schwab.\n\n## [Representation learning](#content)   \n\n1. **Deep Structural Causal Models for Tractable Counterfactual Inference**, *NeurIPS*, 2020. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.06485) [code](https:\u002F\u002Fgithub.com\u002Fbiomedia-mira\u002Fdeepscm)\n\n    Nick Pawlowski, Daniel C. Castro, Ben Glocker.\n\n1. **NCoRE: Neural Counterfactual Representation Learning for Combinations of Treatments**, *arXiv*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.11175)\n    \n    Sonali Parbhoo, Stefan Bauer, Patrick Schwab.\n\n1. **Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.00656) [code](https:\u002F\u002Fgithub.com\u002Fd909b\u002Fperfect_match)\n    \n    Patrick Schwab, Lorenz Linhardt, Walter Karlen.\n\n1. **Representation Learning for Treatment Effect Estimation from Observational Data**, *NeurIPS*, 2019. [paper](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7529-representation-learning-for-treatment-effect-estimation-from-observational-data.pdf) \n    \n    Liuyi Yao et al.\n\n1. **Invariant Models for Causal Transfer Learning**, *JMLR*, 2018. [paper](http:\u002F\u002Fjmlr.org\u002Fpapers\u002Fv19\u002F16-432.html) \n    \n    Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner, Jonas Peters.\n\n1. **Learning Representations for Counterfactual Inference**, *arXiv*, 2018. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1605.03661) [code](https:\u002F\u002Fgithub.com\u002Fclinicalml\u002Fcfrnet)\n    \n    Fredrik D. Johansson, Uri Shalit, David Sontag.\n\n## [Semiparametric \u002F double robust inference](#content)  \n\n1. **Sparsity Double Robust Inference of Average Treatment Effects**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.00744)\n    \n    Jelena Bradic, Stefan Wager, Yinchu Zhu.\n\n1. **Deep Neural Networks for Estimation and Inference**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.09953)\n    \n    Max H. Farrell, Tengyuan Liang, Sanjog Misra.\n\n1. **Deep Counterfactual Networks with Propensity-Dropout**, *arXiv*, 2017. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.05966)\n    \n    Ahmed M. Alaa, Michael Weisz, Mihaela van der Schaar.\n\n1. **Double\u002FDebiased Machine Learning for Treatment and Causal Parameters**, *arXiv*, 2017. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1608.00060)\n    \n    Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo, Christian Hansen, Whitney Newey, James Robins.\n\n1. **Doubly Robust Policy Evaluation and Optimization**, *Statistical Science*, 2014. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1503.02834)\n    \n    Miroslav Dudík, Dumitru Erhan, John Langford, Lihong Li.\n\n## [Policy learning \u002F causal discovery](#content)  \n\n1. **Differentiable Causal Discovery Under Unmeasured Confounding**, *arXiv*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.06978)\n    \n    Rohit Bhattacharya, Tushar Nagarajan, Daniel Malinsky, Ilya Shpitser.\n\n1. **Causal Discovery with Attention-Based Convolutional Neural Networks**, *Machine Learning and Knowledge Extraction*, 2019. [paper](https:\u002F\u002Fwww.mdpi.com\u002F2504-4990\u002F1\u002F1\u002F19) [code](https:\u002F\u002Fgithub.com\u002FM-Nauta\u002FTCDF)\n    \n    Meike Nauta, Doina Bucur, Christin Seifert.\n\n1. **A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.10912)\n    \n    Yoshua Bengio, Tristan Deleu, Nasim Rahaman, Rosemary Ke, Sébastien Lachapelle, Olexa Bilaniuk, Anirudh Goyal, Christopher Pal.\n\n1. **Causal Discovery with Reinforcement Learning**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04477)\n    \n    Shengyu Zhu, Zhitang Chen.\n\n1. **CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1709.02023)\n    \n    Murat Kocaoglu, Christopher Snyder, Alexandros G. Dimakis, Sriram Vishwanath.\n\n1. **Learning When-to-Treat Policies**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09751)\n    \n    Xinkun Nie, Emma Brunskill, Stefan Wager.\n\n1. **Learning Neural Causal Models from Unknown Interventions**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.01075) [code](https:\u002F\u002Fgithub.com\u002Fnke001\u002Fcausal_learning_unknown_interventions)\n    \n    Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio.\n\n1. **Counterfactual Policy Optimization Using Domain-Adversarial Neural Networks**, *ICML*, 2018. [paper](http:\u002F\u002Fmedianetlab.ee.ucla.edu\u002Fpapers\u002Fcf_treat_v5)\n    \n    Onur Atan, William R. Zame, Mihaela van der Schaar.\n\n1. **Causal Bandits: Learning Good Interventions via Causal Inference**, *NIPS*, 2016. [paper](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F6195-causal-bandits-learning-good-interventions-via-causal-inference)\n    \n    Finnian Lattimore, Tor Lattimore, Mark D. Reid.\n\n1. **Counterfactual Risk Minimization: Learning from Logged Bandit Feedback**, *arXiv*, 2015. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1502.02362)\n    \n    Adith Swaminathan, Thorsten Joachims.\n\n## [Causal recommendation](#content) \n\n1. **The Deconfounded Recommender: A Causal Inference Approach to Recommendation**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.06581) [code](https:\u002F\u002Fgithub.com\u002Fblei-lab\u002Fdeconfounder_tutorial)\n    \n    Yixin Wang, Dawen Liang, Laurent Charlin, David M. Blei. \n\n1. **The Blessings of Multiple Causes**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.06826)\n    \n    Yixin Wang, David M. Blei. \n\n\u003Cdetails>\u003Csummary> comments \u003C\u002Fsummary> \n\n3. **Comment: Reflections on the Deconfounder**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.08042)\n\n    Alexander D'Amour\n\n1. **On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.10286)\n\n    Alexander D'Amour\n\n1. **Comment on \"Blessings of Multiple Causes\"**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05438)\n    \n    Elizabeth L. Ogburn, Ilya Shpitser, Eric J. Tchetgen Tchetgen.