令人惊叹的自监督图神经网络

本仓库收录了关于图神经网络（GNN）上的自监督学习的相关论文，并按发表年份进行了分类。

我们会尽量保持这份列表的更新。如果您发现任何错误或遗漏的论文，请随时提出Issue或发送Pull Request。

注：:fire: 表示该论文被广泛引用（例如，超过80次引用）。代码可在get_hot.py中找到。

2024年

1. [ICASSP 2024] 用于社区检测的对比式深度非负矩阵分解 [论文] [代码]

Year 2023

1. [ICLR 2023] Empowering Graph Representation Learning with Test-Time Graph Transformation [paper] [code]
2. [ICLR 2023] Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization [paper] [code]
3. [AAAI 2023] Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning [paper] [code]
4. [arXiv 2023] Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection [paper]
5. [ICASSP 2023] Contrastive Learning at the Relation and Event Level for Rumor Detection [paper]
6. [arXiv 2023] AmGCL: Feature Imputation of Attribute Missing Graph via Self-supervised Contrastive Learning [paper]
7. [arXiv 2023] SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning [paper]
8. [arXiv 2023] CSGCL: Community-Strength-Enhanced Graph Contrastive Learning [paper]
9. [TKDE 2023] MINING: Multi-Granularity Network Alignment Based on Contrastive Learning [paper]
10. [ICASSP 2023] Select The Best: Enhancing Graph Representation with Adaptive Negative Sample Selection [paper]
11. [ICASSP 2023] Graph Contrastive Learning with Learnable Graph Augmentation [paper]
12. [arXiv 2023] FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction [paper]
13. [INS 2023] A fairness-aware graph contrastive learning recommender framework for social tagging systems [paper]
14. [arXiv 2023] Improving Knowledge Graph Entity Alignment with Graph Augmentation [paper]
15. [WWW 2023] Graph Self-supervised Learning with Augmentation-aware Contrastive Learning [paper]
16. [arXiv 2023] A Systematic Survey of Chemical Pre-trained Models [paper]
17. [WWW 2023] Self-Supervised Teaching and Learning of Representations on Graphs [paper]
18. [TKDE 2023] Progressive Hard Negative Masking: From Global Uniformity to Local Tolerance [paper]
19. [KBS 2023] ST-A-PGCL: Spatiotemporal adaptive periodical graph contrastive learning for traffic prediction under real scenarios [paper]
20. [WWW 2023] SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking [paper]
21. [INS 2023] Self-supervised Contrastive Learning on Heterogeneous Graphs with Mutual Constraints of Structure and Feature [paper]
22. [Scientific Reports 2023] A multi-view contrastive learning for heterogeneous network embedding [paper]
23. [WWW 2023] Automated Spatio-Temporal Graph Contrastive Learning [paper]
24. [arXiv 2023] Capturing Fine-grained Semantics in Contrastive Graph Representation Learning [paper]
25. [arXiv 2023] Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One [paper]
26. [arXiv 2023] ID-MixGCL: Identity Mixup for Graph Contrastive Learning [paper]
27. [Bioinformatics 2023] Molecular Property Prediction by Contrastive Learning with Attention-Guided Positive Sample Selection [paper]
28. [AISTAT 2023] Learning Robust Graph Neural Networks with Limited Supervision [paper]
29. [TNNLS 2023] Demystifying and Mitigating Bias for Node Representation Learning [paper]
30. [BICTA 2023] Graph Contrastive Learning with Intrinsic Augmentations [paper]
31. [arXiv 2023] GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner [paper]
32. [arXiv 2023] Adversarial Hard Negative Generation for Complementary Graph Contrastive Learning [paper]
33. [INS 2023] INS-GNN: Improving Graph Imbalance Learning with Self-Supervision [paper]
34. [TNNLS 2023] Dual Contrastive Learning Network for Graph Clustering [paper]
35. [arXiv 2023] RARE: Robust Masked Graph Autoencoder [paper]
36. [TKDE 2023] Maximizing Mutual Information Across Feature and Topology Views for Representing Graphs [paper]
37. [arXiv 2023] When to Pre-Train Graph Neural Networks? An Answer from Data Generation Perspective! [paper]
38. [KBS 2023] Class-homophilic-based data augmentation for improving graph neural networks [paper]
39. [arXiv 2023] Structural Imbalance Aware Graph Augmentation Learning [paper]
40. [arXiv 2023] Hybrid Augmented Automated Graph Contrastive Learning [paper]
41. [arXiv 2023] Decoupling Graph Neural Network with Contrastive Learning for Fraud Detection [paper]
42. [arXiv 2023] Data-Centric Learning from Unlabeled Graphs with Diffusion Model [paper]
43. [TPAMI 2023] Unsupervised Learning of Graph Matching With Mixture of Modes Via Discrepancy Minimization [paper]
44. [arXiv 2023] NESS: Learning Node Embeddings from Static SubGraphs [paper]
45. [Sensors 2023] A Robust Automated Analog Circuits Classification Involving a Graph Neural Network and a Novel Data Augmentation Strategy [paper]
