Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Similarity Preserving Adversarial Graph Contrastive Learning (2306.13854v1)

Published 24 Jun 2023 in cs.LG, cs.AI, and cs.CR

Abstract: Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features. Among various GNN models, graph contrastive learning (GCL) based methods specifically suffer from adversarial attacks due to their inherent design that highly depends on the self-supervision signals derived from the original graph, which however already contains noise when the graph is attacked. To achieve adversarial robustness against such attacks, existing methods adopt adversarial training (AT) to the GCL framework, which considers the attacked graph as an augmentation under the GCL framework. However, we find that existing adversarially trained GCL methods achieve robustness at the expense of not being able to preserve the node feature similarity. In this paper, we propose a similarity-preserving adversarial graph contrastive learning (SP-AGCL) framework that contrasts the clean graph with two auxiliary views of different properties (i.e., the node similarity-preserving view and the adversarial view). Extensive experiments demonstrate that SP-AGCL achieves a competitive performance on several downstream tasks, and shows its effectiveness in various scenarios, e.g., a network with adversarial attacks, noisy labels, and heterophilous neighbors. Our code is available at https://github.com/yeonjun-in/torch-SP-AGCL.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Aleksandar Bojchevski and Stephan Günnemann. 2019. Adversarial Attacks on Node Embeddings via Graph Poisoning. In Proceedings of the 36th International Conference on Machine Learning.
  2. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning.
  3. Iterative deep graph learning for graph neural networks: Better and robust node embeddings. Advances in Neural Information Processing Systems 33 (2020), 19314–19326.
  4. Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 227–236.
  5. Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels. arXiv preprint arXiv:2201.00232 (2022).
  6. Adversarial Attack on Graph Structured Data. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research). PMLR.
  7. Adversarial graph contrastive learning with information regularization. In Proceedings of the ACM Web Conference 2022. 1362–1371.
  8. Graph Random Neural Networks for Semi-Supervised Learning on Graphs. In Advances in Neural Information Processing Systems.
  9. Reliable Graph Neural Networks via Robust Aggregation. In Advances in Neural Information Processing Systems.
  10. Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 855–864.
  11. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).
  12. Kaveh Hassani and Amir Hosein Khasahmadi. 2020. Contrastive Multi-View Representation Learning on Graphs. In Proceedings of International Conference on Machine Learning. 3451–3461.
  13. Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018).
  14. Node similarity preserving graph convolutional networks. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. 148–156.
  15. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 66–74.
  16. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of the 5th International Conference on Learning Representations (Palais des Congrès Neptune, Toulon, France) (ICLR ’17).
  17. Relational self-supervised learning on graphs. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 1054–1063.
  18. Augmentation-free self-supervised learning on graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 7372–7380.
  19. Deeprobust: A pytorch library for adversarial attacks and defenses. arXiv preprint arXiv:2005.06149 (2020).
  20. Unsupervised differentiable multi-aspect network embedding. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1435–1445.
  21. Geom-gcn: Geometric graph convolutional networks. arXiv preprint arXiv:2002.05287 (2020).
  22. DeepWalk. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM. https://doi.org/10.1145/2623330.2623732
  23. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018).
  24. Adversarial attack and defense on graph data: A survey. arXiv preprint arXiv:1812.10528 (2018).
  25. Line: Large-scale information network embedding. In Proceedings of the 24th international conference on world wide web. 1067–1077.
  26. Transferring robustness for graph neural network against poisoning attacks. In Proceedings of the 13th international conference on web search and data mining. 600–608.
  27. Large-scale representation learning on graphs via bootstrapping. In International Conference on Learning Representations.
  28. Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).
  29. Deep graph infomax. arXiv preprint arXiv:1809.10341 (2018).
  30. Am-gcn: Adaptive multi-channel graph convolutional networks. In Proceedings of the 26th ACM SIGKDD International conference on knowledge discovery & data mining. 1243–1253.
  31. Unsupervised adversarially-robust representation learning on graphs. In Proceedings of the AAAI Conference on Artificial Intelligence.
  32. Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19).
  33. Semi-Supervised and Self-Supervised Classification with Multi-View Graph Neural Networks. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 2466–2476.
  34. Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. Advances in neural information processing systems 31 (2018).
  35. Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation. arXiv preprint arXiv:2201.07986 (2022).
  36. Robust Graph Convolutional Networks Against Adversarial Attacks. (2019).
  37. Graph Neural Networks with Heterophily. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 11168–11176.
  38. Deep graph contrastive representation learning. arXiv preprint arXiv:2006.04131 (2020).
  39. Graph contrastive learning with adaptive augmentation. In Proceedings of the Web Conference 2021. 2069–2080.
  40. Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2847–2856.
  41. Daniel Zügner and Stephan Günnemann. 2019. Adversarial attacks on graph neural networks via meta learning. arXiv preprint arXiv:1902.08412 (2019).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Yeonjun In (17 papers)
  2. Kanghoon Yoon (16 papers)
  3. Chanyoung Park (83 papers)
Citations (4)
View on Semantic Scholar