\n\n1. **The Blessings of Multiple Causes: A Reply to Ogburn et al. (2019)**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.07320)\n    \n    Yixin Wang, David M. Blei.\n\n\u003C\u002Fdetails>\n\n7. **Recommendations as Treatments: Debiasing Learning and Evaluation**, *PMLR*, 2016. [paper](http:\u002F\u002Fproceedings.mlr.press\u002Fv48\u002Fschnabel16.html)\n    \n    Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak, Thorsten Joachims.\n\n1. **Collaborative Prediction and Ranking with Non-Random Missing Data**, *RecSys*, 2009. [paper](http:\u002F\u002Fwww.cs.toronto.edu\u002F~zemel\u002Fdocuments\u002Facmrec2009-MarlinZemel.pdf)\n    \n    Benjamin M. Marlin, Richard S. Zemel.\n\n## [Causal reinforcement learning](#content) \n\n1. **Counterfactual Multi-Agent Policy Gradients**, *AAAI*, 2018. [paper](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI18\u002Fpaper\u002FviewPaper\u002F17193)\n    \n    Jakob N. Foerster, Gregory Farquhar, Triantafyllos Afouras, Nantas Nardelli, Shimon Whiteson. \n\n## [Feature Selection in causal inference](#content)\n\n1. **Ultra-high dimensional variable selection for doubly robust causal inference**, *Biometrics*, 2022. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.14190) [code](https:\u002F\u002Fgithub.com\u002Fdingketang\u002Fultra-high-DRCI) [slides](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1OlwNi9eMu_MQe3TyiHpHg2ULdfGD2x0S\u002Fview?usp=sharing)\n\n    Dingke Tang, Dehan Kong, Wenliang Pan, Linbo Wang\n\n1. **Outcome‐adaptive lasso: variable selection for causal inference**, *Biometrics* 2017. [paper](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdf\u002F10.1111\u002Fbiom.12679?casa_token=_xFuHHhoWlAAAAAA:gKO0JyJC0g54pOfbOVlNew7t1M29UD_A46yJJUAGiLAuxO87p4lGmMneYklKfuWGiHCitIbvKtjfEMAN)  [video](https:\u002F\u002Fcrossminds.ai\u002Fvideo\u002Fvariable-selection-for-causal-inference-outcome-adaptive-lasso-6070a5f9fa08279acdb2124a\u002F)\n\n    Susan M. Shortreed, Ashkan Ertefaie\n\n## [Applications](#content)\n\n### [Social sciences](#content)\n\n1. **Double machine learning-based programme evaluation under unconfoundedness**, *The Econometrics Journal*, 2022. [paper](https:\u002F\u002Fdoi.org\u002F10.1093\u002Fectj\u002Futac015)\n    \n    Michael C Knaus.\n\n1. **State-Building through Public Land Disposal? An Application of Matrix Completion for Counterfactual Prediction**, *arXiv*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.08028) [code](https:\u002F\u002Fgithub.com\u002Fjvpoulos\u002Fhomesteads)\n    \n    Jason Poulos.\n\n1. **RNN-based counterfactual prediction, with an application to homestead policy and public schooling**, *JRSS-C*, 2021. [paper](http:\u002F\u002Fjasonvpoulos.com\u002Fpapers\u002F17117351.pdf) [code](https:\u002F\u002Fgithub.com\u002Fjvpoulos\u002Frnns-causal)\n    \n    Jason Poulos, Shuxi Zeng.\n\n1. **Estimating Treatment Effects with Causal Forests: An Application**, *arXiv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.07409)\n    \n    Susan Athey, Stefan Wager.\n\n1. **Ensemble Methods for Causal Effects in Panel Data Settings**, *AER P&P*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.10079)\n    \n    Susan Athey, Mohsen Bayati, Guido W. Imbens, Zhaonan Qu.\n\n### [Text](#content)\n\n1. **Counterfactual Data Augmentation for Neural Machine Translation**, *ACL*, 2021. [paper](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.18\u002F) [code](https:\u002F\u002Fgithub.com\u002Fxxxiaol\u002FGCI)\n    \n     Qi Liu, Matt Kusner, Phil Blunsom.\n\n1. **Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis**, *arXIv*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.09420) [code](https:\u002F\u002Fgithub.com\u002Fxxxiaol\u002FGCI)\n    \n     Xiao Liu, Da Yin, Yansong Feng, Yuting Wu, Dongyan Zhao.\n\n1. **Causal Effects of Linguistic Properties**, *arXIv*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.12919)\n    \n     Reid Pryzant, Dallas Card, Dan Jurafsky, Victor Veitch, Dhanya Sridhar.\n\n1. **Sketch and Customize: A Counterfactual Story Generator**, *arXIv*, 2021. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.00929)\n    \n    Changying Hao, Liang Pang, Yanyan Lan, Yan Wang, Jiafeng Guo, Xueqi Cheng.\n\n1. **Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition**, *EMNLP*, 2020. [paper](https:\u002F\u002Fgithub.com\u002Fxijiz\u002Fcfgen\u002Fblob\u002Fmaster\u002Fdocs\u002Fcfgen.pdf) [code](https:\u002F\u002Fgithub.com\u002Fxijiz\u002Fcfgen)\n    \n    Xiangji Zeng, Yunliang Li, Yuchen Zhai, Yin Zhang.\n\n1. **Using Text Embeddings for Causal Inference**, *arXIv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.12741) [code](https:\u002F\u002Fgithub.com\u002Fblei-lab\u002Fcausal-text-embeddings)\n    \n    Victor Veitch, Dhanya Sridhar, David M. Blei.\n\n1. **Counterfactual Story Reasoning and Generation**, *arXIv*, 2019. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.04076)\n    \n    Lianhui Qin, Antoine Bosselut, Ari Holtzman, Chandra Bhagavatula, Elizabeth Clark, Yejin Choi.\n\n1. **How to Make Causal Inferences Using Texts**, *arXIv*, 2018. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.02163)\n\n    Naoki Egami, Christian J. Fong, Justin Grimmer, Margaret E. Roberts, Brandon M. Stewart.\n\n### [Health](#content)\n\n1. **Targeted learning in observational studies with multi-level treatments: An evaluation of antipsychotic drug treatment safety for patients with serious mental illnesses**, *arXIv*, 2022. [paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.15367) [code](https:\u002F\u002Fgithub.com\u002Fjvpoulos\u002Fmulti-tmle)\n    \n     Jason Poulos, Marcela Horvitz-Lennon, Katya Zelevinsky, Thomas Huijskens, Pooja Tyagi, Jiaju Yan, Jordi Diaz, Tudor Cristea-Platon, Sharon-Lise Normand.\n\n## [Resources](#content)\n\n### [Workshops](#content)\n\n1. **NeurIPS 2021 Workshop** [link](https:\u002F\u002Fwhy21.causalai.net\u002F)\n\n1. **UAI 2021 Workshop** [link](https:\u002F\u002Fsites.google.com\u002Fuw.edu\u002Fcausaluai2021\u002Fhome?authuser=0)\n\n1. **KDD 2021 Workshop** [link](https:\u002F\u002Fbcirwis2021.github.io\u002Fcfp.html)\n\n1. **ICML 2021 Workshop** [link](https:\u002F\u002Fsites.google.com\u002Fview\u002Fnaci2021\u002Fhome)\n\n1. **EMNLP 2021 Workshop** [link](https:\u002F\u002Fcausaltext.github.io\u002F2021\u002F)\n\n1. **NeurIPS 2020 Workshop** [link](https:\u002F\u002Fwww.cmu.edu\u002Fdietrich\u002Fcausality\u002Fneurips20ws\u002F)\n\n1. **NeurIPS 2019 Workshop** [link](http:\u002F\u002Ftripods.cis.cornell.edu\u002Fneurips19_causalml\u002F)\n\n1. **NIPS 2018 Workshop** [link](https:\u002F\u002Fsites.google.com\u002Fview\u002Fnips2018causallearning\u002Fhome)\n\n1. **NIPS 2017 Workshop** [link](https:\u002F\u002Fsites.google.com\u002Fview\u002Fcausalnips2017)\n\n1. **NIPS 2016 Workshop** [link](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fwhatif2016nips\u002F)\n\n1. **NIPS 2013 Workshop** [link](http:\u002F\u002Fclopinet.com\u002Fisabelle\u002FProjects\u002FNIPS2013\u002F)\n\n### [Proceedings](#content)\n\n1. **PMLR, Volume 6: Causality: Objectives and Assessment, 12 December 2008, Whistler, Canada** [link](http:\u002F\u002Fproceedings.mlr.press\u002Fv6\u002F)\n\n### [Code libraries](#content)\n\n1. **Causal Inference 360: A Python package for inferring causal effects from observational data.** [link](https:\u002F\u002Fgithub.com\u002FIBM\u002Fcausallib)\n\n1. **WhyNot: A Python package connecting tools from causal inference and reinforcement learning with a range of complex simulators** [link](https:\u002F\u002Fgithub.com\u002Fzykls\u002Fwhynot)\n\n1. **EconML: A Python Package for ML-Based Heterogeneous Treatment Effects Estimation** [link](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FEconML)\n\n1. **Uplift modeling and causal inference with machine learning algorithms** [link](https:\u002F\u002Fgithub.com\u002Fuber\u002Fcausalml)\n\n### [Benchmark datasets](#content)\n\n1. **IHDP, Jobs, and News benchmarks** [link](https:\u002F\u002Ffredjo.com\u002F)\n\n1. **Twins** [link](http:\u002F\u002Fwww.nber.org\u002Fdata\u002Flinked-birth-infant-death-data-vitalstatistics-data.htm)\n\n1. **Causality workbench** [link](http:\u002F\u002Fwww.causality.inf.ethz.ch\u002Frepository.php?page=data)\n\n### [Courses](#content)\n\n1. **CS7792 - Counterfactual Machine Learning** [link](http:\u002F\u002Fwww.cs.cornell.edu\u002Fcourses\u002Fcs7792\u002F2016fa\u002F)\n\n1. **Introduction to Causal Inference** [link](https:\u002F\u002Fwww.bradyneal.com\u002Fcausal-inference-course)\n\n1. **Machine Learning & Causal Inference: A Short Course** [link](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLxq_lXOUlvQAoWZEqhRqHNezS30lI49G-)\n\n1. **KDD 2020: Lecture Style Tutorials: Casual Inference Meets Machine Learning** [link](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=DbW2e2q8Gjs)\n\n### [Industry](#content)\n\n1. **Causality and Machine Learning: Microsoft Research** [link](https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fgroup\u002Fcausal-inference\u002F#!publications)\n\n### [Groups](#content)\n\n1. **Society for Causal Inference** [link](https:\u002F\u002Fsci-info.org\u002F)\n\n1. **Research Laboratory led by Prof. Mihaela van der Schaar** [link](http:\u002F\u002Fwww.vanderschaar-lab.com\u002FNewWebsite\u002Fcausal_inference_and_treatment_effects.html)\n\n### [Lists](#content)\n\n1. **An index of algorithms for learning causality with data** [link](https:\u002F\u002Fgithub.com\u002Frguo12\u002Fawesome-causality-algorithms)\n\n1. **An index of datasets that can be used for learning causality** [link](https:\u002F\u002Fgithub.com\u002Frguo12\u002Fawesome-causality-data)\n\n1. **Papers about Causal Inference and Language** [link](https:\u002F\u002Fgithub.com\u002Fcausaltext\u002Fcausal-text-papers)\n\n### [Books](#content)\n\n1. **Causal Machine Learning** [link](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fcausal-machine-learning)\n","# {因果}∩{机器学习}领域的必读最新论文与资源\n\n欢迎贡献。灵感来源于 [GNNpapers](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FGNNPapers)。\n\n## [目录](#content)\n\n\u003Ctable>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#survey-papers\">1. 综述论文\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr> \n\u003Ctr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#individual-treatment-effects\">2. 个体治疗效应\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctd> \u003Ca href=\"#heterogeneous-treatment-effects\">2.1. 