46. [arXiv 2023] Contrastive knowledge integrated graph neural networks for Chinese medical text classification [paper]
47. [arXiv 2023] CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network [paper]
48. [arXiv 2023] Contrastive Learning under Heterophily [paper]
49. [arXiv 2023] Structure-Aware Group Discrimination with Adaptive-View Graph Encoder: A Fast Graph Contrastive Learning Framework [paper]
50. [TNNLS 2023] Self-supervised Learning IoT Device Features with Graph Contrastive Neural Network for Device Classification in Social Internet of Things [paper]
51. [TKDE 2023] Feature-Level Deeper Self-Attention Network With Contrastive Learning for Sequential Recommendation [paper]
52. [AAAI 2023] Recommend What to Cache: a Simple Self-supervised Graph-based Recommendation Framework for Edge Caching Network [paper]
53. [arXiv 2023] Self-Supervised Interest Transfer Network via Prototypical Contrastive Learning for Recommendation [paper]
54. [arXiv 2023] SGL-PT: A Strong Graph Learner with Graph Prompt Tuning [paper]
55. [CIS 2023] SimGRL: a simple self-supervised graph representation learning framework via triplets [paper]
56. [WSDM 2023] Self-Supervised Group Graph Collaborative Filtering for Group Recommendation [paper]
57. [WSDM 2023] S2GAE: Self-Supervised Graph Autoencoders are Generalizable Learners with Graph Masking [paper]
58. [WSDM 2023] Heterogeneous Graph Contrastive Learning for Recommendation [paper]
59. [Nature Communications Chemistry] Hierarchical Molecular Graph Self-Supervised Learning for property prediction [paper]
60. [arXiv 2023] Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning [paper]
61. [arXiv 2023] Heterogeneous Social Event Detection via Hyperbolic Graph Representations [paper]
62. [arXiv 2023] LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation [paper]
63. [arXiv 2023] GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks [paper]
64. [Pattern Recognition] Dual-Channel Graph Contrastive Learning for Self-Supervised Graph-Level Representation Learning [paper]
65. [NCA 2023] Self-supervised contrastive learning for heterogeneous graph based on multi-pretext tasks [paper]
66. [arXiv 2023] STERLING: Synergistic Representation Learning on Bipartite Graphs [paper]
67. [ICLR 2023] Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization [paper]
68. [WBD 2023] Mixed-Order Heterogeneous Graph Pre-training for Cold-Start Recommendation [paper]
69. [arXiv 2023] Explainable Action Prediction through Self-Supervision on Scene Graphs [paper]
70. [arXiv 2023] Spectral Augmentations for Graph Contrastive Learning [paper]
71. [RS 2023] Representing Spatial Data with Graph Contrastive Learning [paper]
72. [ACLF 2023] KE-GCL: Knowledge Enhanced Graph Contrastive Learning for Commonsense Question Answering [paper]
73. [TNNLS 2023] GRLC: Graph Representation Learning With Constraints [paper]
74. [ESA 2023] Contrastive graph clustering with adaptive filter [paper]
75. [arXiv 2023] Biomedical Interaction Prediction with Adaptive Line Graph Contrastive Learning [paper]
76. [arXiv 2023] Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning [paper]
77. [arXiv 2023] Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking [paper]
78. [ACM Trans. Web 2023] Contrastive Graph Similarity Networks [paper]
79. [ICBD 2023] Predictive Masking for Semi-Supervised Graph Contrastive Learning [paper]
80. [TNNLS 2023] Graph Representation Learning With Adaptive Metric [paper]
81. [RAL 2023] Self-Supervised Local Topology Representation for Random Cluster Matching [paper]
82. [KBS 2023] CrysGNN: Distilling pre-trained knowledge to enhance property prediction for crystalline materials [paper]
83. [Entropy 2023] A Semantic-Enhancement-Based Social Network User-Alignment Algorithm [paper]
84. [KBS 2023] Cross-view temporal graph contrastive learning for session-based recommendation [paper]
85. [PR 2023] Robust Image Clustering via Context-aware Contrastive Graph Learning [paper]
86. [ICMLCS 2023] AP-GCL: Adversarial Perturbation on Graph Contrastive Learning [paper]
87. [arXiv 2023] Signed Directed Graph Contrastive Learning with Laplacian Augmentation [paper]
88. [OJCS 2023] SC-FGCL: Self-adaptive Cluster-based Federal Graph Contrastive Learning [paper]
89. [BIB 2023] CasANGCL: pre-training and fine-tuning model based on cascaded attention network and graph contrastive learning for molecular property prediction [paper]
90. [AAAI 2023] Spectral Feature Augmentation for Graph Contrastive Learning and Beyond [paper]
91. [Entropy 2023] Self-Supervised Node Classification with Strategy and Actively Selected Labeled Set [paper]

