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

Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection (2403.10339v1)

Published 15 Mar 2024 in cs.LG

Abstract: Graph-based anomaly detection is currently an important research topic in the field of graph neural networks (GNNs). We find that in graph anomaly detection, the homophily distribution differences between different classes are significantly greater than those in homophilic and heterophilic graphs. For the first time, we introduce a new metric called Class Homophily Variance, which quantitatively describes this phenomenon. To mitigate its impact, we propose a novel GNN model named Homophily Edge Generation Graph Neural Network (HedGe). Previous works typically focused on pruning, selecting or connecting on original relationships, and we refer to these methods as modifications. Different from these works, our method emphasizes generating new relationships with low class homophily variance, using the original relationships as an auxiliary. HedGe samples homophily adjacency matrices from scratch using a self-attention mechanism, and leverages nodes that are relevant in the feature space but not directly connected in the original graph. Additionally, we modify the loss function to punish the generation of unnecessary heterophilic edges by the model. Extensive comparison experiments demonstrate that HedGe achieved the best performance across multiple benchmark datasets, including anomaly detection and edgeless node classification. The proposed model also improves the robustness under the novel Heterophily Attack with increased class homophily variance on other graph classification tasks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In International Conference on Machine Learning. PMLR, 21–29.
  2. Beyond low-frequency information in graph convolutional networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 3950–3957.
  3. A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory. 144–152.
  4. Leo Breiman. 2001. Random forests. Machine Learning 45 (2001), 5–32.
  5. Can abnormality be detected by graph neural networks. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. 23–29.
  6. Anomaly detection: A survey. Comput. Surveys 41, 3 (2009), 1–58.
  7. Interaction-aware graph neural networks for fault diagnosis of complex industrial processes. IEEE Transactions on Neural Networks and Learning Systems (2021).
  8. Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 785–794.
  9. Efficient top-k vulnerable nodes detection in uncertain graphs. IEEE Transactions on Knowledge and Data Engineering 35, 2 (2021), 1460–1472.
  10. Risk guarantee prediction in networked-loans. In IJCAI International Joint Conference on Artificial Intelligence.
  11. Anti-Money laundering by group-Aware deep graph learning. IEEE Transactions on Knowledge and Data Engineering (2023).
  12. Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 257–266.
  13. Adaptive universal generalized pageRank graph neural network. In International Conference on Learning Representations.
  14. Thomas Cover and Peter Hart. 1967. Nearest neighbor pattern classification. IEEE Transactions on Information Theory 13, 1 (1967), 21–27.
  15. Ailin Deng and Bryan Hooi. 2021. Graph neural network-based anomaly detection in multivariate time series. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4027–4035.
  16. Contextual stochastic block models. Advances in Neural Information Processing Systems 31 (2018).
  17. Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 315–324.
  18. Addressing heterophily in graph anomaly detection: A perspective of graph spectrum. In Proceedings of the Web Conference. 1528–1538.
  19. Alleviating structural distribution shift in graph anomaly detection. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. 357–365.
  20. Beyond homophily: robust graph anomaly detection via neural sparsification. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. 2104–2113.
  21. Inductive representation learning on large graphs. Advances in Neural Information Processing Systems 30 (2017).
  22. Auc-oriented graph neural network for fraud detection. In Proceedings of the ACM Web Conference. 1311–1321.
  23. Categorical reparameterization with Gumbel-Softmax. In International Conference on Learning Representations.
  24. Universal graph convolutional networks. Advances in Neural Information Processing Systems 34 (2021), 10654–10664.
  25. Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems 30 (2017).
  26. Diederik P Kingma and Max Welling. 2014. Auto-Encoding variational bayes. In International Conference on Learning Representations.
  27. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
  28. Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement. In International Conference on Machine Learning. PMLR, 3499–3508.
  29. Predicting dynamic embedding trajectory in temporal interaction networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1269–1278.