异质性治疗效应\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#static-data\">2.2. 静态数据\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#temporal-data\">2.3. 时序数据\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#representation-learning\">3. 表征学习\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#semiparametric-inference\">4. 半参数\u002F双重稳健推断\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#policy-learning\">5. 策略学习\u002F因果发现\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#causal-recommendation\">6. 因果推荐\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#causal-reinforcement-learning\">7. 因果强化学习\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#causal-reinforcement-learning\">8. 因果推断中的特征选择\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#applications\">9. 应用\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr>\n    \u003Ctd> \u003Ca href=\"#social-sciences\">9.1. 社会科学\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#text\">9.2. 文本\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#health\">9.3. 健康\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\u003Ctd colspan=\"2\">\u003Ca href=\"#resources\">10. 资源\u003C\u002Fa>\u003C\u002Ftd>\u003C\u002Ftr> \n    \u003Ctd> \u003Ca href=\"#workshops\">10.1. 研讨会\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#proceedings\">10.2. 会议论文集\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#code-libraries\">10.3. 代码库\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#benchmark-datasets\">10.4. 基准数据集\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#courses\">10.5. 课程\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#industry\">10.6. 工业界\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#groups\">10.7. 团体\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd> \u003Ca href=\"#lists\">10.8. 列表\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003Ctr>\n    \u003Ctd> \u003Ca href=\"#books\">10.9. 书籍\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr> \n\u003C\u002Ftable>\n\n## [综述论文](#content)\n\n1. **因果机器学习：综述与开放问题**, 2022年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.15475)\n\n    Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva.\n\t\n1. **异质性治疗效应估计与提升建模的统一综述**, *ACM 计算机科学评论*, 2022年. [论文](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fabs\u002F10.1145\u002F3466818)\n\n    Weijia Zhang, Jiuyong Li, Lin Liu.\n\n1. **迈向因果表征学习**, *IEEE*, 2021年. [论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9363924)\n    \n    Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio。\n\n1. **利用数据学习因果关系的综述：问题与方法**, *ACM*, 2020年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.09337)\n    \n    Ruocheng Guo, Lu Cheng, Jundong Li, P. Richard Hahn, Huan Liu。\n\n1. **用于政策评估的机器学习与因果推断**, *KDD*, 2015年. [论文](https:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=2785466)\n    \n    Susan Athey。\n\n## [个体治疗效应](#content) \n\n### [异质性治疗效应](#content)  \n\n1. **Transformer能否成为强大的治疗效应估计器？**, *arXiv*, 2022年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2202.01336) [代码](https:\u002F\u002Fgithub.com\u002Fhlzhang109\u002FTransTEE)\n\n    Yi-Fan Zhang, Hanlin Zhang, Zachary C. Lipton, Li Erran Li, Eric P. Xing。\n\n1. **异质性治疗效应的非参数估计：从理论到学习算法**, *AISTATS*, 2021年. [论文](https:\u002F\u002Fproceedings.mlr.press\u002Fv130\u002Fcurth21a.html)\n    \n    Alicia Curth, Mihaela van der Schaar。\n\n1. **面向结构化干预的因果效应推断**, *NeurIPS*, 2021年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.01939) [代码](https:\u002F\u002Fgithub.com\u002FJeanKaddour\u002FSIN)\n    \n    Jean Kaddour, Yuchen Zhu, Qi Liu, Matt J. Kusner, Ricardo Silva。\n\t\n1. **基于解耦潜在因子的治疗效应估计**, *AAAI*, 2021年. [论文](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F17304) [代码](https:\u002F\u002Fgithub.com\u002FWeijiaZhang24\u002FTEDVAE)\n    \n    Weijia Zhang, Lin Liu, Jiuyong Li。\n\n1. **随机实验中异质性治疗效应的通用机器学习推断**, *arXiv*, 2020年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.04802)\n\n    Victor Chernozhukov, Mert Demirer, Esther Duflo, Iván Fernández-Val。\n\n1. **异质性治疗效应的准最优估计**, *arXiv*, 2019年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.04912)\n\n    Xinkun Nie, Stefan Wager。\n\n1. **广义随机森林**, *统计学年鉴*, 2019年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1610.01271)\n\n    Susan Athey, Julie Tibshirani, Stefan Wager。\n\n1. **使用工具变量的异质性治疗效应机器学习估计**, *NeurIPS*, 2019年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.10176)\n    \n    Vasilis Syrgkanis, Victor Lei, Miruna Oprescu, Maggie Hei, Keith Battocchi, Greg Lewis。\n\n1. **用于因果推断的正交随机森林**, *PMLR*, 2019年. [论文](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Foprescu19a.html)\n\n    Miruna Oprescu, Vasilis Syrgkanis, Zhiwei Steven Wu。\n\n1. **基于元学习的异质性治疗效应机器学习估计方法**, *PNAS*, 2019年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.03461)\n\n    Sören R. Künzel, Jasjeet S. Sekhon, Peter J. Bickel, Bin Yu。\n\n1. **学生心态干预效果异质性的机器学习分析**, *观察性研究*, 2019年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.05975)\n    \n    Fredrik D. Johansson。\n\n1. **利用随机森林进行异质性治疗效应的估计与推断**, *JASA*, 2018年. [论文](https:\u002F\u002Famstat.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F01621459.2017.1319839#.XaPLBeZKhhE)\n    \n    Stefan Wager, Susan Athey。\n\n1. **异质性治疗效应估计的局限性：实用算法设计指南**, *PMLR*, 2018年. [论文](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Falaa18a.html)\n    \n    Ahmed Alaa, Mihaela Schaar。\n\n1. **利用神经网络进行因果效应估计的迁移学习**, *arXiv*, 2018年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.07804)\n\n    Sören R. Künzel, Bradly C. Stadie, Nikita Vemuri, Varsha Ramakrishnan, Jasjeet S. Sekhon, Pieter Abbeel。