Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 88 tok/s
Gemini 2.5 Pro 52 tok/s Pro
GPT-5 Medium 12 tok/s Pro
GPT-5 High 19 tok/s Pro
GPT-4o 110 tok/s Pro
GPT OSS 120B 470 tok/s Pro
Kimi K2 197 tok/s Pro
2000 character limit reached

Self-Guided Robust Graph Structure Refinement (2402.11837v2)

Published 19 Feb 2024 in cs.LG

Abstract: Recent studies have revealed that GNNs are vulnerable to adversarial attacks. To defend against such attacks, robust graph structure refinement (GSR) methods aim at minimizing the effect of adversarial edges based on node features, graph structure, or external information. However, we have discovered that existing GSR methods are limited by narrowassumptions, such as assuming clean node features, moderate structural attacks, and the availability of external clean graphs, resulting in the restricted applicability in real-world scenarios. In this paper, we propose a self-guided GSR framework (SG-GSR), which utilizes a clean sub-graph found within the given attacked graph itself. Furthermore, we propose a novel graph augmentation and a group-training strategy to handle the two technical challenges in the clean sub-graph extraction: 1) loss of structural information, and 2) imbalanced node degree distribution. Extensive experiments demonstrate the effectiveness of SG-GSR under various scenarios including non-targeted attacks, targeted attacks, feature attacks, e-commerce fraud, and noisy node labels. Our code is available at https://github.com/yeonjun-in/torch-SG-GSR.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Louis Abraham. 2020. fastnode2vec. https://doi.org/10.5281/zenodo.3902632
  2. Lada A Adamic and Eytan Adar. 2003. Friends and neighbors on the web. Social networks 25, 3 (2003), 211–230.
  3. Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 283–292.
  4. Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels. WSDM (2022).
  5. All you need is low (rank) defending against adversarial attacks on graphs. In Proceedings of the 13th International Conference on Web Search and Data Mining. 169–177.
  6. SLAPS: Self-supervision improves structure learning for graph neural networks. Advances in Neural Information Processing Systems 34 (2021), 22667–22681.
  7. 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.
  8. Ruining He and Julian McAuley. 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceedings of the 25th international conference on world wide web. 507–517.
  9. Similarity Preserving Adversarial Graph Contrastive Learning. arXiv preprint arXiv:2306.13854 (2023).
  10. Universal graph convolutional networks. Advances in Neural Information Processing Systems 34 (2021), 10654–10664.
  11. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 66–74.
  12. Dongkwan Kim and Alice Oh. 2022. How to find your friendly neighborhood: Graph attention design with self-supervision. arXiv preprint arXiv:2204.04879 (2022).
  13. Class Label-aware Graph Anomaly Detection. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 4008–4012.
  14. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
  15. Robust optimization as data augmentation for large-scale graphs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 60–69.
  16. Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks. arXiv preprint arXiv:2205.13892 (2022).
  17. Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 925–935.
  18. Attributed social network embedding. IEEE Transactions on Knowledge and Data Engineering 30, 12 (2018), 2257–2270.
  19. David Liben-Nowell and Jon Kleinberg. 2003. The link prediction problem for social networks. In Proceedings of the twelfth international conference on Information and knowledge management. 556–559.
  20. Compact Graph Structure Learning via Mutual Information Compression. In Proceedings of the ACM Web Conference 2022. 1601–1610.
  21. Local augmentation for graph neural networks. In International Conference on Machine Learning. PMLR, 14054–14072.
  22. Graph neural networks with adaptive residual. Advances in Neural Information Processing Systems 34 (2021), 9720–9733.
  23. Elastic graph neural networks. In International Conference on Machine Learning. PMLR, 6837–6849.
  24. Tail-gnn: Tail-node graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1109–1119.
  25. Towards locality-aware meta-learning of tail node embeddings on networks. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 975–984.
  26. Image-based recommendations on styles and substitutes. In Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval. 43–52.
  27. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018).
  28. Towards an optimal asymmetric graph structure for robust semi-supervised node classification. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1656–1665.
  29. Transferring Robustness for Graph Neural Network Against Poisoning Attacks. In Proceedings of the 13th International Conference on Web Search and Data Mining. ACM. https://doi.org/10.1145/3336191.3371851
  30. Attention is all you need. Advances in neural information processing systems 30 (2017).
  31. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
  32. Structural deep network embedding. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. 1225–1234.
  33. Graph structure estimation neural networks. In Proceedings of the Web Conference 2021. 342–353.
  34. Neural graph collaborative filtering. In Proceedings of the 42nd international ACM SIGIR conference on Research and development in Information Retrieval. 165–174.
  35. Am-gcn: Adaptive multi-channel graph convolutional networks. In Proceedings of the 26th ACM SIGKDD International conference on knowledge discovery & data mining. 1243–1253.
  36. Handling distribution shifts on graphs: An invariance perspective. arXiv preprint arXiv:2202.02466 (2022).
  37. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16. Springer, 247–263.
  38. Graph convolutional networks for text classification. In Proceedings of the AAAI conference on artificial intelligence, Vol. 33. 7370–7377.
  39. LTE4G: Long-Tail Experts for Graph Neural Networks. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2434–2443.
  40. Graph Data Augmentation for Graph Machine Learning: A Survey. arXiv preprint arXiv:2202.08871 (2022).
  41. Data augmentation for graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 11015–11023.
  42. Scalable graph embedding for asymmetric proximity. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31.
  43. Robust graph convolutional networks against adversarial attacks. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 1399–1407.
  44. SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization. arXiv preprint arXiv:2303.09778 (2023).
  45. Adversarial Attacks on Neural Networks for Graph Data. In SIGKDD. 2847–2856.
  46. Daniel Zügner and Stephan Günnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. In International Conference on Learning Representations (ICLR).
Citations (3)
View on Semantic Scholar
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Ai Generate Text Spark Streamline Icon: https://streamlinehq.com

Paper Prompts

Sign up for free to create and run prompts on this paper using GPT-5.

List Streamline Icon: https://streamlinehq.com Explore 10 Community Prompts
Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now