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

Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation (2306.10534v1)

Published 18 Jun 2023 in cs.LG and cs.AI

Abstract: Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage the available labels as prior knowledge, have achieved superior performances than unsupervised methods. In practice, people usually need to identify anomalies on new (sub)graphs to secure their business, but they may lack labels to train an effective detection model. One natural idea is to directly adopt a trained GAD model to the new (sub)graph for testing. However, we find that existing semi-supervised GAD methods suffer from poor generalization issue, i.e., well-trained models could not perform well on an unseen area (i.e., not accessible in training) of the same graph. It may cause great troubles. In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers. Nevertheless, it is a challenging task since only limited labels are available, and the normal background may differ between training and testing data. Accordingly, we propose a data augmentation method named \textit{AugAN} (\uline{Aug}mentation for \uline{A}nomaly and \uline{N}ormal distributions) to enrich training data and boost the generalizability of GAD models. Experiments verify the effectiveness of our method in improving model generalizability.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (74)
  1. L. Akoglu, H. Tong, and D. Koutra, “Graph based anomaly detection and description: a survey,” Data mining and knowledge discovery, vol. 29, no. 3, pp. 626–688, 2015.
  2. X. Ma, J. Wu, S. Xue, J. Yang, C. Zhou, Q. Z. Sheng, H. Xiong, and L. Akoglu, “A comprehensive survey on graph anomaly detection with deep learning,” IEEE Transactions on Knowledge and Data Engineering, 2021.
  3. Deep representation learning for social network analysis. Frontiers in big Data, 2:2, 2019.
  4. D. Wang, J. Lin, P. Cui, Q. Jia, Z. Wang, Y. Fang, Q. Yu, J. Zhou, S. Yang, and Y. Qi, “A semi-supervised graph attentive network for financial fraud detection,” in ICDM, 2019.
  5. B. Chen, J. Zhang, X. Zhang, Y. Dong, J. Song, P. Zhang, K. Xu, E. Kharlamov, and J. Tang, “Gccad: Graph contrastive learning for anomaly detection,” IEEE Transactions on Knowledge and Data Engineering, 2022.
  6. F. T. Liu, K. M. Ting, and Z.-H. Zhou, “On detecting clustered anomalies using sciforest,” in ECML-KDD.   Springer, 2010, pp. 274–290.
  7. G. Pang, C. Shen, L. Cao, and A. V. D. Hengel, “Deep learning for anomaly detection: A review,” ACM Computing Surveys (CSUR), vol. 54, no. 2, pp. 1–38, 2021.
  8. H. Xu, Y. Wang, Y. Wang, and Z. Wu, “Mix: a joint learning framework for detecting both clustered and scattered outliers in mixed-type data,” in ICDM, 2019.
  9. D. Zhou, J. He, H. Yang, and W. Fan, “Sparc: Self-paced network representation for few-shot rare category characterization,” in KDD, 2018.
  10. J. Gao, F. Liang, W. Fan, C. Wang, Y. Sun, and J. Han, “On community outliers and their efficient detection in information networks,” in KDD, 2010, pp. 813–822.
  11. L. Gutiérrez-Gómez, A. Bovet, and J.-C. Delvenne, “Multi-scale anomaly detection on attributed networks,” in AAAI, vol. 34, no. 01, 2020, pp. 678–685.
  12. P. I. Sánchez, E. Müller, O. Irmler, and K. Böhm, “Local context selection for outlier ranking in graphs with multiple numeric node attributes,” in SSDBM, 2014, pp. 1–12.
  13. B. Perozzi, L. Akoglu, P. Iglesias Sánchez, and E. Müller, “Focused clustering and outlier detection in large attributed graphs,” in KDD, 2014, pp. 1346–1355.
  14. J. Li, H. Dani, X. Hu, and H. Liu, “Radar: Residual analysis for anomaly detection in attributed networks.” in IJCAI, 2017, pp. 2152–2158.
  15. Z. Peng, M. Luo, J. Li, H. Liu, and Q. Zheng, “Anomalous: A joint modeling approach for anomaly detection on attributed networks.” in IJCAI, 2018, pp. 3513–3519.
  16. Z. Peng, M. Luo, J. Li, L. Xue, and Q. Zheng, “A deep multi-view framework for anomaly detection on attributed networks,” IEEE Transactions on Knowledge and Data Engineering, 2020.
  17. L. Huang, Y. Zhu, Y. Gao, T. Liu, C. Chang, C. Liu, Y. Tang, and C.-D. Wang, “Hybrid-order anomaly detection on attributed networks,” IEEE Transactions on Knowledge and Data Engineering, 2021.
  18. S. Bandyopadhyay, S. V. Vivek, and M. Murty, “Outlier resistant unsupervised deep architectures for attributed network embedding,” in WSDM, 2020, pp. 25–33.
  19. M. Jin, Y. Liu, Y. Zheng, L. Chi, Y.-F. Li, and S. Pan, “Anemone: graph anomaly detection with multi-scale contrastive learning,” in CIKM, 2021, pp. 3122–3126.
  20. K. Liu, Y. Dou, Y. Zhao, X. Ding, X. Hu, R. Zhang, K. Ding, C. Chen, H. Peng, K. Shu et al., “Bond: Benchmarking unsupervised outlier node detection on static attributed graphs,” in NeurIPS, 2022.
  21. S. Han, X. Hu, H. Huang, M. Jiang, and Y. Zhao, “Adbench: Anomaly detection benchmark,” in NeurIPS, 2022.
  22. K. Ding, Q. Zhou, H. Tong, and H. Liu, “Few-shot network anomaly detection via cross-network meta-learning,” in WWW, 2021.
  23. Q. Guo, X. Zhao, Y. Fang, S. Yang, X. Lin, and D. Ouyang, “Learning hypersphere for few-shot anomaly detection on attributed networks,” in CIKM, 2022, pp. 635–645.
  24. J. Tang, J. Li, Z. Gao, and J. Li, “Rethinking graph neural networks for anomaly detection,” in ICML, 2022.
  25. J. Wang, C. Lan, C. Liu, Y. Ouyang, T. Qin, W. Lu, Y. Chen, W. Zeng, and P. Yu, “Generalizing to unseen domains: A survey on domain generalization,” IEEE Transactions on Knowledge and Data Engineering, 2022.
  26. K. Ding, Z. Xu, H. Tong, and H. Liu, “Data augmentation for deep graph learning: A survey,” ACM SIGKDD Explorations Newsletter, vol. 24, no. 2, pp. 61–77, 2022.
  27. S. Yu, H. Huang, M. N. Dao, and F. Xia, “Graph augmentation learning,” in WWW, 2022, pp. 1063–1072.
  28. Y. Wang, W. Wang, Y. Liang, Y. Cai, J. Liu, and B. Hooi, “Nodeaug: Semi-supervised node classification with data augmentation,” in KDD, 2020, pp. 207–217.
  29. J. Park, J. Song, and E. Yang, “Graphens: Neighbor-aware ego network synthesis for class-imbalanced node classification,” in ICLR, 2021.
  30. T. Zhao, X. Zhang, and S. Wang, “Graphsmote: Imbalanced node classification on graphs with graph neural networks,” in WSDM, 2021.
  31. L. Wu, J. Xia, Z. Gao, H. Lin, C. Tan, and S. Z. Li, “Graphmixup: Improving class-imbalanced node classification by reinforcement mixup and self-supervised context prediction,” in ECML-PKDD, 2022.
  32. Q. Liu, Q. Dou, and P.-A. Heng, “Shape-aware meta-learning for generalizing prostate mri segmentation to unseen domains,” in MICCAI.   Springer, 2020, pp. 475–485.
  33. C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” in ICML, 2017.
  34. J. McAuley, R. Pandey, and J. Leskovec, “Inferring networks of substitutable and complementary products,” in KDD, 2015.
  35. J. McAuley, C. Targett, Q. Shi, and A. Van Den Hengel, “Image-based recommendations on styles and substitutes,” in SIGIR, 2015.
  36. J. Tang, J. Zhang, L. Yao, J. Li, L. Zhang, and Z. Su, “Arnetminer: extraction and mining of academic social networks,” in KDD, 2008.
  37. A. Sinha, Z. Shen, Y. Song, H. Ma, D. Eide, B.-J. Hsu, and K. Wang, “An overview of microsoft academic service (mas) and applications,” in WWW, 2015.
  38. X. Wang, B. Jin, Y. Du, P. Cui, Y. Tan, and Y. Yang, “One-class graph neural networks for anomaly detection in attributed networks,” Neural Computing and Applications, pp. 1–13, 2021.
  39. S. Zhou, X. Huang, N. Liu, Q. Tan, and F.-L. Chung, “Unseen anomaly detection on networks via multi-hypersphere learning,” in SDM, 2022.
  40. Z. Xu, H. He, G.-H. Lee, Y. Wang, and H. Wang, “Graph-relational domain adaptation,” in ICLR, 2022.
  41. K. Ding, J. Li, R. Bhanushali, and H. Liu, “Deep anomaly detection on attributed networks,” in SDM, 2019.
  42. Y. Liu, Z. Li, S. Pan, C. Gong, C. Zhou, and G. Karypis, “Anomaly detection on attributed networks via contrastive self-supervised learning,” IEEE Transactions on Neural Networks and Learning Systems, 2021.
  43. Y. Zheng, M. Jin, Y. Liu, L. Chi, K. T. Phan, and Y.-P. P. Chen, “Generative and contrastive self-supervised learning for graph anomaly detection,” IEEE Transactions on Knowledge and Data Engineering, 2021.
  44. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in ICLR, 2017.
  45. L. Ruff, R. A. Vandermeulen, N. Görnitz, A. Binder, E. Müller, K.-R. Müller, and M. Kloft, “Deep semi-supervised anomaly detection,” in ICLR, 2020.
  46. Y. Liu, X. Ao, Z. Qin, J. Chi, J. Feng, H. Yang, and Q. He, “Pick and choose: A gnn-based imbalanced learning approach for fraud detection,” in WWW, 2021, 2021, pp. 3168–3177.
  47. G. Pang, C. Shen, and A. van den Hengel, “Deep anomaly detection with deviation networks,” in KDD, 2019, pp. 353–362.
  48. K. Ding, K. Shu, X. Shan, J. Li, and H. Liu, “Cross-domain graph anomaly detection,” IEEE Transactions on Neural Networks and Learning Systems, 2021.
  49. Q. Wu, H. Zhang, J. Yan, and D. Wipf, “Handling distribution shifts on graphs: An invariance perspective,” in ICLR, 2022.
  50. Q. Dou, D. Coelho de Castro, K. Kamnitsas, and B. Glocker, “Domain generalization via model-agnostic learning of semantic features,” in NeurIPS, 2019.
  51. Z. Yang, M. Ding, X. Zou, J. Tang, B. Xu, C. Zhou, and H. Yang, “Region or global a principle for negative sampling in graph-based recommendation,” IEEE Transactions on Knowledge and Data Engineering, 2022.
  52. X. Guo, X. Liu, E. Zhu, X. Zhu, M. Li, X. Xu, and J. Yin, “Adaptive self-paced deep clustering with data augmentation,” IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 9, pp. 1680–1693, 2019.
  53. L. Van der Maaten and G. Hinton, “Visualizing data using t-sne.” Journal of machine learning research, vol. 9, no. 11, 2008.
  54. K. Zhou, Y. Yang, T. Hospedales, and T. Xiang, “Deep domain-adversarial image generation for domain generalisation,” in AAAI, vol. 34, no. 07, 2020, pp. 13 025–13 032.