\n\n1. **递归分割法用于异质性因果效应的估计**, *PNAS*, 2016年. [论文](https:\u002F\u002Fwww.pnas.org\u002Fcontent\u002F113\u002F27\u002F7353)\n    \n    Susan Athey, Guido Imbens。\n\n1. **用于估计异质性因果效应的机器学习方法**, *ArXiv*, 2015年. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1504.01132v1)\n\n    Susan Athey, Guido W. Imbens。\n\n### [静态数据](#content) \n\n1. **VCNet与函数型目标正则化：用于学习连续处理的因果效应**, *ICLR*, 2021年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.07861)  [代码](https:\u002F\u002Fgithub.com\u002Flushleaf\u002Fvarying-coefficient-net-with-functional-tr)\n\n    Lizhen Nie, Mao Ye, Qiang Liu, Dan Nicolae。\n\n1. **用于估计个体剂量-反应曲线的反事实表示学习**, *AAAI*, 2020年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00981) [代码](https:\u002F\u002Fgithub.com\u002Fd909b\u002Fdrnet)\n\n    Patrick Schwab, Lorenz Linhardt, Stefan Bauer, Joachim M. Buhmann, Walter Karlen。\n\n1. **利用生成对抗网络估计连续值干预的效果**, *NeurIPS*, 2020年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.12326) [代码](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FSCIGAN)\n\n    Ioana Bica, James Jordon, Mihaela van der Schaar。\n\n1. **从网络观测数据中学习个体因果效应**, *WSDM*, 2020年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.03485) [代码](https:\u002F\u002Fgithub.com\u002Frguo12\u002Fnetwork-deconfounder-wsdm20)\n\n    Ruocheng Guo, Jundong Li, Huan Liu。\n\n1. **用于估计个体化治疗效果的重叠表示学习**, *AISTATS*, 2020年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.04754)\n\n    Yao Zhang, Alexis Bellot, Mihaela van der Schaar。\n\n1. **为治疗效果估计而改进的神经网络**, *arXiv*, 2019年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.02120) [代码](http:\u002F\u002Fgithub.com\u002Fclaudiashi57\u002Fdragonnet)\n    \n    Claudia Shi, David M. Blei, Victor Veitch。\n\n1. **高维数据下的项目评估与因果推断**, *arXiv*, 2018年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1311.2645)\n    \n    Alexandre Belloni, Victor Chernozhukov, Ivan Fernández-Val, Christian Hansen。    \n\n1. **GANITE：利用生成对抗网络估计个体化治疗效果**, *ICLR*, 2018年。[论文](https:\u002F\u002Fopenreview.net\u002Fpdf?id=ByKWUeWA-) [代码](https:\u002F\u002Fgithub.com\u002Fjsyoon0823\u002FGANITE)\n    \n    Jinsung Yoon, James Jordon, Mihaela van der Schaar。\n\n1. **通过对抗学习在潜在混杂因素模型中估计个体治疗效果**, *arXiv*, 2018年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1811.08943)\n    \n    Changhee Lee, Nicholas Mastronarde, Mihaela van der Schaar。\n\n1. **Deep IV：一种灵活的反事实预测方法**, *PMLR*, 2017年。[论文](http:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Fhartford17a.html)\n    \n    Uri Shalit, Fredrik D. Johansson, David Sontag。\n\n1. **基于深度潜在变量模型的因果效应推断**, *arXiv*, 2017年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.08821) [代码](https:\u002F\u002Fgithub.com\u002FAMLab-Amsterdam\u002FCEVAE)\n    \n    Christos Louizos, Uri Shalit, Joris Mooij, David Sontag, Richard Zemel, Max Welling。\n\n1. **估计个体治疗效果：泛化界与算法**, *PMLR*, 2017年。[论文](http:\u002F\u002Fproceedings.mlr.press\u002Fv70\u002Fshalit17a.html) [代码](https:\u002F\u002Fgithub.com\u002Fclinicalml\u002Fcfrnet)\n    \n    Uri Shalit, Fredrik D. Johansson, David Sontag。\n\n### [时间序列数据](#content) \n\n1. **时间序列去混杂器：在存在隐藏混杂因素时估计随时间变化的治疗效果**, *ICML*, 2020年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.00450) [代码](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FTime-Series-Deconfounder)\n\n    Ioana Bica, Ahmed M. Alaa, Mihaela van der Schaar。\n\n1. **通过对抗平衡表示估计随时间变化的反事实治疗结果**, *ICLR*, 2020年。[论文](https:\u002F\u002Fopenreview.net\u002Fpdf?id=BJg866NFvB) [代码](https:\u002F\u002Fgithub.com\u002Fioanabica\u002FCounterfactual-Recurrent-Network)\n\n    Ioana Bica, Ahmed M. Alaa, James Jordon, Mihaela van der Schaar。\n\n1. **用于计量经济学中合成控制应用的反事实生成学习**, *arXiv*, 2019年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.07178)\n    \n    Chirag Modi, Uros Seljak。\n\n1. **鲁棒合成控制**, *JMLR*, 2019年。[论文](http:\u002F\u002Fwww.jmlr.org\u002Fpapers\u002Fvolume19\u002F17-777.pdf)\n    \n    Muhammad Amjad, Devavrat Shah, Dennis Shen。\n\n1. **ArCo：一种针对高维面板时间序列数据的人工反事实方法**, *计量经济学杂志*, 2018年。[论文](https:\u002F\u002Fpapers.ssrn.com\u002Fsol3\u002Fpapers.cfm?abstract_id=2823687)\n    \n    Carlos Carvalho, Ricardo Masini, Marcelo C. Medeiros。\n\n1. **利用递归边际结构网络预测随时间变化的治疗反应**, *NIPS*, 2018年。[论文](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7977-forecasting-treatment-responses-over-time-using-recurrent-marginal-structural-networks) [代码](https:\u002F\u002Fgithub.com\u002Fsjblim\u002Frmsn_nips_2018)\n    \n    Sonali Parbhoo, Stefan Bauer, Patrick Schwab。\n\n## [表示学习](#content)   \n\n1. **用于可处理反事实推断的深度结构因果模型**, *NeurIPS*, 2020年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.06485) [代码](https:\u002F\u002Fgithub.com\u002Fbiomedia-mira\u002Fdeepscm)\n\n    Nick Pawlowski, Daniel C. Castro, Ben Glocker。\n\n1. **NCoRE：用于多种治疗组合的神经反事实表示学习**, *arXiv*, 2021年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.11175)\n    \n    Sonali Parbhoo, Stefan Bauer, Patrick Schwab。\n\n1. **完美匹配：一种利用神经网络学习反事实推断表示的简单方法**, *arXiv*, 2019年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.00656) [代码](https:\u002F\u002Fgithub.com\u002Fd909b\u002Fperfect_match)\n    \n    Patrick Schwab, Lorenz Linhardt, Walter Karlen。\n\n1. **从观测数据中估计治疗效果的表示学习**, *NeurIPS*, 2019年。[论文](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7529-representation-learning-for-treatment-effect-estimation-from-observational-data.pdf) \n    \n    Liuyi Yao等。\n\n1. **用于因果迁移学习的不变模型**, *JMLR*, 2018年。[论文](http:\u002F\u002Fjmlr.org\u002Fpapers\u002Fv19\u002F16-432.html) \n    \n    Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner, Jonas Peters。