/awesome-self-supervised-gnn

Papers about pretraining and self-supervised learning on Graph Neural Networks (GNN).

awesome-self-supervised-gnn

PRs Welcome Awesome Stars Forks

This repository contains a list of papers on the Self-supervised Learning on Graph Neural Networks (GNNs), we categorize them based on their published years.

We will try to make this list updated. If you found any error or any missed paper, please don't hesitate to open an issue or pull request.

Year 2022

  1. [KDD 2022] GraphMAE: Self-supervised Masked Graph Autoencoders [paper]
  2. [arXiv 2022] SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks [paper]
  3. [arXiv 2022] HCL: Hybrid Contrastive Learning for Graph-based Recommendation [paper]
  4. [arXiv 2022] Representation learning with function call graph transformations for malware open set recognition [paper]
  5. [arXiv 2022] Simple Contrastive Graph Clustering [paper]
  6. [NCA 2022] Self-supervised graph representation learning using multi-scale subgraph views contrast [paper]
  7. [ACL 2022] JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection [paper]
  8. [IPM 2022] Contrastive Graph Convolutional Networks with adaptive augmentation for text classification [paper]
  9. [PAKDD 2022] Contrastive Attributed Network Anomaly Detection with Data Augmentation [paper]
  10. [DASFAA 2022] CSGNN: Improving Graph Neural Networks with Contrastive Semi-supervised Learning [paper]
  11. [arXiv 2022] Dynamic Graph Representation Based on Temporal and Contextual Contrasting [paper]
  12. [DASFAA 2022] Diffusion-Based Graph Contrastive Learning for Recommendation with Implicit Feedback [paper]
  13. [arXiv 2022] FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation [paper]
  14. [arXiv 2022] RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning [paper]
  15. [arXiv 2022] Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning [paper]
  16. [WSDM 2022] JGCL: Joint Self-Supervised and Supervised Graph Contrastive Learning [paper]
  17. [AAAI 2022] SAIL: Self-Augmented Graph Contrastive Learning [paper]
  18. [ICASSP 2022] Graph Fine-Grained Contrastive Representation Learning [paper]
  19. [arXiv 2022] SCGC: Self-Supervised Contrastive Graph Clustering [paper]
  20. [arXiv 2022] A Content-First Benchmark for Self-Supervised Graph Representation Learning [paper]
  21. [SIGIR 2022] Hypergraph Contrastive Collaborative Filtering [paper]
  22. [WWW 2022] Rumor Detection on Social Media with Graph Adversarial Contrastive Learning [paper]
  23. [arXiv 2022] A Review-aware Graph Contrastive Learning Framework for Recommendation [paper]
  24. [WWW 2022] Robust Self-Supervised Structural Graph Neural Network for Social Network Prediction [paper]
  25. [arXiv 2022] CGC: Contrastive Graph Clustering for Community Detection and Tracking [paper]
  26. [TCyber 2022] Multiview Deep Graph Infomax to Achieve Unsupervised Graph Embedding [paper]
  27. [arXiv 2022] MVGCNMDA: Multi-view Graph Augmentation Convolutional Network for Uncovering Disease-Related Microbes [paper]
  28. [arXiv 2022] CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data [paper]
  29. [arXiv 2022] Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation [paper]
  30. [arXiv 2022] Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation [paper]
  31. [arXiv 2022] Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning [paper]
  32. [arXiv 2022] Augmentation-Free Graph Contrastive Learning [paper]
  33. [TCybern 2022] Link-Information Augmented Twin Autoencoders for Network Denoising [paper]
  34. [arXiv 2022] Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization [paper]
  35. [arXiv 2022] GraphCoCo: Graph Complementary Contrastive Learning [paper]
  36. [arXiv 2022] Unsupervised Heterophilous Network Embedding via r-Ego Network Discrimination [paper]
  37. [Bioinformatics 2022] Supervised Graph Co-contrastive Learning for Drug-Target Interaction Prediction [paper]
  38. [arXiv 2022] Supervised Contrastive Learning with Structure Inference for Graph Classification [paper]
  39. [arXiv 2022] Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision [paper]