Year 2022

1. [NeurIPS 2022] Generalized Laplacian Eigenmaps [paper]
2. [KDD 2022] COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning [paper]
3. [ITBE 2022] Contrastive Multi-view Composite Graph Convolutional Networks Based on Contribution Learning for Autism Spectrum Disorder Classification [paper]
4. [IEEE Access 2022] ROME: A Graph Contrastive Multi-view Framework from Hyperbolic Angular Space for MOOCs Recommendation [paper]
5. [arXiv 2022] Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Weighted Negative Samples [paper]
6. [arXiv 2022] MolCPT: Molecule Continuous Prompt Tuning to Generalize Molecular Representation Learning [paper]
7. [arXiv 2022] Toward Improved Generalization: Meta Transfer of Self-supervised Knowledge on Graphs [paper]
8. [arXiv 2022] Coarse-to-Fine Contrastive Learning on Graphs [paper]
9. [arXiv 2022] MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning [paper]
10. [arXiv 2022] Mul-GAD: a semi-supervised graph anomaly detection framework via aggregating multi-view information [paper]
11. [arXiv 2022] Localized Contrastive Learning on Graphs [paper]
12. [arXiv 2022] Alleviating neighbor bias: augmenting graph self-supervise learning with structural equivalent positive samples [paper]
13. [arXiv 2022] Self-supervised Graph Representation Learning for Black Market Account Detection [paper]
14. [arXiv 2022] Contrastive Deep Graph Clustering with Learnable Augmentation [paper]
15. [arXiv 2022] Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View [paper]
16. [arXiv 2022] Self Supervised Clustering of Traffic Scenes using Graph Representations [paper]
17. [arXiv 2022] Graph Contrastive Learning for Materials [paper]
18. [arXiv 2022] Link Prediction with Non-Contrastive Learning [paper]
19. [IJMIR 2022] TCKGE: Transformers with contrastive learning for knowledge graph embedding [paper]
20. [arXiv 2022] Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating [paper]
21. [Neural Networks 2022] Unsupervised graph-level representation learning with hierarchical contrasts [paper]
22. [arXiv 2022] Relation-dependent Contrastive Learning with Cluster Sampling for Inductive Relation Prediction [paper]
23. [arXiv 2022] Relational Symmetry based Knowledge Graph Contrastive Learning [paper]
24. [arXiv 2022] Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective [paper]
25. [arXiv 2022] Can Single-Pass Contrastive Learning Work for Both Homophilic and Heterophilic Graph? [paper]
26. [SIGSPATIAL 2022] When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting? [paper]
27. [Scientific Reports 2022] Deep graph level anomaly detection with contrastive learning [paper]
28. [TII 2022] Semi-supervised machine fault diagnosis fusing unsupervised graph contrastive learning [paper]
29. [KBS 2022] SMGCL: Semi-supervised Multi-view Graph Contrastive Learning [paper]
30. [arXiv 2022] Unsupervised Graph Contrastive Learning with Data Augmentation for Malware Classification [paper]
31. [IJCRS 2022] Multi-scale Subgraph Contrastive Learning for Link Prediction [paper]
32. [arXiv 2022] Flaky Performances when Pretraining on Relational Databases [paper]
33. [arXiv 2022] GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection [paper]
34. [ATKDD 2022] Ada-MIP: Adaptive Self-supervised Graph Representation Learning via Mutual Information and Proximity Optimization [paper]
35. [arXiv 2022] Graph Contrastive Learning with Implicit Augmentations [paper]
36. [Information Sciences 2022] Contrastive Graph Neural Network-based Camouflaged Fraud Detector [paper]
37. [arXiv 2022] DyG2Vec: Representation Learning for Dynamic Graphs with Self-Supervision [paper]
38. [arXiv 2022] Federated Graph Representation Learning using Self-Supervision [paper]
39. [arXiv 2022] Benchmark of Self-supervised Graph Neural Networks [paper]
40. [arXiv 2022] Line Graph Contrastive Learning for Link Prediction [paper]
41. [TDSC 2022] FewM-HGCL: Few-Shot Malware Variants Detection Via Heterogeneous Graph Contrastive Learning [paper]
42. [arXiv 2022] Self-supervised Graph-based Point-of-interest Recommendation [paper]
43. [IJMLC 2022] Hybrid sampling-based contrastive learning for imbalanced node classification [paper]
44. [CIKM 2022] Temporality-and Frequency-aware Graph Contrastive Learning for Temporal Network [paper]
45. [CIKM 2022] Towards Self-supervised Learning on Graphs with Heterophily [paper]
46. [ISWC 2022] HCL: Improving Graph Representation with Hierarchical Contrastive Learning [paper]
47. [CIKM 2022] Cognize Yourself: Graph Pre-Training via Core Graph Cognizing and Differentiating [paper]
48. [CIKM 2022] AdaGCL: Adaptive Subgraph Contrastive Learning to Generalize Large-scale Graph Training [paper]
49. [CIKM 2022] Look Twice as Much as You Say: Scene Graph Contrastive Learning for Self-Supervised Image Caption Generation [paper]
50. [CIKM 2022] Malicious Repositories Detection with Adversarial Heterogeneous Graph Contrastive Learning [paper]
51. [ICEBE 2022] Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering [paper]
52. [arXiv 2022] Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering [paper]
53. [NeurIPS 2022] Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative [paper] [code]
54. [ICCL 2022] Modeling Intra-and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis [paper]
55. [TKDE 2022] Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks [paper]
56. [MM 2022] Simple Self-supervised Multiplex Graph Representation Learning [paper]
57. [TMM 2022] Self-consistent Contrastive Attributed Graph Clustering with Pseudo-label Prompt [paper]
58. [NeurIPS 2022] Uncovering the Structural Fairness in Graph Contrastive Learning [paper]
59. [NeurIPS 2022] Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum [paper]
60. [arXiv 2022] Heterogeneous Graph Contrastive Multi-view Learning [paper]
61. [arXiv 2022] Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation [paper]
62. [arXiv 2022] Prompt Tuning for Graph Neural Networks [paper]
63. [arXiv 2022] Improving Molecular Pretraining with Complementary Featurizations [paper]
64. [arXiv 2022] Graph Soft-Contrastive Learning via Neighborhood Ranking [paper]
65. [EDBT 2022] Spatial Structure-Aware Road Network Embedding via Graph Contrastive Learning [paper]
66. [arXiv 2022] Adversarial Cross-View Disentangled Graph Contrastive Learning [paper]
67. [Neurocomputing 2022] Motifs-based Recommender System via Hypergraph Convolution and Contrastive Learning [paper]