\n\n1. **用于反事实推断的表示学习**, *arXiv*, 2018年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1605.03661) [代码](https:\u002F\u002Fgithub.com\u002Fclinicalml\u002Fcfrnet)\n    \n    Fredrik D. Johansson, Uri Shalit, David Sontag。\n\n## [半参数\u002F双重稳健推断](#content)  \n\n1. **平均处理效应的稀疏性双重稳健推断**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.00744)\n    \n    杰莱娜·布拉迪奇、斯特凡·韦格尔、尹楚·朱。\n\n1. **用于估计与推断的深度神经网络**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.09953)\n    \n    马克斯·H·法雷尔、滕远·梁、桑乔格·米斯拉。\n\n1. **基于倾向得分丢弃的深度反事实网络**, *arXiv*, 2017. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.05966)\n    \n    艾哈迈德·M·阿拉、迈克尔·魏茨、米哈埃拉·范德沙尔。\n\n1. **用于处理效应和因果参数的双重\u002F去偏机器学习**, *arXiv*, 2017. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1608.00060)\n    \n    维克托·切尔诺朱科夫、丹尼斯·切特维里科夫、梅尔特·德米尔尔、埃丝特·杜弗洛、克里斯蒂安·汉森、惠特尼·纽伊、詹姆斯·罗宾斯。\n\n1. **双重稳健的政策评估与优化**, *统计科学*, 2014. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1503.02834)\n    \n    米罗斯拉夫·杜迪克、杜米特鲁·埃尔汉、约翰·兰福德、李宏利。\n\n## [政策学习\u002F因果发现](#content)  \n\n1. **在未观测混杂下的可微分因果发现**, *arXiv*, 2021. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.06978)\n    \n    罗希特·巴塔查亚、图沙尔·纳加拉詹、丹尼尔·马林斯基、伊利亚·什皮策。\n\n1. **基于注意力机制的卷积神经网络进行因果发现**, *机器学习与知识提取*, 2019. [论文](https:\u002F\u002Fwww.mdpi.com\u002F2504-4990\u002F1\u002F1\u002F19) [代码](https:\u002F\u002Fgithub.com\u002FM-Nauta\u002FTCDF)\n    \n    梅克·瑙塔、多伊娜·布库尔、克里斯汀·赛费特。\n\n1. **用于学习解耦因果机制的元迁移目标**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.10912)\n    \n    约书亚·本吉奥、特里斯坦·德勒、纳西姆·拉哈曼、罗丝玛丽·凯、塞巴斯蒂安·拉沙佩尔、奥列克萨·比拉纽克、阿尼鲁德·戈亚尔、克里斯托弗·帕尔。\n\n1. **通过强化学习进行因果发现**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.04477)\n    \n    朱盛宇、陈志唐。\n\n1. **CausalGAN：利用对抗训练学习因果隐式生成模型**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1709.02023)\n    \n    穆拉特·科恰奥卢、克里斯托弗·斯奈德、亚历山德罗斯·G·迪马基斯、斯里拉姆·维什瓦纳特。\n\n1. **学习何时实施治疗的策略**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09751)\n    \n    聂欣坤、艾玛·布鲁恩斯维尔、斯特凡·韦格尔。\n\n1. **从未知干预中学习神经因果模型**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.01075) [代码](https:\u002F\u002Fgithub.com\u002Fnke001\u002Fcausal_learning_unknown_interventions)\n    \n    南·罗丝玛丽·凯、奥列克萨·比拉纽克、阿尼鲁德·戈亚尔、斯特凡·鲍尔、于戈·拉罗谢尔、克里斯·帕尔、约书亚·本吉奥。\n\n1. **使用领域对抗神经网络进行反事实政策优化**, *ICML*, 2018. [论文](http:\u002F\u002Fmedianetlab.ee.ucla.edu\u002Fpapers\u002Fcf_treat_v5)\n    \n    奥努尔·阿坦、威廉·R·扎梅、米哈埃拉·范德沙尔。\n\n1. **因果多臂老虎机：通过因果推断学习良好干预措施**, *NIPS*, 2016. [论文](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F6195-causal-bandits-learning-good-interventions-via-causal-inference)\n    \n    芬尼安·拉蒂莫尔、托尔·拉蒂莫尔、马克·D·里德。\n\n1. **反事实风险最小化：从记录的多臂老虎机反馈中学习**, *arXiv*, 2015. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1502.02362)\n    \n    阿迪思·斯瓦米纳坦、托尔斯滕·约阿希姆斯。\n\n## [因果推荐](#content) \n\n1. **去混杂推荐系统：一种基于因果推断的推荐方法**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.06581) [代码](https:\u002F\u002Fgithub.com\u002Fblei-lab\u002Fdeconfounder_tutorial)\n    \n    王一昕、梁大文、洛朗·夏尔林、大卫·M·布莱。\n\n1. **多重原因的优势**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.06826)\n    \n    王一昕、大卫·M·布莱。\n\n\u003Cdetails>\u003Csummary> 评论 \u003C\u002Fsummary> \n\n3. **评论：关于去混杂推荐系统的反思**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.08042)\n\n    亚历山大·达穆尔\n\n1. **关于存在未观测混杂时的多原因因果推断：反例、不可能性及替代方案**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.10286)\n\n    亚历山大·达穆尔\n\n1. **对“多重原因的优势”的评论**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05438)\n    \n    伊丽莎白·L·奥格本、伊利亚·什皮策、埃里克·J·切特根·切特根。\n\n1. **多重原因的优势：回应奥格本等人（2019）**, *arXiv*, 2019. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.07320)\n    \n    王一昕、大卫·M·布莱。\n\n\u003C\u002Fdetails>\n\n7. **将推荐视为治疗：去偏学习与评估**, *PMLR*, 2016. [论文](http:\u002F\u002Fproceedings.mlr.press\u002Fv48\u002Fschnabel16.html)\n    \n    托比亚斯·施纳贝尔、阿迪思·斯瓦米纳坦、阿舒迪普·辛格、纳文·钱达克、托尔斯滕·约阿希姆斯。\n\n1. **具有非随机缺失数据的协同预测与排序**, *RecSys*, 2009. [论文](http:\u002F\u002Fwww.cs.toronto.edu\u002F~zemel\u002Fdocuments\u002Facmrec2009-MarlinZemel.pdf)\n    \n    本杰明·M·马林、理查德·S·泽梅尔。\n\n## [因果强化学习](#content) \n\n1. **反事实多智能体策略梯度**, *AAAI*, 2018. [论文](https:\u002F\u002Fwww.aaai.org\u002Focs\u002Findex.php\u002FAAAI\u002FAAAI18\u002Fpaper\u002FviewPaper\u002F17193)\n    \n    雅各布·N·福斯特、格雷戈里·法夸尔、特里安塔菲洛斯·阿福拉斯、南塔斯·纳尔德利、希蒙·怀特森。\n\n## [因果推断中的特征选择](#content)\n\n1. **用于双重稳健因果推断的超高维变量选择**, *生物计量学*, 2022. [论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.14190) [代码](https:\u002F\u002Fgithub.com\u002Fdingketang\u002Fultra-high-DRCI) [演示文稿](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1OlwNi9eMu_MQe3TyiHpHg2ULdfGD2x0S\u002Fview?usp=sharing)\n\n    唐丁科、孔德涵、潘文亮、王林波\n\n1. **基于结果自适应的套索：用于因果推断的变量选择**, *生物计量学* 2017. [论文](https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdf\u002F10.1111\u002Fbiom.12679?casa_token=_xFuHHhoWlAAAAAA:gKO0JyJC0g54pOfbOVlNew7t1M29UD_A46yJJUAGiLAuxO87p4lGmMneYklKfuWGiHCitIbvKtjfEMAN)  [视频](https:\u002F\u002Fcrossminds.ai\u002Fvideo\u002Fvariable-selection-for-causal-inference-outcome-adaptive-lasso-6070a5f9fa08279acdb2124a\u002F)\n\n    苏珊·M·肖特里德、阿什坎·埃尔特法耶\n\n## [应用](#content)\n\n### [社会科学](#content)\n\n1. **基于双重机器学习的无混杂性假设下的项目评估**, *计量经济学期刊*, 2022年。[论文](https:\u002F\u002Fdoi.org\u002F10.1093\u002Fectj\u002Futac015)\n    \n    迈克尔·C·克瑙斯。\n\n1. **通过公共土地处置进行国家建设？矩阵补全在反事实预测中的应用**, *arXiv*, 2021年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.08028) [代码](https:\u002F\u002Fgithub.com\u002Fjvpoulos\u002Fhomesteads)\n    \n    杰森·普洛斯。\n\n1. **基于RNN的反事实预测及其在宅地政策和公立教育中的应用**, *JRSS-C*, 2021年。