mlsanityData to 7 Oct 2026

Spectral Augmentation for Self-Supervised Learning on Graphs

arXiv 2210.00643 ↗First posted 2 Oct 2022cs.LG cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Graph contrastive learning (GCL), as an emerging self-supervised learning technique on graphs, aims to learn representations via instance discrimination. Its performance heavily relies on graph augmentation to reflect invariant patterns that are robust to small perturbations; yet it still remains unclear about what graph invariance GCL should capture. Recent studies mainly perform topology augmentations in a uniformly random manner in the spatial domain, ignoring its influence on the intrinsic structural properties embedded in the spectral domain. In this work, we aim to find a principled way for topology augmentations by exploring the invariance of graphs from the spectral perspective. We develop spectral augmentation which guides topology augmentations by maximizing the spectral change. Extensive experiments on both graph and node classification tasks demonstrate the effectiveness of our method in self-supervised representation learning. The proposed method also brings promising generalization capability in transfer learning, and is equipped with intriguing robustness property under adversarial attacks. Our study sheds light on a general principle for graph topology augmentation.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 54 of its 82 references that are in the map. First posted on arXiv 2 Oct 2022.

Builds on

54 of 82 references.

References · 54

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  9. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  12. 2018Deep Graph Infomaxcited by 1,101
38 more
  1. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  2. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  3. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  4. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  5. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  7. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  8. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  9. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  10. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  11. 2019On Variational Bounds of Mutual Informationcited by 550
  12. 2020Deep Graph Contrastive Representation Learningcited by 535
  13. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  14. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 461
  15. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  16. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  17. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  18. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  19. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
  20. 2021Graph Contrastive Learning Automatedcited by 287
  21. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  22. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  23. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
  24. 2017struc2vec: Learning Node Representations from Structural Identitycited by 214
  25. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  26. 2017Predicting multicellular function through multi-layer tissue networkscited by 138
  27. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  28. 2020When Does Self-Supervision Help Graph Convolutional Networks?cited by 121
  29. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  30. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  31. 2021Augmentation-Free Self-Supervised Learning on Graphscited by 94
  32. 2020Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learningcited by 90
  33. 2021Graph Barlow Twins: A self-supervised representation learning framework for graphscited by 85
  34. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  35. 2019Stability and Generalization of Graph Convolutional Neural Networkscited by 81
  36. 2016Hiding Individuals and Communities in a Social Networkcited by 77
  37. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  38. 2022Adversarial Graph Contrastive Learning with Information Regularizationcited by 38

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 19; 2025: 4; 2026: 3.

38 papers.

Sort:

By area:

  1. 2023Data-centric Graph Learning: A Surveycited by 22
  2. 2023Embedding in Recommender Systems: A Surveycited by 19
  3. 2024Road Network Representation Learning with the Third Law of Geographycited by 10
  4. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  5. 2023Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learningcited by 6
  6. 2023Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learningcited by 6
  7. 2024Graph Contrastive Learning with Cohesive Subgraph Awarenesscited by 6
  8. 2024A Pure Transformer Pretraining Framework on Text-attributed Graphscited by 6
  9. 2024Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correctioncited by 5
  10. 2023Spectral-Aware Augmentation for Enhanced Graph Representation Learningcited by 4
  11. 2024Community-Invariant Graph Contrastive Learningcited by 4
  12. 2023Globally Interpretable Graph Learning via Distribution Matchingcited by 3
26 more
  1. 2024DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networkscited by 3
  2. 2026MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Modelscited by 3
  3. 2023Perfect Alignment May be Poisonous to Graph Contrastive Learningcited by 2
  4. 2024Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classificationcited by 2
  5. 2024Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attackcited by 2
  6. 2025AugWard: Augmentation-Aware Representation Learning for Accurate Graph Classificationcited by 2
  7. 2025Principled Data Augmentation for Learning to Solve Quadratic Programming Problemscited by 2
  8. 2023Self-supervision meets kernel graph neural models: From architecture to augmentationscited by 1
  9. 2024Graph Contrastive Learning with Low-Rank Regularization and Low-Rank Attention for Noisy Node Classificationcited by 1
  10. 2024Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learningcited by 1
  11. 2024Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphscited by 1
  12. 2024Exploring Consistency in Graph Representations:from Graph Kernels to Graph Neural Networkscited by 1
  13. 2024Graph Community Augmentation with GMM-based Modeling in Latent Spacecited by 1
  14. 2024Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Modelcited by 1
  15. 2025Graph Self-Supervised Learning with Learnable Structural and Positional Encodingscited by 1
  16. 2023Robust Graph Contrastive Learning with Information Restorationcited by 0
  17. 2023Hodge-Aware Contrastive Learningcited by 0
  18. 2023Balancing Augmentation with Edge-Utility Filter for Signed GNNscited by 0
  19. 2023Uncertainty in Graph Contrastive Learning with Bayesian Neural Networkscited by 0
  20. 2024Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentationcited by 0
  21. 2024Heterogeneous Graph Contrastive Learning with Spectral Augmentationcited by 0
  22. 2024Enhancing Graph Self-Supervised Learning with Graph Interplaycited by 0
  23. 2024LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Spacecited by 0
  24. 2025Negative Metric Learning for Graphscited by 0
  25. 2026When Vision Meets Graphs: A Survey on Graph Reasoning and Learningcited by 0
  26. 2026Moment-guided edge samplingcited by 0