68. [TNNLS 2022] Graph Representation Learning for Large-Scale Neuronal Morphological Analysis [paper]
69. [ECML-PKDD 2022] Self-supervised Graph Learning with Segmented Graph Channels [paper]
70. [ECML-PKDD 2022] Graph Contrastive Learning with Adaptive Augmentation for Recommendation [paper]
71. [CIKM 2022] Contrastive Knowledge Graph Error Detection [paper]
72. [TKDE 2022] Disentangled Graph Contrastive Learning With Independence Promotion [paper]
73. [ECML-PKDD 2022] Supervised Graph Contrastive Learning for Few-shot Node Classification [paper]
74. [Information Sciences 2022] Graph Prototypical Contrastive Learning [paper]
75. [ICAAN 2022] Knowledge-Aware Self-supervised Graph Representation Learning for Recommendation [paper]
76. [arXiv 2022] Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax [paper]
77. [arXiv 2022] Disentangled Graph Contrastive Learning for Review-based Recommendation [paper]
78. [arXiv 2022] Contrastive Learning with Heterogeneous Graph Attention Networks on Short Text Classification [paper]
79. [arXiv 2022] Features Based Adaptive Augmentation for Graph Contrastive Learning [paper]
80. [TKDE 2022] GCCAD: Graph Contrastive Learning for Anomaly Detection [paper]
81. [JCIM 2022] SMICLR: Contrastive Learning on Multiple Molecular Representations for Semisupervised and Unsupervised Representation Learning [paper]
82. [arXiv 2022] XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation [paper][code]
83. [CIKM 2022] Relational Self-Supervised Learning on Graphs [paper][code]
84. [Information Sciences 2022] Self-Supervised Graph Representation Learning via Positive Mining [paper]
85. [arXiv 2022] Heterogeneous Graph Masked Autoencoders [paper]
86. [arXiv 2022] KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion [paper]
87. [arXiv 2022] R'enyiCL: Contrastive Representation Learning with Skew R'enyi Divergence [paper]
88. [TNNLS 2022] Prototypical Graph Contrastive Learning [paper]
89. [KDD 2022] Mining Spatio-Temporal Relations via Self-Paced Graph Contrastive Learning [paper]
90. [KDD 2022] Rep2Vec: Repository Embedding via Heterogeneous Graph Adversarial Contrastive Learning [paper]
91. [arXiv 2022] Deep Contrastive Multiview Network Embedding [paper]
92. [arXiv 2022] Analyzing Data-Centric Properties for Contrastive Learning on Graphs [paper]
93. [KDD 2022] Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries [paper]
94. [arXiv 2022] Generative Subgraph Contrast for Self-Supervised Graph Representation Learning [paper]
95. [IJCAI 2022] Graph Masked Autoencoder Enhanced Predictor for Neural Architecture Search [paper]
96. [IJCAI 2022] Proximity Enhanced Graph Neural Networks with Channel Contrast [paper]
97. [IJCAI 2022] Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification [paper]
98. [IPM 2022] HCNA: Hyperbolic Contrastive Learning Framework for Self-Supervised Network Alignment [paper]
99. [arXiv 2022] 3D Equivariant Molecular Graph Pretraining [paper]
100. [arXiv 2022] Unified 2D and 3D Pre-Training of Molecular Representations [paper]
101. [arXiv 2022] Does GNN Pretraining Help Molecular Representation? [paper]
102. [arXiv 2022] Latent Augmentation For Better Graph Self-Supervised Learning [paper]
103. [arXiv 2022] Geometry Contrastive Learning on Heterogeneous Graphs [paper]
104. [KIS 2022] Self-supervised role learning for graph neural networks [paper]
105. [JFCST 2022] Graph Neural Network Defense Combined with Contrastive Learning [paper]
106. [ICMLW 2022] Evaluating Self-Supervised Learned Molecular Graphs [paper]
107. [KDD 2022] Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN [paper]
108. [ICMLW 2022] Featurizations Matter: A Multiview Contrastive Learning Approach to Molecular Pretraining [paper]
109. [bioRiv 2022] Cross-modal Graph Contrastive Learning with Cellular Images [paper]
110. [Information Sciences 2022] A new self-supervised task on graphs: Geodesic distance prediction [paper]
111. [arXiv 2022] Evaluating Self-Supervised Learning for Molecular Graph Embeddings [paper]
112. [arXiv 2022] Evaluating Graph Generative Models with Contrastively Learned Features [paper]
113. [arXiv 2022] COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning [paper]
114. [arXiv 2022] Decoupled Self-supervised Learning for Non-Homophilous Graphs [paper]
115. [arXiv 2022] Interpolation-based Correlation Reduction Network for Semi-Supervised Graph Learning [paper]
116. [arXiv 2022] Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination [paper]
117. [arXiv 2022] KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction [paper]
118. [CVPR 2022] Robust Optimization As Data Augmentation for Large-Scale Graphs [paper]
119. [arXiv 2022] COIN: Co-Cluster Infomax for Bipartite Graphs [paper]
120. [TSIPN 2022] Fair Contrastive Learning on Graphs [paper]
121. [arXiv 2022] I’m Me, We’re Us, and I’m Us: Tri-directional Contrastive Learning on Hypergraphs [paper]
122. [TNNLS 2022] CLEAR: Cluster-Enhanced Contrast for Self-Supervised Graph Representation Learning [paper]
123. [arXiv 2022] Let Invariant Rationale Discovery Inspire Graph Contrastive Learning [paper]
124. [arXiv 2022] Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning [paper]
125. [arXiv 2022] Improving Subgraph Representation Learning via Multi-View Augmentation [paper]
126. [arXiv 2022] Triangular Contrastive Learning on Molecular Graphs [paper]
127. [KDD 2022] GraphMAE: Self-supervised Masked Graph Autoencoders [paper]
128. [arXiv 2022] MaskGAE: Masked Graph Modeling Meets Graph Autoencoders [paper]
129. [ICML 2022] Understanding Limitations of Unsupervised Graph Representation Learning from a Data-Dependent Perspective [paper]
130. [arXiv 2022] Towards Explanation for Unsupervised Graph-Level Representation Learning [paper]
131. [arXiv 2022] ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification [paper]
132. [TNNLS 2022] Collaborative Decision-Reinforced Self-Supervision for Attributed Graph Clustering [paper]
133. [arXiv 2022] Contrastive Graph Learning with Graph Convolutional Networks [paper]
134. [TISPN 2022] Fair Contrastive Learning on Graphs [paper]
135. [arXiv 2022] SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks [paper]
136. [arXiv 2022] HCL: Hybrid Contrastive Learning for Graph-based Recommendation [paper]
137. [arXiv 2022] Representation learning with function call graph transformations for malware open set recognition [paper]