[论文](http:\u002F\u002Fjasonvpoulos.com\u002Fpapers\u002F17117351.pdf) [代码](https:\u002F\u002Fgithub.com\u002Fjvpoulos\u002Frnns-causal)\n    \n    杰森·普洛斯、曾淑熙。\n\n1. **使用因果森林估计处理效应：一项应用**, *arXiv*, 2019年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.07409)\n    \n    苏珊·艾西、斯特凡·韦格尔。\n\n1. **面板数据情境下因果效应的集成方法**, *AER P&P*, 2019年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.10079)\n    \n    苏珊·艾西、莫森·巴亚蒂、圭多·W·伊姆本斯、钱南·邱。\n\n### [文本](#content)\n\n1. **面向神经机器翻译的反事实数据增强**, *ACL*, 2021年。[论文](https:\u002F\u002Fwww.aclweb.org\u002Fanthology\u002F2021.naacl-main.18\u002F) [代码](https:\u002F\u002Fgithub.com\u002Fxxxiaol\u002FGCI)\n    \n     刘奇、马特·库斯纳、菲尔·布伦索姆。\n\n1. **万物皆有因：在法律文本分析中利用因果推断**, *arXIv*, 2021年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.09420) [代码](https:\u002F\u002Fgithub.com\u002Fxxxiaol\u002FGCI)\n    \n     小刘、达音、燕松·冯、宇婷·吴、东艳·赵。\n\n1. **语言学属性的因果效应**, *arXIv*, 2021年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.12919)\n    \n     里德·普赖赞特、达拉斯·卡德、丹·朱拉夫斯基、维克托·维奇、达尼亚·斯里达尔。\n\n1. **草图与定制：一种反事实故事生成器**, *arXIv*, 2021年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.00929)\n    \n    郝昌英、庞亮、兰燕燕、王燕、郭家峰、程雪琪。\n\n1. **反事实生成器：一种用于命名实体识别的弱监督方法**, *EMNLP*, 2020年。[论文](https:\u002F\u002Fgithub.com\u002Fxijiz\u002Fcfgen\u002Fblob\u002Fmaster\u002Fdocs\u002Fcfgen.pdf) [代码](https:\u002F\u002Fgithub.com\u002Fxijiz\u002Fcfgen)\n    \n    曾祥吉、李云良、翟宇辰、张寅。\n\n1. **利用文本嵌入进行因果推断**, *arXIv*, 2019年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.12741) [代码](https:\u002F\u002Fgithub.com\u002Fblei-lab\u002Fcausal-text-embeddings)\n    \n    维克托·维奇、达尼亚·斯里达尔、大卫·M·布莱。\n\n1. **反事实故事推理与生成**, *arXIv*, 2019年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.04076)\n    \n    秦连辉、安托万·博塞吕特、阿里·霍尔茨曼、钱德拉·巴加瓦图拉、伊丽莎白·克拉克、叶津·崔。\n\n1. **如何利用文本进行因果推断**, *arXIv*, 2018年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1802.02163)\n\n    江美直树、克里斯蒂安·J·方格、贾斯汀·格里默、玛格丽特·E·罗伯茨、布兰登·M·斯图尔特。\n\n### [健康](#content)\n\n1. **具有多水平治疗的观察性研究中的目标学习：对严重精神疾病患者抗精神病药物治疗安全性的评估**, *arXIv*, 2022年。[论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.15367) [代码](https:\u002F\u002Fgithub.com\u002Fjvpoulos\u002Fmulti-tmle)\n    \n     杰森·普洛斯、马塞拉·霍维茨-莱侬、卡佳·泽列文斯基、托马斯·海斯肯斯、普贾·泰亚吉、贾久·颜、乔迪·迪亚斯、图多尔·克里斯蒂亚-普拉顿、莎伦-莉丝·诺曼德。\n\n## [资源](#content)\n\n### [研讨会](#content)\n\n1. **NeurIPS 2021研讨会** [链接](https:\u002F\u002Fwhy21.causalai.net\u002F)\n\n1. **UAI 2021研讨会** [链接](https:\u002F\u002Fsites.google.com\u002Fuw.edu\u002Fcausaluai2021\u002Fhome?authuser=0)\n\n1. **KDD 2021研讨会** [链接](https:\u002F\u002Fbcirwis2021.github.io\u002Fcfp.html)\n\n1. **ICML 2021研讨会** [链接](https:\u002F\u002Fsites.google.com\u002Fview\u002Fnaci2021\u002Fhome)\n\n1. **EMNLP 2021研讨会** [链接](https:\u002F\u002Fcausaltext.github.io\u002F2021\u002F)\n\n1. **NeurIPS 2020研讨会** [链接](https:\u002F\u002Fwww.cmu.edu\u002Fdietrich\u002Fcausality\u002Fneurips20ws\u002F)\n\n1. **NeurIPS 2019研讨会** [链接](http:\u002F\u002Ftripods.cis.cornell.edu\u002Fneurips19_causalml\u002F)\n\n1. **NIPS 2018研讨会** [链接](https:\u002F\u002Fsites.google.com\u002Fview\u002Fnips2018causallearning\u002Fhome)\n\n1. **NIPS 2017研讨会** [链接](https:\u002F\u002Fsites.google.com\u002Fview\u002Fcausalnips2017)\n\n1. **NIPS 2016研讨会** [链接](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fwhatif2016nips\u002F)\n\n1. **NIPS 2013研讨会** [链接](http:\u002F\u002Fclopinet.com\u002Fisabelle\u002FProjects\u002FNIPS2013\u002F)\n\n### [会议论文集](#content)\n\n1. **PMLR，第6卷：因果关系：目标与评估，2008年12月12日，加拿大惠斯勒** [链接](http:\u002F\u002Fproceedings.mlr.press\u002Fv6\u002F)\n\n### [代码库](#content)\n\n1. **因果推断360：一个用于从观察性数据中推断因果效应的Python包。** [链接](https:\u002F\u002Fgithub.com\u002FIBM\u002Fcausallib)\n\n1. **WhyNot：一个将因果推断和强化学习工具与一系列复杂模拟器连接起来的Python包** [链接](https:\u002F\u002Fgithub.com\u002Fzykls\u002Fwhynot)\n\n1. **EconML：一个用于基于机器学习的异质性处理效应估计的Python包** [链接](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FEconML)\n\n1. **提升建模与机器学习算法结合的因果推断** [链接](https:\u002F\u002Fgithub.com\u002Fuber\u002Fcausalml)\n\n### [基准数据集](#content)\n\n1. **IHDP、Jobs和News基准数据集** [链接](https:\u002F\u002Ffredjo.com\u002F)\n\n1. **双胞胎数据集** [链接](http:\u002F\u002Fwww.nber.org\u002Fdata\u002Flinked-birth-infant-death-data-vitalstatistics-data.htm)\n\n1. **因果关系工作台** [链接](http:\u002F\u002Fwww.causality.inf.ethz.ch\u002Frepository.php?page=data)\n\n### [课程](#content)\n\n1. **CS7792 - 反事实机器学习** [链接](http:\u002F\u002Fwww.cs.cornell.edu\u002Fcourses\u002Fcs7792\u002F2016fa\u002F)\n\n1. **因果推断导论** [链接](https:\u002F\u002Fwww.bradyneal.com\u002Fcausal-inference-course)\n\n1. **机器学习与因果推断：短期课程** [链接](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLxq_lXOUlvQAoWZEqhRqHNezS30lI49G-)\n\n1. **KDD 2020：讲座式教程：因果推断与机器学习的结合** [链接](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=DbW2e2q8Gjs)\n\n### [产业](#content)\n\n1. **因果关系与机器学习：微软研究院** [链接](https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fgroup\u002Fcausal-inference\u002F#!publications)\n\n### [团体](#content)\n\n1. **因果推断学会** [链接](https:\u002F\u002Fsci-info.org\u002F)\n\n1. **由米哈埃拉·范德沙尔教授领导的研究实验室** [链接](http:\u002F\u002Fwww.vanderschaar-lab.com\u002FNewWebsite\u002Fcausal_inference_and_treatment_effects.html)\n\n### [列表](#content)\n\n1. **利用数据学习因果关系的算法索引** [链接](https:\u002F\u002Fgithub.com\u002Frguo12\u002Fawesome-causality-algorithms)\n\n1. **可用于学习因果关系的数据集索引** [链接](https:\u002F\u002Fgithub.com\u002Frguo12\u002Fawesome-causality-data)\n\n1. **关于因果推断与语言的论文** [链接](https:\u002F\u002Fgithub.com\u002Fcausaltext\u002Fcausal-text-papers)\n\n### [书籍](#content)\n\n1. **因果机器学习** [链接](https:\u002F\u002Fwww.manning.com\u002Fbooks\u002Fcausal-machine-learning)","# causal-ml 快速上手指南\n\n**注意**：您提供的 README 内容实际上是一个**因果推断与机器学习（Causal ML）领域的论文与资源列表**，而非名为 `causal-ml` 的具体软件库的安装文档。