mlsanityData to 13 Oct 2026

Robust Graph Contrastive Learning with Information Restoration

arXiv 2307.12555 ↗First posted 24 Jul 2023cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

The graph contrastive learning (GCL) framework has gained remarkable achievements in graph representation learning. However, similar to graph neural networks (GNNs), GCL models are susceptible to graph structural attacks. As an unsupervised method, GCL faces greater challenges in defending against adversarial attacks. Furthermore, there has been limited research on enhancing the robustness of GCL. To thoroughly explore the failure of GCL on the poisoned graphs, we investigate the detrimental effects of graph structural attacks against the GCL framework. We discover that, in addition to the conventional observation that graph structural attacks tend to connect dissimilar node pairs, these attacks also diminish the mutual information between the graph and its representations from an information-theoretical perspective, which is the cornerstone of the high-quality node embeddings for GCL. Motivated by this theoretical insight, we propose a robust graph contrastive learning framework with a learnable sanitation view that endeavors to sanitize the augmented graphs by restoring the diminished mutual information caused by the structural attacks. Additionally, we design a fully unsupervised tuning strategy to tune the hyperparameters without accessing the label information, which strictly coincides with the defender's knowledge. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method compared to competitive baselines.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 40 of its 61 references that are in the map. First posted on arXiv 24 Jul 2023.

Builds on

40 of 61 references.

References · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
  5. 2017Inductive Representation Learning on Large Graphscited by 6,303
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,726
  7. 2021Convex optimizationcited by 2,488
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,915
  9. 2014DeepWalk: Online Learning of Social Representationscited by 1,544
  10. 2018Deep Graph Infomaxcited by 1,104
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,003
  12. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 973
28 more
  1. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  2. 2020Deep Graph Contrastive Representation Learningcited by 537
  3. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  4. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 396
  5. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  6. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  7. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 257
  8. 2019Understanding Straight-Through Estimator in Training Activation Quantized Neural Netscited by 228
  9. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  10. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  11. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 185
  12. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  13. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  14. 2021AutoGCL: Automated Graph Contrastive Learning via Learnable View Generatorscited by 73
  15. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 39
  16. 2022Adversarial Graph Contrastive Learning with Information Regularizationcited by 38
  17. 2022Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagationcited by 25
  18. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  19. 2021Graph Sanitation with Application to Node Classificationcited by 20
  20. 2020Unsupervised Adversarially-Robust Representation Learning on Graphscited by 17
  21. 2021Mask-GVAE: Blind Denoising Graphs via Partitioncited by 9
  22. 2021BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detectioncited by 9
  23. 2022FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classificationcited by 7
  24. 2023Similarity Preserving Adversarial Graph Contrastive Learningcited by 6
  25. 2014Sparsity-Aware Sensor Collaboration for Linear Coherent Estimationcited by 3
  26. 2022Towards Adversarially Robust Recommendation from Adaptive Fraudster Detectioncited by 3
  27. 2022From Bi-Level to One-Level: A Framework for Structural Attacks to Graph Anomaly Detectioncited by 2
  28. 2022Towards Secrecy-Aware Attacks Against Trust Prediction in Signed Social Networkscited by 1

Built on by

Not cited yet.