138. [arXiv 2022] Simple Contrastive Graph Clustering [paper]
139. [NCA 2022] Self-supervised graph representation learning using multi-scale subgraph views contrast [paper]
140. [ACL 2022] JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection [paper]
141. [IPM 2022] Contrastive Graph Convolutional Networks with adaptive augmentation for text classification [paper]
142. [PAKDD 2022] Contrastive Attributed Network Anomaly Detection with Data Augmentation [paper]
143. [DASFAA 2022] CSGNN: Improving Graph Neural Networks with Contrastive Semi-supervised Learning [paper]
144. [arXiv 2022] Dynamic Graph Representation Based on Temporal and Contextual Contrasting [paper]
145. [DASFAA 2022] Diffusion-Based Graph Contrastive Learning for Recommendation with Implicit Feedback [paper]
146. [arXiv 2022] FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation [paper]
147. [arXiv 2022] RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning [paper]
148. [arXiv 2022] Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning [paper]
149. [WSDM 2022] JGCL: Joint Self-Supervised and Supervised Graph Contrastive Learning [paper]
150. [AAAI 2022] SAIL: Self-Augmented Graph Contrastive Learning [paper]
151. [ICASSP 2022] Graph Fine-Grained Contrastive Representation Learning [paper]
152. [arXiv 2022] SCGC: Self-Supervised Contrastive Graph Clustering [paper]
153. [arXiv 2022] A Content-First Benchmark for Self-Supervised Graph Representation Learning [paper]
154. [SIGIR 2022] Hypergraph Contrastive Collaborative Filtering [paper]
155. [WWW 2022] Rumor Detection on Social Media with Graph Adversarial Contrastive Learning [paper]
156. [arXiv 2022] A Review-aware Graph Contrastive Learning Framework for Recommendation [paper]
157. [WWW 2022] Robust Self-Supervised Structural Graph Neural Network for Social Network Prediction [paper]
158. [arXiv 2022] CGC: Contrastive Graph Clustering for Community Detection and Tracking [paper]
159. [TCyber 2022] Multiview Deep Graph Infomax to Achieve Unsupervised Graph Embedding [paper]
160. [arXiv 2022] MVGCNMDA: Multi-view Graph Augmentation Convolutional Network for Uncovering Disease-Related Microbes [paper]
161. [arXiv 2022] CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data [paper]
162. [arXiv 2022] Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation [paper]
163. [SIGIR 2022] Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation [paper][code]
164. [arXiv 2022] Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning [paper]
165. [arXiv 2022] Augmentation-Free Graph Contrastive Learning [paper]
166. [TCybern 2022] Link-Information Augmented Twin Autoencoders for Network Denoising [paper]
167. [arXiv 2022] Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization [paper]
168. [arXiv 2022] GraphCoCo: Graph Complementary Contrastive Learning [paper]
169. [arXiv 2022] Unsupervised Heterophilous Network Embedding via r-Ego Network Discrimination [paper]
170. [Bioinformatics 2022] Supervised Graph Co-contrastive Learning for Drug-Target Interaction Prediction [paper]
171. [arXiv 2022] Supervised Contrastive Learning with Structure Inference for Graph Classification [paper]
172. [arXiv 2022] Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision [paper]
173. [arXiv 2022] Analyzing Heterogeneous Networks with Missing Attributes by Unsupervised Contrastive Learning [paper]
174. [arXiv 2022] Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast [paper]
175. [arXiv 2022] Contrastive Meta Learning with Behavior Multiplicity for Recommendation [paper][code]
176. [arXiv 2022] Fair Node Representation Learning via Adaptive Data Augmentation [paper]
177. [arXiv 2022] Learning Graph Augmentations to Learn Graph Representations [paper][code]
178. [arXiv 2022] Graph Data Augmentation for Graph Machine Learning: A Survey [paper]
179. [arXiv 2022] Data Augmentation for Deep Graph Learning: A Survey [paper]
180. [arXiv 2022] Adversarial Graph Contrastive Learning with Information Regularization [paper]
181. [arXiv 2022] SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation [paper]
182. [NeurIPS 2022] Graph Self-supervised Learning with Accurate Discrepancy Learning [paper]
183. [arXiv 2022] Learning Robust Representation through Graph Adversarial Contrastive Learning [paper]
184. [arXiv 2022] Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data [paper]
185. [arXiv 2022] Link Prediction with Contextualized Self-Supervision [paper]
186. [arXiv 2022] Dual Space Graph Contrastive Learning [paper]
187. [arXiv 2022] Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation [paper]
188. [arXiv 2022] From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach [paper]
189. [arXiv 2022] Dual Space Graph Contrastive Learning [paper]
190. [arXiv 2022] Structure-Enhanced Heterogeneous Graph Contrastive Learning [paper]
191. [bioRxiv 2022] Towards Effective and Generalizable Fine-tuning for Pre-trained Molecular Graph Models [paper]
192. [SDM 2022] Neural Graph Matching for Pre-training Graph Neural Networks [paper] [code]
193. [TNNLS 2022] Analyzing Heterogeneous Networks with Missing Attributes by Unsupervised Contrastive Learning [paper]
194. [WWW 2022] Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning [paper] [code]
195. [WWW 2022] ClusterSCL: Cluster-Aware Supervised Contrastive Learning on Graphs [paper]
196. [ICLR 2022] Large-Scale Representation Learning on Graphs via Bootstrapping [paper][Code]
197. [ICLR 2022] Automated Self-Supervised Learning for Graphs [paper] [code]
198. [AAAI 2022] Self-supervised Graph Neural Networks via Diverse and Interactive Message Passing [paper]
199. [AAAI 2022] Augmentation-Free Self-Supervised Learning on Graphs [paper][code]
200. [AAAI 2022] Molecular Contrastive Learning with Chemical Element Knowledge Graph [paper]
201. [AAAI 2022] Deep Graph Clustering via Dual Correlation Reduction [paper][code]
202. [AAAI 2022] Simple Unsupervised Graph Representation Learning [paper]
203. [WSDM 2022] Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations [paper] [code]
204. [ICOIN 2022] Adaptive Self-Supervised Graph Representation Learning [paper]
205. [NPL 2022] How Does Bayesian Noisy Self-Supervision Defend Graph Convolutional Networks? [paper]
206. [SIGIR 2022] Knowledge Graph Contrastive Learning for Recommendation [paper] [code]