该列表由社区维护，旨在收录相关前沿研究（如异质性处理效应、表示学习、策略学习等）。\n\n由于列表中包含了多个独立的开源项目（如 `TransTEE`, `SIN`, `TEDVAE`, `DRNet`, `CFRNet` 等），每个项目都有独立的环境要求和安装方式，因此**不存在统一的 `causal-ml` 安装包**。\n\n本指南将指导您如何基于此资源列表，快速搭建通用的因果推断开发环境，并演示如何使用列表中提到的经典算法库（以 Uber 开源的广泛使用的 `causalml` 库及列表中常见的 `CFRNet` 为例）进行快速上手。\n\n---\n\n## 1. 环境准备\n\n在开始之前，请确保您的系统满足以下基本要求。大多数因果推断深度学习模型依赖 PyTorch 或 TensorFlow。\n\n*   **操作系统**: Linux (推荐 Ubuntu 18.04+), macOS, 或 Windows (建议使用 WSL2)\n*   **Python 版本**: 3.7 - 3.9 (部分新模型可能需要 3.10+)\n*   **前置依赖**:\n    *   `pip` 或 `conda` 包管理器\n    *   GPU 驱动 (可选，但运行深度学习模型如 GANITE, CEVAE 时强烈推荐)\n\n**推荐国内加速方案**：\n使用清华源或阿里源加速 Python 包安装。\n\n```bash\n# 配置 pip 使用清华源 (临时生效)\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple \u003Cpackage_name>\n```\n\n## 2. 安装步骤\n\n由于 README 是论文列表，您需要根据想复现的具体论文安装对应的库。以下是两种最常见的安装场景：\n\n### 场景 A：安装通用因果推断库 (推荐新手)\n如果您希望快速体验因果推断流程（包含元学习器、森林法等，对应列表中 Susan Athey 等人的工作），推荐安装 Uber 开源的 `causalml` 库。\n\n```bash\n# 使用 pip 安装 (推荐国内镜像)\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple causalml\n\n# 或者使用 conda\nconda install -c conda-forge causalml\n```\n\n### 场景 B：安装特定深度学习模型 (复现列表中的论文)\n列表中许多论文（如 *CEVAE*, *GANITE*, *CFRNet*）提供了独立的 GitHub 代码库。以列表中提到的 **CFRNet** (Estimating individual treatment effect) 为例：\n\n```bash\n# 1. 克隆代码库\ngit clone https:\u002F\u002Fgithub.com\u002Fclinicalml\u002Fcfrnet.git\ncd cfrnet\n\n# 2. 创建虚拟环境并安装依赖\npython -m venv venv\nsource venv\u002Fbin\u002Factivate  # Windows 用户请使用: venv\\Scripts\\activate\n\n# 3. 安装依赖 (通常包含 tensorflow 或 torch)\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple -r requirements.txt\n```\n\n> **提示**：对于列表中的其他模型（如 `TransTEE`, `SIN`），请访问其 README 中提供的 `[code]` 链接，通常遵循类似的 `git clone` + `pip install -r requirements.txt` 流程。\n\n## 3. 基本使用\n\n以下展示如何使用通用的 `causalml` 库进行最简单的**异质性处理效应 (HTE)** 估计。这对应了列表中 \"Individual treatment effects\" 章节的核心内容。\n\n### 示例：使用 S-Learner 估计处理效应\n\n此示例模拟数据并使用机器学习模型估计不同特征下的处理效应。\n\n```python\nimport numpy as np\nimport pandas as pd\nfrom causalml.inference.meta import LRSRegressor, XGBRegressor\nfrom causalml.dataset import synthetic_data\n\n# 1. 生成合成数据\n# n_samples: 样本数, p: 特征数, sigma_y: 噪声标准差\ny, X, treatment, _, _, _ = synthetic_data(\n    mode=1, \n    n_samples=1000, \n    p=5, \n    sigma_y=0.5\n)\n\n# 转换为 DataFrame 方便查看\ndata = pd.DataFrame(X, columns=[f'feature_{i}' for i in range(X.shape[1])])\ndata['treatment'] = treatment\ndata['outcome'] = y\n\n# 2. 初始化模型 (这里使用基于梯度提升树的 S-Learner)\n# 也可以使用 LRSRegressor (线性回归), RandomForestRegressor 等\nmodel = XGBRegressor()\n\n# 3. 拟合模型\n# outcome: 目标变量, treatment: 处理变量, features: 协变量\nmodel.fit(\n    X=data[[f'feature_{i}' for i in range(5)]].values,\n    treatment=data['treatment'].values,\n    y=data['outcome'].values\n)\n\n# 4. 预测个体处理效应 (ITE)\nite = model.predict(\n    X=data[[f'feature_{i}' for i in range(5)]].values,\n    treatment=data['treatment'].values\n)\n\n# 5. 输出结果概览\nprint(\"前 5 个样本的个体处理效应 (ITE):\")\nprint(ite[:5])\n\nprint(f\"\\n平均处理效应 (ATE) 估计值: {np.mean(ite):.4f}\")\n```\n\n### 进阶：复现列表中的深度学习方法\n若您正在复现列表中的 **CEVAE** (Causal Effect Inference with Deep Latent-Variable Models)，通常用法如下（假设已安装对应 repo）：\n\n```python\n# 伪代码示例，具体取决于各仓库的实现\nfrom cevae import CEVAE \n\n# 初始化模型\nmodel = CEVAE(input_dim=X.shape[1])\n\n# 训练\nmodel.fit(x=X, t=treatment, y=y, epochs=100)\n\n# 推断反事实结果\ny_pred_0, y_pred_1 = model.predict_counterfactuals(X)\nite = y_pred_1 - y_pred_0\n```\n\n---\n\n**下一步建议**：\n浏览您提供的 README 原文，根据您感兴趣的具体研究方向（如 \"Temporal data\" 或 \"Causal recommendation\"），点击对应的 `[code]` 链接进入具体项目的 GitHub 页面，查阅其特定的 `README.md` 以获取该模型独有的参数配置和高级用法。","某大型电商平台的营销团队正试图优化优惠券发放策略，希望精准识别哪些用户真正因收到优惠券而产生了购买行为（即提升量建模）。\n\n### 没有 causal-ml 时\n- **混淆相关性因果性**：数据科学家仅依赖传统机器学习模型，错误地将“高消费意愿用户”等同于“受优惠券影响用户”，导致资源浪费在本来就会购买的人群上。\n- **缺乏异质性分析能力**：面对静态数据和复杂的时间序列行为，团队难以估算不同用户群体的个性化处理效应（Heterogeneous Treatment Effects），只能采取“一刀切”的粗放式发放。\n- **技术选型迷茫**：面对因果推断与深度学习结合的前沿论文（如 Transformer 在因果估计中的应用），研发人员难以快速筛选出适合业务场景的算法和开源代码库，试错成本极高。\n\n### 使用 causal-ml 后\n- **精准因果识别**：团队利用 causal-ml 整理的异质性处理效应估计算法，成功剥离了自然购买倾向，精准锁定了那些“不发券不买、发券才买”的敏感用户群。\n- **适配复杂场景**：参考库中关于时序数据和结构化处理的最新论文（如 TransTEE），团队构建了能捕捉用户动态行为变化的深度因果模型，显著提升了策略的细粒度。\n- **高效落地研发**：通过 causal-ml 提供的分类资源索引，算法工程师直接定位到经过验证的代码库和基准数据集，将原本需要数月的文献调研和复现周期缩短至两周。\n\ncausal-ml 通过系统化整合前沿因果机器学习资源，帮助团队从“盲目撒网”转型为“精准干预”，大幅提升了营销预算的投资回报率。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjvpoulos_causal-ml_36b92f82.png","jvpoulos","Jason Poulos","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fjvpoulos_f7ec3130.jpg","Working on machine learning and causal inference in health and social sciences",null,"Boston, MA","poulos@berkeley.edu","http:\u002F\u002Fpoulos.ai","https:\u002F\u002Fgithub.com\u002Fjvpoulos",749,134,"2026-04-07T03:42:31",1,"","未说明",{"notes":88,"python":86,"dependencies":89},"提供的 README 内容实际上是一个关于“因果机器学习（Causal ML）”领域的论文和资源列表（类似 Awesome List），而非名为 'causal-ml' 的具体软件工具的安装文档。因此，文中未包含任何关于操作系统、GPU、内存、Python 版本或依赖库的技术运行环境需求。该文档主要列举了相关学术论文、代码库链接（指向各个独立项目的 GitHub）以及学习资源。",[],[14],[92,93,94,95,96,97,98,99,100,101,102,103,104,105],"causal-inference","causal-models","counterfactual","treatment-effects","representation-learning","causal-discovery","paper-list","randomized-controlled-trials","heterogeneous-treatment-effects","counterfactual-learning","estimating-treatment-effects","causal-learning","deep-learning","machine-learning","2026-03-27T02:49:30.150509","2026-04-11T16:54:14.488351",[],[]]