mlsanityData to 7 Oct 2026

When Does Self-Supervision Help Graph Convolutional Networks?

arXiv 2006.09136 ↗First posted 16 Jun 2020cs.LG stat.MLcited by 121

Not on the map. Why?

Abstract (arXiv)

Self-supervision as an emerging technique has been employed to train convolutional neural networks (CNNs) for more transferrable, generalizable, and robust representation learning of images. Its introduction to graph convolutional networks (GCNs) operating on graph data is however rarely explored. In this study, we report the first systematic exploration and assessment of incorporating self-supervision into GCNs. We first elaborate three mechanisms to incorporate self-supervision into GCNs, analyze the limitations of pretraining & finetuning and self-training, and proceed to focus on multi-task learning. Moreover, we propose to investigate three novel self-supervised learning tasks for GCNs with theoretical rationales and numerical comparisons. Lastly, we further integrate multi-task self-supervision into graph adversarial training. Our results show that, with properly designed task forms and incorporation mechanisms, self-supervision benefits GCNs in gaining more generalizability and robustness. Our codes are available at https://github.com/Shen-Lab/SS-GCNs.

Key facts. Cited by 121 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 40; 2022: 33; 2023: 21; 2024: 21; 2025: 4; 2026: 2.

121 papers.

Sort:

By area:

  1. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  2. 2021Graph Self-Supervised Learning: A Surveycited by 289
  3. 2021Graph Contrastive Learning Automatedcited by 287
  4. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  5. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  6. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  7. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  8. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  9. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  10. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
  11. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  12. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
38 more
  1. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  2. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  3. 2022Graph Attention Multi-Layer Perceptroncited by 82
  4. 2021Graph Representation Learning in Biomedicinecited by 79
  5. 2021AutoGCL: Automated Graph Contrastive Learning via Learnable View Generatorscited by 73
  6. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  7. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  8. 2021Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detectioncited by 67
  9. 2021MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graphcited by 65
  10. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 63
  11. 2022Does GNN Pretraining Help Molecular Representation?cited by 59
  12. 2021Automated Self-Supervised Learning for Graphscited by 50
  13. 2023Rethinking Tokenizer and Decoder in Masked Graph Modeling for Moleculescited by 49
  14. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
  15. 2021Rethinking Graph Auto-Encoder Models for Attributed Graph Clusteringcited by 37
  16. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  17. 2021When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?cited by 36
  18. 2022Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalizationcited by 35
  19. 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
  20. 2021Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networkscited by 31
  21. 2021Adaptive Transfer Learning on Graph Neural Networkscited by 31
  22. 2022SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Drivingcited by 31
  23. 2022MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initializationcited by 31
  24. 2022Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentationscited by 28
  25. 2022Augmentations in Hypergraph Contrastive Learning: Fabricated and Generativecited by 28
  26. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  27. 2021Curvature Graph Neural Networkcited by 24
  28. 2021Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practicescited by 24
  29. 2023SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Maskingcited by 23
  30. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
  31. 2022Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Predictioncited by 22
  32. 2022CGC: Contrastive Graph Clustering for Community Detection and Trackingcited by 21
  33. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  34. 2022Informative Pseudo-Labeling for Graph Neural Networks with Few Labelscited by 19
  35. 2021ROD: Reception-aware Online Distillation for Sparse Graphscited by 18
  36. 2023When to Pre-Train Graph Neural Networks? From Data Generation Perspective!cited by 17
  37. 2021Graph Neural Networks: Methods, Applications, and Opportunitiescited by 16
  38. 2022Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervisioncited by 16

50 most cited of 121 All 121 (JSON)