Year 2021

1. [AAAI 2021] Self-supervised hypergraph convolutional networks for session-based recommendation [paper]
2. [arXiv 2021] Pre-training Graph Neural Network for Cross Domain Recommendation [paper]
3. [arXiv 2021] Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices [paper]
4. [arXiv 2021] Collaborative Graph Contrastive Learning: Data Augmentation Composition May Not be Necessary for Graph Representation Learning [paper]
5. [arXiv 2021] Multi-task Self-distillation for Graph-based Semi-Supervised Learning [paper]
6. [arXiv 2021] Subgraph Contrastive Link Representation Learning [paper]
7. [arXiv 2021] Multilayer Graph Contrastive Clustering Network [paper]
8. [arXiv 2021] Graph Representation Learning via Contrasting Cluster Assignments [paper]
9. [arXiv 2021] Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning [paper]
10. [arXiv 2021] Bayesian Graph Contrastive Learning [paper]
11. [arXiv 2021] TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning [paper]
12. [arXiv 2021] Graph Communal Contrastive Learning [paper]
13. [arXiv 2021] Self-supervised Contrastive Attributed Graph Clustering [paper]
14. [arXiv 2021] Self-Supervised Learning for Molecular Property Prediction [paper]
15. [arXiv 2021] RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training [paper]
16. [arXiv 2021] Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation [paper]
17. [arXiv 2021] PRE-TRAINING MOLECULAR GRAPH REPRESENTATION WITH 3D GEOMETRY [paper] [code]
18. [arXiv 2021] 3D Infomax improves GNNs for Molecular Property Prediction [paper] [code]
19. [arXiv 2021] Motif-based Graph Self-Supervised Learning for Molecular Property Prediction [paper]
20. [arXiv 2021] Debiased Graph Contrastive Learning [paper]
21. [arXiv 2021] 3D-Transformer: Molecular Representation with Transformer in 3D Space [paper]
22. [arXiv 2021] Contrastive Pre-Training of GNNs on Heterogeneous Graphs [paper]
23. [arXiv 2021] Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores [paper]
24. [arXiv 2021] GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction [paper]
25. [arXiv 2021] Adaptive Multi-layer Contrastive Graph Neural Networks [paper]
26. [arXiv 2021] Graph-MVP: Multi-View Prototypical Contrastive Learning for Multiplex Graphs [paper]
27. [arXiv 2021] Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation [paper]
28. [arXiv 2021] Negative Sampling Strategies for Contrastive Self-Supervised Learning of Graph Representations [paper]
29. [arXiv 2021] Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning [paper]
30. [arXiv 2021] Spatio-Temporal Graph Contrastive Learning [paper]
31. [arXiv 2021] Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection [paper]
32. [Arxiv 2021] Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation [paper] [code]
33. [arXiv 2021] GCCAD: Graph Contrastive Coding for Anomaly Detection [paper]
34. [arXiv 2021] Contrastive Self-supervised Sequential Recommendation with Robust Augmentation [paper]
35. [arXiv 2021] RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks [paper]
36. [arXiv 2021] Group Contrastive Self-Supervised Learning on Graphs [paper]
37. [arXiv 2021] Multi-Level Graph Contrastive Learning [paper]
38. [arXiv 2021] From Canonical Correlation Analysis to Self-supervised Graph Neural Networks [paper] [code]
39. [arXiv 2021] Evaluating Modules in Graph Contrastive Learning [paper] [code]
40. [arXiv 2021] Prototypical Graph Contrastive Learning [paper]
41. [arXiv 2021] Fairness-Aware Node Representation Learning [paper]
42. [arXiv 2021] Adversarial Graph Augmentation to Improve Graph Contrastive Learning [paper]
43. [arXiv 2021] Graph Barlow Twins: A self-supervised representation learning framework for graphs [paper]
44. [arXiv 2021] Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast [paper]
45. [arXiv 2021] Self-supervised on Graphs: Contrastive, Generative,or Predictive [paper]
46. [arXiv 2021] FedGL: Federated Graph Learning Framework with Global Self-Supervision [paper]
47. [arXiv 2021] Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks [paper]
48. [arXiv 2021] Representation Learning for Networks in Biology and Medicine: Advancements, Challenges, and Opportunities [paper]
49. [arXiv 2021] Graph Representation Learning by Ensemble Aggregating Subgraphs via Mutual Information Maximization [paper]
50. [arXiv 2021] Drug Target Prediction Using Graph Representation Learning via Substructures Contrast [paper]
51. [arXiv 2021] Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning [paper]
52. [arXiv 2021] Graph Self-Supervised Learning: A Survey [paper]
53. [arXiv 2021] Towards Robust Graph Contrastive Learning [paper]
54. [arXiv 2021] Pre-Training on Dynamic Graph Neural Networks [paper]
55. [arXiv 2021] Self-Supervised Learning of Graph Neural Networks: A Unified Review [paper]
56. [Openreview 2021] An Empirical Study of Graph Contrastive Learning [paper]
57. [BIBM 2021] SGAT: a Self-supervised Graph Attention Network for Biomedical Relation Extraction [paper]
58. [BIBM 2021] Molecular Graph Contrastive Learning with Parameterized Explainable Augmentations [paper]
59. [NeurIPS 2021 Workshop] Self-Supervised GNN that Jointly Learns to Augment [paper]
60. [NeurIPS 2021 Workshop] Contrastive Embedding of Structured Space for Bayesian Optimisation [paper]
61. [NeurIPS 2021] Enhancing Hyperbolic Graph Embeddings via Contrastive Learning [paper]
62. [NeurIPS 2021] Graph Adversarial Self-Supervised Learning [paper]
63. [NeurIPS 2021] Contrastive laplacian eigenmaps [paper]
64. [NeurIPS 2021] Directed Graph Contrastive Learning [paper][code]
65. [NeurIPS 2021] Multi-view Contrastive Graph Clustering [paper][code]
66. [NeurIPS 2021] From Canonical Correlation Analysis to Self-supervised Graph Neural Networks [paper][code]
67. [NeurIPS 2021] InfoGCL: Information-Aware Graph Contrastive Learning [paper]
68. [NeurIPS 2021] Adversarial Graph Augmentation to Improve Graph Contrastive Learning [paper][code]
69. [NeurIPS 2021] Disentangled Contrastive Learning on Graphs [paper]
70. [CIKM 2021] Multimodal Graph Meta Contrastive Learning [paper]
71. [CIKM 2021] Self-supervised Representation Learning on Dynamic Graphs [paper]
72. [CIKM 2021] Rectifying Pseudo Labels: Iterative Feature Clustering for Graph Representation Learning [paper]
73. [CIKM 2021] SGCL: Contrastive Representation Learning for Signed Graphs [paper]
74. [CIKM 2021] Semi-Supervised and Self-Supervised Classification with Multi-View Graph Neural Networks [paper]
75. [CIKM 2021] Social Recommendation with Self-Supervised Metagraph Informax Network [paper] [code]
76. [IJCAI 2021] Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning [paper]
77. [IJCAI 2021] Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks [paper]
78. [IJCAI 2021] CuCo: Graph Representation with Curriculum Contrastive Learning [paper]
79. [IJCAI 2021] Graph Debiased Contrastive Learning with Joint Representation Clustering [paper]
80. [IJCAI 2021] CSGNN: Contrastive Self-Supervised Graph Neural Network for Molecular Interaction Prediction [paper]
81. [KDD 2021] MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph [paper] [code]
82. [KDD 2021] Contrastive Multi-View Multiplex Network Embedding with Applications to Robust Network Alignment [paper]
83. [KDD 2021] Adaptive Transfer Learning on Graph Neural Networks [paper]
84. :fire:[ICML 2021] Graph Contrastive Learning Automated [paper] [code]
85. [ICML 2021] Self-supervised Graph-level Representation Learning with Local and Global Structure [paper] [code]
86. [KDD 2021] Pre-training on Large-Scale Heterogeneous Graph [paper]
87. [KDD 2021] MoCL: Contrastive Learning on Molecular Graphs with Multi-level Domain Knowledge [paper]
88. [KDD 2021] Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning [paper] [code]
89. [WWW 2021 Workshop] Iterative Graph Self-Distillation [paper]
90. [WWW 2021] HDMI: High-order Deep Multiplex Infomax [paper] [code]
91. :fire:[WWW 2021] Graph Contrastive Learning with Adaptive Augmentation [paper] [code]
92. [WWW 2021] SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism [paper] [code]
93. [WWW 2021] Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction [paper] [code]
94. :fire:[ICLR 2021] How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision [paper] [code]
95. [WSDM 2021] Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation [paper] [code]
96. [KBS 2021] Multi-aspect self-supervised learning for heterogeneous information network [paper]
97. [CVPR 2021] Zero-Shot Learning via Contrastive Learning on Dual Knowledge Graphs [paper]
98. [ICBD 2021] Session-based Recommendation via Contrastive Learning on Heterogeneous Graph [paper]
99. [ICONIP 2021] Concordant Contrastive Learning for Semi-supervised Node Classification on Graph [paper]
100. [ICCSNT 2021] Graph Data Augmentation based on Adaptive Graph Convolution for Skeleton-based Action Recognition [paper]
101. [IJCNN 2021] Node Embedding using Mutual Information and Self-Supervision based Bi-level Aggregation [paper]