  30. Classifying relations in clinical narratives using segment graph convolutional and recurrent neural networks (Seg-GCRNs). Journal of the American Medical Informatics Association 26, 3 (2019), 262–268.
  31. BA-GNN: Behavior-aware graph neural network for session-based recommendation. Frontiers of Computer Science 17, 6 (2023), 176613.
  32. Pygod: A python library for graph outlier detection. arXiv preprint arXiv:2204.12095 (2022).
  33. Non-local graph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 12 (2021), 10270–10276.
  34. Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 39, 2 (2008), 539–550.
  35. Pick and choose: a GNN-based imbalanced learning approach for fraud detection. In Proceedings of the Web Conference. 3168–3177.
  36. Anomaly detection on attributed networks via contrastive self-supervised learning. IEEE Transactions on Neural Networks and Learning Systems 33, 6 (2021), 2378–2392.
  37. When do graph neural networks help with node classification: Investigating the homophily principle on node distinguishability. arXiv preprint arXiv:2304.14274 (2023).
  38. A comprehensive survey on graph anomaly detection with deep learning. IEEE Transactions on Knowledge and Data Engineering (2021).
  39. Is Homophily a Necessity for Graph Neural Networks?. In International Conference on Learning Representations.
  40. Julian John McAuley and Jure Leskovec. 2013. From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. In Proceedings of the 22nd International Conference on World Wide Web. 897–908.
  41. Birds of a feather: Homophily in social networks. Annual Review of Sociology 27, 1 (2001), 415–444.
  42. iconviz: Interactive visual exploration of the default contagion risk of networked-guarantee loans. In 2020 IEEE conference on visual analytics science and technology (VAST). IEEE, 84–94.
  43. Geom-GCN: Geometric graph convolutional networks. In International Conference on Learning Representations.
  44. CatBoost: unbiased boosting with categorical features. Advances in Neural Information Processing Systems 31 (2018).
  45. Shebuti Rayana and Leman Akoglu. 2015. Collective opinion spam detection: Bridging review networks and metadata. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 985–994.
  46. Frank Rosenblatt. 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review 65, 6 (1958), 386.
  47. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018).
  48. H2-fdetector: A gnn-based fraud detector with homophilic and heterophilic connections. In Proceedings of the Web Conference. 1486–1494.
  49. Breaking the limit of graph neural networks by improving the assortativity of graphs with local mixing patterns. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1541–1551.
  50. Rethinking graph neural networks for anomaly detection. In International Conference on Machine Learning. PMLR, 21076–21089.
  51. Lei Tang and Huan Liu. 2009. Relational learning via latent social dimensions. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 817–826.
  52. Anomaly detection for cybersecurity of the substations. IEEE Transactions on Smart Grid 2, 4 (2011), 865–873.
  53. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017).
  54. Graph attention networks. In International Conference on Learning Representations.
  55. Extending the nested model for user-centric XAI: A design study on GNN-based drug repurposing. IEEE Transactions on Visualization and Computer Graphics 29, 1 (2022), 1266–1276.
  56. Powerful graph convolutional networks with adaptive propagation mechanism for homophily and heterophily. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 4210–4218.
  57. Yu Wang and Tyler Derr. 2021. Tree decomposed graph neural network. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management. 2040–2049.
  58. Jiaying Wu and Bryan Hooi. 2023. DECOR: Degree-Corrected social graph refinement for fake news detection. In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2582–2593.
  59. Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks. In 2022 IEEE International Conference on Data Mining. IEEE, 1287–1292.
  60. Mining fraudsters and fraudulent strategies in large-scale mobile social networks. IEEE Transactions on Knowledge and Data Engineering 33, 1 (2019), 169–179.
  61. Revisiting semi-supervised learning with graph embeddings. In International Conference on Machine Learning. PMLR, 40–48.
  62. Error-bounded graph anomaly loss for GNNs. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 1873–1882.
  63. A synergistic approach for graph anomaly detection with pattern mining and feature learning. IEEE Transactions on Neural Networks and Learning Systems 33, 6 (2021), 2393–2405.
  64. Graph neural networks for graphs with heterophily: A survey. arXiv preprint arXiv:2202.07082 (2022).
  65. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in Neural Information Processing Systems 33 (2020), 7793–7804.
  66. Daniel Zügner and Stephan Günnemann. 2019. Adversarial attacks on graph neural networks via meta learning. In International Conference on Learning Representations.
Citations (1)
View on Semantic Scholar

Summary

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets