Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 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

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection (2312.14535v1)

Published 22 Dec 2023 in cs.LG, cs.AI, and cs.SI

Abstract: Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the \textit{Anomaly Overfitting} and \textit{Homophily Trap} problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate \textit{Anomaly Overfitting}. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Fraud detection system: A survey. Journal of Network and Computer Applications, 68: 90–113.
  2. Outlier Resistant Unsupervised Deep Architectures for Attributed Network Embedding. In Proceedings of the 13th International Conference on Web Search and Data Mining.
  3. Autoencoders. CoRR, abs/2003.05991.
  4. Bradley, A. P. 1997. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern recognition, 30(7): 1145–1159.
  5. Generative Adversarial Attributed Network Anomaly Detection. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management.
  6. Graph neural network for fraud detection via spatial-temporal attention. IEEE Transactions on Knowledge and Data Engineering, 34(8): 3800–3813.
  7. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, 29.
  8. Inductive anomaly detection on attributed networks. In Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence, 1288–1294.
  9. Deep Anomaly Detection on Attributed Networks, 594–602.
  10. Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 315–324.
  11. Graph anomaly detection via multi-scale contrastive learning networks with augmented view. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, 7459–7467.
  12. Anomalydae: Dual Autoencoder for Anomaly Detection on Attributed Networks. International Conference on Acoustics, Speech, and Signal Processing.
  13. Addressing heterophily in graph anomaly detection: A perspective of graph spectrum. In Proceedings of the ACM Web Conference 2023, 1528–1538.
  14. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric environment, 32(14-15): 2627–2636.
  15. Generative Adversarial Nets. Journal of Japan Society for Fuzzy Theory and Intelligent Informatics, 177–177.
  16. Graph neural network: Current state of Art, challenges and applications. Materials Today: Proceedings, 46: 10927–10932.
  17. Inductive representation learning on large graphs. Advances in neural information processing systems, 30.
  18. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16000–16009.
  19. Graphmae: Self-supervised masked graph autoencoders. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 594–604.
  20. Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method. In 2023 IEEE 39th International Conference on Data Engineering, 2565–2578. IEEE.
  21. Self-supervised learning on graphs: Deep insights and new direction. arXiv preprint arXiv:2006.10141.
  22. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  23. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308.
  24. Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
  25. Augmentation-free self-supervised learning on graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 7372–7380.
  26. Radar: residual analysis for anomaly detection in attributed networks. International Joint Conference on Artificial Intelligence.
  27. SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management.
  28. PyGOD: A Python Library for Graph Outlier Detection. arXiv preprint arXiv:2204.12095.
  29. Bond: Benchmarking unsupervised outlier node detection on static attributed graphs. Advances in Neural Information Processing Systems, 35: 27021–27035.
  30. Graph self-supervised learning: A survey. IEEE Transactions on Knowledge and Data Engineering.
  31. Anomaly detection on attributed networks via contrastive self-supervised learning. IEEE transactions on neural networks and learning systems, 33(6): 2378–2392.
  32. A comprehensive survey on graph anomaly detection with deep learning. IEEE Transactions on Knowledge and Data Engineering.
  33. Graph-based neural network models with multiple self-supervised auxiliary tasks. Pattern Recognition Letters, 148: 15–21.
  34. Ranking outlier nodes in subspaces of attributed graphs. International Conference on Data Engineering.
  35. Self-supervised graph representation learning via global context prediction. arXiv preprint arXiv:2003.01604.
  36. ANOMALOUS: A Joint Modeling Approach for Anomaly Detection on Attributed Networks. International Joint Conference on Artificial Intelligence.
  37. Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the MLSDA 2014 2nd workshop on machine learning for sensory data analysis, 4–11.
  38. Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction. In Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis.
  39. Collective classification in network data. AI magazine, 29(3): 93–93.
  40. Pitfalls of Graph Neural Network Evaluation.
  41. Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. arXiv preprint arXiv:1908.01000.
  42. Statistical Selection of Congruent Subspaces for Mining Attributed Graphs. International Conference on Data Mining.
  43. Rethinking graph neural networks for anomaly detection. In International Conference on Machine Learning, 21076–21089. PMLR.
  44. Graph attention networks. arXiv preprint arXiv:1710.10903.
  45. Graph attention networks. stat, 1050(20): 10–48550.
  46. Graph neural networks: Methods, applications, and opportunities. arXiv preprint arXiv:2108.10733.
  47. One-class graph neural networks for anomaly detection in attributed networks. Neural computing and applications, 33: 12073–12085.
  48. A new perspective on” how graph neural networks go beyond weisfeiler-lehman?”. In International Conference on Learning Representations.
  49. Self-supervised learning on graphs: Contrastive, generative, or predictive. IEEE Transactions on Knowledge and Data Engineering.
  50. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826.
  51. SCAN. Knowledge Discovery and Data Mining.
  52. Contrastive attributed network anomaly detection with data augmentation. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, 444–457. Springer.
  53. Graph Contrastive Learning with Augmentations. In Larochelle, H.; Ranzato, M.; Hadsell, R.; Balcan, M. F.; and Lin, H., eds., Advances in Neural Information Processing Systems, volume 33, 5812–5823. Curran Associates, Inc.
  54. Contrastive self-supervised learning for graph classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 10824–10832.
  55. Error-Bounded Graph Anomaly Loss for GNNs. Conference on Information and Knowledge Management.
  56. Graph neural networks: A review of methods and applications. AI open, 1: 57–81.
  57. Interpreting and unifying graph neural networks with an optimization framework. In Proceedings of the Web Conference 2021, 1215–1226.
  58. Self-supervised training of graph convolutional networks. arXiv preprint arXiv:2006.02380.
  59. A survey on graph structure learning: Progress and opportunities. arXiv preprint arXiv:2103.03036.
  60. Graph contrastive learning with adaptive augmentation. In Proceedings of the Web Conference 2021, 2069–2080.
Citations (11)
View on Semantic Scholar

Summary

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

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