Year 2020

1. [Openreview 2020] Motif-Driven Contrastive Learning of Graph Representations [paper]
2. [Openreview 2020] SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks [paper]
3. [Openreview 2020] TopoTER: Unsupervised Learning of Topology Transformation Equivariant Representations [paper]
4. [Openreview 2020] Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks [paper]
5. [Openreview 2020] Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization [paper]
6. [Arxiv 2020] COAD: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking [paper] [code]
7. [Arxiv 2020] Distance-wise Graph Contrastive Learning [paper]
8. :fire:[Arxiv 2020] Self-supervised Learning on Graphs: Deep Insights and New Direction. [paper] [code]
9. :fire:[Arxiv 2020] Deep Graph Contrastive Representation Learning [paper]
10. [Arxiv 2020] Self-supervised Training of Graph Convolutional Networks. [paper]
11. [Arxiv 2020] Self-Supervised Graph Representation Learning via Global Context Prediction. [paper]
12. :fire:[Arxiv 2020] Graph-Bert: Only Attention is Needed for Learning Graph Representations. [paper] [code]
13. :fire:[NeurIPS 2020] Self-Supervised Graph Transformer on Large-Scale Molecular Data [paper]
14. [NeurIPS 2020] Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs [paper] [code]
15. :fire:[NeurIPS 2020] Graph Contrastive Learning with Augmentations [paper] [code]
16. :fire:[ICML 2020] When Does Self-Supervision Help Graph Convolutional Networks? [paper] [code]
17. :fire:[ICML 2020] Graph-based, Self-Supervised Program Repair from Diagnostic Feedback. [paper]
18. :fire:[ICML 2020] Contrastive Multi-View Representation Learning on Graphs. [paper] [code]
19. [ICML 2020 Workshop] Self-supervised edge features for improved Graph Neural Network training. [paper]
20. :fire:[KDD 2020] GPT-GNN: Generative Pre-Training of Graph Neural Networks. [pdf] [code]
21. :fire:[KDD 2020] GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training. [pdf] [code]
22. :fire:[ICLR 2020] InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization. [paper] [code]
23. :fire:[ICLR 2020] Strategies for Pre-training Graph Neural Networks. [paper] [code]
24. :fire:[AAAI 2020] Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels. [paper]
25. [ICDM 2020] Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning [paper] [code]

Year 2019

1. [KDD 2019 Workshop] SGR: Self-Supervised Spectral Graph Representation Learning. [paper]
2. [ICLR 2019 Workshop] Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference. [paper]
3. [ICLR 2019 workshop] Pre-Training Graph Neural Networks for Generic Structural Feature Extraction. [paper]
4. [Arxiv 2019] Heterogeneous Deep Graph Infomax [paper] [code]
5. :fire:[ICLR 2019] Deep Graph Informax. [paper] [code]

Other related papers

(implicitly using self-supersvied learning or applying graph neural networks in other domains)

1. [Arxiv 2020] Self-supervised Learning: Generative or Contrastive. [paper]
2. [KDD 2020] Octet: Online Catalog Taxonomy Enrichment with Self-Supervision. [paper]
3. [WWW 2020] Structural Deep Clustering Network. [paper] [code]
4. [IJCAI 2019] Pre-training of Graph Augmented Transformers for Medication Recommendation. [paper] [code]
5. [AAAI 2020] Unsupervised Attributed Multiplex Network Embedding [paper] [code]
6. [WWW 2020] Graph representation learning via graphical mutual information maximization [paper]
7. [NeurIPS 2017] Inductive Representation Learning on Large Graphs [paper] [code]
8. [NeurIPS 2016 Workshop] Variational Graph Auto-Encoders [paper] [code]
9. [WWW 2015] LINE: Large-scale Information Network Embedding [paper] [code]
10. [KDD 2014] DeepWalk: Online Learning of Social Representations [paper] [code]

Acknowledgement

This page is contributed and maintained by Wei Jin(joe.weijin@gmail.com), Yuning You(yuning.you@tamu.edu) and Yingheng Wang(jakewyh@163.com).

awesome-self-supervised-gnn 快速上手指南

awesome-self-supervised-gnn 并非一个可直接安装的软件包或框架，而是一个精选论文与代码资源列表。它汇集了图神经网络（GNN）领域中自监督学习方向的前沿研究成果。本指南将指导你如何利用该仓库查找资源、获取代码并复现相关算法。

环境准备

由于本仓库包含多个不同作者实现的独立项目，没有统一的前置依赖。你需要根据具体想复现的论文，配置相应的环境。

系统要求

• 操作系统: Linux, macOS, 或 Windows (推荐 Linux)
• Python: 建议版本 3.8+ (具体版本需参考目标论文的 requirements.txt)
• GPU: 推荐配备 NVIDIA GPU 以加速训练 (可选，视具体模型而定)

前置依赖

在克隆仓库后，建议安装通用的深度学习基础库。大多数列表中的项目基于以下框架：

• PyTorch
• DGL (Deep Graph Library) 或 PyTorch Geometric (PyG)
• NumPy, SciPy, Pandas

安装步骤

1. 克隆仓库

首先，将资源列表仓库克隆到本地。国内用户推荐使用 Gitee 镜像（如有）或通过加速代理访问 GitHub。

git clone https://github.com/ChandlerBang/awesome-self-supervised-gnn.git
cd awesome-self-supervised-gnn

2. 选择目标项目

浏览目录中的 README.md 文件，按年份（如 Year 2023, Year 2024）查找你感兴趣的论文。每个条目都提供了 Paper (论文链接) 和 Code (代码仓库链接)。

3. 安装具体项目的依赖

点击对应论文的 [[code]] 链接进入其独立的 GitHub 仓库，按照该项目具体的说明进行安装。通常步骤如下：

# 假设你选择了 "GTrans" 项目 (ICLR 2023)
git clone https://github.com/ChandlerBang/GTrans.git
cd GTrans

# 创建虚拟环境 (推荐)
python -m venv venv
source venv/bin/activate  # Windows 用户使用: venv\Scripts\activate

# 安装依赖 (优先使用国内镜像源加速)
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

注意：如果目标项目未提供 requirements.txt，请根据论文描述手动安装 torch, dgl 或 torch-geometric 等核心库。

基本使用

本仓库的核心用法是作为索引查找代码，然后运行具体项目的脚本。以下以列表中 2023 年的热门项目 GTrans 为例，展示典型的复现流程：

示例：运行 GTrans (Test-Time Graph Transformation)

1. 获取数据： 大多数 GNN 项目会自动下载标准数据集（如 Cora, Citeseer, Pubmed）。确保网络通畅，或手动下载数据集放置于项目指定的 data/ 目录下。

2. 执行训练/评估： 进入项目目录，运行提供的训练脚本。命令通常如下：

   python main.py --dataset cora --model gtrans
   

3. 查看结果： 程序运行结束后，终端将输出准确率（Accuracy）、NMI 或其他评估指标，结果通常也会保存至 results/ 文件夹。

查找高引用论文

仓库 README 中使用 :fire: 标记了高引用论文（引用数 > 80）。你可以运行仓库根目录下可能提供的辅助脚本（如原文提到的 get_hot.py，若存在）来筛选这些热门资源，或者直接阅读 README 中带有火焰图标的条目。

# 如果仓库包含此工具脚本
python get_hot.py

通过上述步骤，你可以高效地利用 awesome-self-supervised-gnn 追踪最新技术，并在本地复现顶尖的自监督图学习算法。