  40. [arXiv 2022] Structural and Semantic Contrastive Learning for Self-supervised Node Representation Learning [paper]
  41. [arXiv 2022] Analyzing Heterogeneous Networks with Missing Attributes by Unsupervised Contrastive Learning [paper]
  42. [arXiv 2022] Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast [paper]
  43. [arXiv 2022] Contrastive Meta Learning with Behavior Multiplicity for Recommendation [paper][code]
  44. [arXiv 2022] Fair Node Representation Learning via Adaptive Data Augmentation [paper]
  45. [arXiv 2022] Learning Graph Augmentations to Learn Graph Representations [paper][code]
  46. [arXiv 2022] Graph Data Augmentation for Graph Machine Learning: A Survey [paper]
  47. [arXiv 2022] Data Augmentation for Deep Graph Learning: A Survey [paper]
  48. [arXiv 2022] Adversarial Graph Contrastive Learning with Information Regularization [paper]
  49. [arXiv 2022] SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation [paper]
  50. [arXiv 2022] Graph Self-supervised Learning with Accurate Discrepancy Learning [paper]
  51. [arXiv 2022] Learning Robust Representation through Graph Adversarial Contrastive Learning [paper]
  52. [arXiv 2022] Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data [paper]
  53. [arXiv 2022] Link Prediction with Contextualized Self-Supervision [paper]
  54. [arXiv 2022] Dual Space Graph Contrastive Learning [paper]
  55. [arXiv 2022] Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation [paper]
  56. [arXiv 2022] From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach [paper]
  57. [arXiv 2022] Dual Space Graph Contrastive Learning [paper]
  58. [arXiv 2022] Structure-Enhanced Heterogeneous Graph Contrastive Learning [paper]
  59. [bioRxiv 2022] Towards Effective and Generalizable Fine-tuning for Pre-trained Molecular Graph Models [paper]
  60. [SDM 2022] Neural Graph Matching for Pre-training Graph Neural Networks [paper] [code]
  61. [TNNLS 2022] Analyzing Heterogeneous Networks with Missing Attributes by Unsupervised Contrastive Learning [paper]
  62. [WWW 2022] Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning [paper] [code]
  63. [WWW 2022] ClusterSCL: Cluster-Aware Supervised Contrastive Learning on Graphs [paper]
  64. [ICLR 2022] Large-Scale Representation Learning on Graphs via Bootstrapping [paper][Code]
  65. [ICLR 2022] Automated Self-Supervised Learning for Graphs [paper] [code]
  66. [AAAI 2022] Self-supervised Graph Neural Networks via Diverse and Interactive Message Passing [paper]
  67. [AAAI 2022] Augmentation-Free Self-Supervised Learning on Graphs [paper][code]
  68. [AAAI 2022] Molecular Contrastive Learning with Chemical Element Knowledge Graph [paper]
  69. [AAAI 2022] Deep Graph Clustering via Dual Correlation Reduction [paper][code]
  70. [AAAI 2022] Simple Unsupervised Graph Representation Learning [paper]
  71. [WSDM 2022] Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations [paper] [code]
  72. [ICOIN 2022] Adaptive Self-Supervised Graph Representation Learning [paper]
  73. [NPL 2022] How Does Bayesian Noisy Self-Supervision Defend Graph Convolutional Networks? [paper]
  74. [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] Graph Augmentation-Free Contrastive Learning for Recommendation [paper]
  11. [arXiv 2021] Bayesian Graph Contrastive Learning [paper]
  12. [arXiv 2021] TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning [paper]
  13. [arXiv 2021] Graph Communal Contrastive Learning [paper]
  14. [arXiv 2021] Self-supervised Contrastive Attributed Graph Clustering [paper]
  15. [arXiv 2021] Self-Supervised Learning for Molecular Property Prediction [paper]
  16. [arXiv 2021] RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training [paper]
  17. [arXiv 2021] Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation [paper]
  18. [arXiv 2021] PRE-TRAINING MOLECULAR GRAPH REPRESENTATION WITH 3D GEOMETRY [paper] [code]
  19. [arXiv 2021] 3D Infomax improves GNNs for Molecular Property Prediction [paper] [code]
  20. [arXiv 2021] Motif-based Graph Self-Supervised Learning for Molecular Property Prediction [paper]
  21. [arXiv 2021] Debiased Graph Contrastive Learning [paper]
  22. [arXiv 2021] 3D-Transformer: Molecular Representation with Transformer in 3D Space [paper]
  23. [arXiv 2021] Contrastive Pre-Training of GNNs on Heterogeneous Graphs [paper]
  24. [arXiv 2021] Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores [paper]
  25. [arXiv 2021] GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction [paper]
  26. [arXiv 2021] Adaptive Multi-layer Contrastive Graph Neural Networks [paper]
  27. [arXiv 2021] Graph-MVP: Multi-View Prototypical Contrastive Learning for Multiplex Graphs [paper]
  28. [arXiv 2021] Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation [paper]
  29. [arXiv 2021] Negative Sampling Strategies for Contrastive Self-Supervised Learning of Graph Representations [paper]
  30. [arXiv 2021] Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning [paper]
  31. [arXiv 2021] Spatio-Temporal Graph Contrastive Learning [paper]
  32. [arXiv 2021] Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection [paper]
  33. [Arxiv 2021] Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation [paper] [code]
  34. [arXiv 2021] GCCAD: Graph Contrastive Coding for Anomaly Detection [paper]
  35. [arXiv 2021] Contrastive Self-supervised Sequential Recommendation with Robust Augmentation [paper]
  36. [arXiv 2021] RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks [paper]
  37. [arXiv 2021] Group Contrastive Self-Supervised Learning on Graphs [paper]
  38. [arXiv 2021] Multi-Level Graph Contrastive Learning [paper]
  39. [arXiv 2021] From Canonical Correlation Analysis to Self-supervised Graph Neural Networks [paper] [code]
  40. [arXiv 2021] Evaluating Modules in Graph Contrastive Learning [paper] [code]
  41. [arXiv 2021] Prototypical Graph Contrastive Learning [paper]
  42. [arXiv 2021] Fairness-Aware Node Representation Learning [paper]
  43. [arXiv 2021] Adversarial Graph Augmentation to Improve Graph Contrastive Learning [paper]
  44. [arXiv 2021] Graph Barlow Twins: A self-supervised representation learning framework for graphs [paper]
  45. [arXiv 2021] Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast [paper]
  46. [arXiv 2021] Self-supervised on Graphs: Contrastive, Generative,or Predictive [paper]
  47. [arXiv 2021] FedGL: Federated Graph Learning Framework with Global Self-Supervision [paper]
  48. [arXiv 2021] Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks [paper]
  49. [arXiv 2021] Representation Learning for Networks in Biology and Medicine: Advancements, Challenges, and Opportunities [paper]
  50. [arXiv 2021] Graph Representation Learning by Ensemble Aggregating Subgraphs via Mutual Information Maximization [paper]
  51. [arXiv 2021] Drug Target Prediction Using Graph Representation Learning via Substructures Contrast [paper]
  52. [arXiv 2021] Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning [paper]
  53. [arXiv 2021] Graph Self-Supervised Learning: A Survey [paper]
  54. [arXiv 2021] Towards Robust Graph Contrastive Learning [paper]
  55. [arXiv 2021] Pre-Training on Dynamic Graph Neural Networks [paper]
  56. [arXiv 2021] Self-Supervised Learning of Graph Neural Networks: A Unified Review [paper]
  57. [Openreview 2021] An Empirical Study of Graph Contrastive Learning [paper]
  58. [BIBM 2021] SGAT: a Self-supervised Graph Attention Network for Biomedical Relation Extraction [paper]
  59. [BIBM 2021] Molecular Graph Contrastive Learning with Parameterized Explainable Augmentations [paper]
  60. [NeurIPS 2021 Workshop] Self-Supervised GNN that Jointly Learns to Augment [paper]
  61. [NeurIPS 2021 Workshop] Contrastive Embedding of Structured Space for Bayesian Optimisation [paper]
  62. [NeurIPS 2021] Enhancing Hyperbolic Graph Embeddings via Contrastive Learning [paper]
  63. [NeurIPS 2021] Graph Adversarial Self-Supervised Learning [paper]
  64. [NeurIPS 2021] Contrastive laplacian eigenmaps [paper]
  65. [NeurIPS 2021] Directed Graph Contrastive Learning [paper][code]
  66. [NeurIPS 2021] Multi-view Contrastive Graph Clustering [paper][code]
  67. [NeurIPS 2021] From Canonical Correlation Analysis to Self-supervised Graph Neural Networks [paper][code]
  68. [NeurIPS 2021] InfoGCL: Information-Aware Graph Contrastive Learning [paper]
  69. [NeurIPS 2021] Adversarial Graph Augmentation to Improve Graph Contrastive Learning [paper][code]
  70. [NeurIPS 2021] Disentangled Contrastive Learning on Graphs [paper]
  71. [CIKM 2021] Multimodal Graph Meta Contrastive Learning [paper]
  72. [CIKM 2021] Self-supervised Representation Learning on Dynamic Graphs [paper]
  73. [CIKM 2021] Rectifying Pseudo Labels: Iterative Feature Clustering for Graph Representation Learning [paper]
  74. [CIKM 2021] SGCL: Contrastive Representation Learning for Signed Graphs [paper]
  75. [CIKM 2021] Semi-Supervised and Self-Supervised Classification with Multi-View Graph Neural Networks [paper]
  76. [CIKM 2021] Social Recommendation with Self-Supervised Metagraph Informax Network [paper] [code]
  77. [IJCAI 2021] Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning [paper]
  78. [IJCAI 2021] Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks [paper]
  79. [IJCAI 2021] CuCo: Graph Representation with Curriculum Contrastive Learning [paper]
  80. [IJCAI 2021] Graph Debiased Contrastive Learning with Joint Representation Clustering [paper]
  81. [IJCAI 2021] CSGNN: Contrastive Self-Supervised Graph Neural Network for Molecular Interaction Prediction [paper]
  82. [KDD 2021] MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph [paper] [code]
  83. [KDD 2021] Contrastive Multi-View Multiplex Network Embedding with Applications to Robust Network Alignment [paper]
  84. [KDD 2021] Adaptive Transfer Learning on Graph Neural Networks [paper]
  85. [ICML 2021] Graph Contrastive Learning Automated [paper] [code]
  86. [ICML 2021] Self-supervised Graph-level Representation Learning with Local and Global Structure [paper] [code]
  87. [KDD 2021] Pre-training on Large-Scale Heterogeneous Graph [paper]
  88. [KDD 2021] MoCL: Contrastive Learning on Molecular Graphs with Multi-level Domain Knowledge [paper]
  89. [KDD 2021] Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning [paper] [code]
  90. [WWW 2021 Workshop] Iterative Graph Self-Distillation [paper]
  91. [WWW 2021] HDMI: High-order Deep Multiplex Infomax [paper] [code]
  92. [WWW 2021] Graph Contrastive Learning with Adaptive Augmentation [paper] [code]
  93. [WWW 2021] SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism [paper] [code]
  94. [WWW 2021] Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction [paper] [code]
  95. [ICLR 2021] How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision [paper] [code]
  96. [WSDM 2021] Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation [paper] [code]
  97. [KBS 2021] Multi-aspect self-supervised learning for heterogeneous information network [paper]
  98. [CVPR 2021] Zero-Shot Learning via Contrastive Learning on Dual Knowledge Graphs [paper]
  99. [ICBD 2021] Session-based Recommendation via Contrastive Learning on Heterogeneous Graph [paper]
  100. [ICONIP 2021] Concordant Contrastive Learning for Semi-supervised Node Classification on Graph [paper]
  101. [ICCSNT 2021] Graph Data Augmentation based on Adaptive Graph Convolution for Skeleton-based Action Recognition [paper]
  102. [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. [Arxiv 2020] Self-supervised Learning on Graphs: Deep Insights and New Direction. [paper] [code]
  9. [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. [Arxiv 2020] Graph-Bert: Only Attention is Needed for Learning Graph Representations. [paper] [code]
  13. [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. [NeurIPS 2020] Graph Contrastive Learning with Augmentations [paper] [code]
  16. [ICML 2020] When Does Self-Supervision Help Graph Convolutional Networks? [paper] [code]
  17. [ICML 2020] Graph-based, Self-Supervised Program Repair from Diagnostic Feedback. [paper]
  18. [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. [KDD 2020] GPT-GNN: Generative Pre-Training of Graph Neural Networks. [pdf] [code]
  21. [KDD 2020] GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training. [pdf] [code]
  22. [ICLR 2020] InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization. [paper] [code]
  23. [ICLR 2020] Strategies for Pre-training Graph Neural Networks. [paper] [code]
  24. [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. [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).