  55. S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, and Y. Yoo, “Cutmix: Regularization strategy to train strong classifiers with localizable features,” in ICCV, 2019.
  56. H. Nam and H.-E. Kim, “Batch-instance normalization for adaptively style-invariant neural networks,” in NeurIPS, 2018.
  57. Y. Li, X. Tian, M. Gong, Y. Liu, T. Liu, K. Zhang, and D. Tao, “Deep domain generalization via conditional invariant adversarial networks,” in ECCV, 2018.
  58. K. Thopalli, S. Katoch, J. J. Thiagarajan, P. K. Turaga, and A. Spanias, “Multi-domain ensembles for domain generalization,” in NeurIPS, 2021.
  59. V. M. Patel, R. Gopalan, R. Li, and R. Chellappa, “Visual domain adaptation: A survey of recent advances,” IEEE signal processing magazine, vol. 32, no. 3, pp. 53–69, 2015.
  60. S. Li, S. Li, M. Xie, K. Gong, J. Zhao, C. H. Liu, and G. Wang, “End-to-end transferable anomaly detection via multi-spectral cross-domain representation alignment,” IEEE Transactions on Knowledge and Data Engineering, 2021.
  61. M. Mancini, Z. Akata, E. Ricci, and B. Caputo, “Towards recognizing unseen categories in unseen domains,” in ECCV, 2020.
  62. R. Volpi, H. Namkoong, O. Sener, J. C. Duchi, V. Murino, and S. Savarese, “Generalizing to unseen domains via adversarial data augmentation,” in NeurIPS, 2018.
  63. S. K. Lim, Y. Loo, N.-T. Tran, N.-M. Cheung, G. Roig, and Y. Elovici, “Doping: Generative data augmentation for unsupervised anomaly detection with gan,” in ICDM, 2018.
  64. T. Zhao, B. Ni, W. Yu, Z. Guo, N. Shah, and M. Jiang, “Action sequence augmentation for early graph-based anomaly detection,” in CIKM, 2021, pp. 2668–2678.
  65. A. R. Rivera, A. Khan, I. E. I. Bekkouch, and T. S. Sheikh, “Anomaly detection based on zero-shot outlier synthesis and hierarchical feature distillation,” IEEE Transactions on Neural Networks and Learning Systems, 2020.
  66. Z. Xu, X. Huang, Y. Zhao, Y. Dong, and J. Li, “Contrastive attributed network anomaly detection with data augmentation,” in PAKDD, 2022.
  67. F. Liu, X. Ma, J. Wu, J. Yang, S. Xue, A. Behesht, C. Zhou, H. Peng, Q. Z. Sheng, and C. C. Aggarwal, “Dagad: Data augmentation for graph anomaly detection,” in ICDM, 2022.
  68. J. Qiu, Q. Chen, Y. Dong, J. Zhang, H. Yang, M. Ding, K. Wang, and J. Tang, “Gcc: Graph contrastive coding for graph neural network pre-training,” in KDD, 2020, pp. 1150–1160.
  69. M. Shi, Y. Tang, X. Zhu, D. Wilson, and J. Liu, “Multi-class imbalanced graph convolutional network learning,” in IJCAI, 2020.
  70. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” Communications of the ACM, vol. 63, no. 11, pp. 139–144, 2020.
  71. T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey, “Meta-learning in neural networks: A survey,” IEEE transactions on pattern analysis and machine intelligence, vol. 44, no. 9, pp. 5149–5169, 2021.
  72. Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, “Generalizing from a few examples: A survey on few-shot learning,” ACM Computing Surveys (CSUR), vol. 53, no. 3, pp. 1–34, 2020.
  73. J. Snell, K. Swersky, and R. Zemel, “Prototypical networks for few-shot learning,” in NeurIPS, 2017.
  74. A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra, and T. Lillicrap, “Meta-learning with memory-augmented neural networks,” in ICML, 2016.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Shuang Zhou (65 papers)
  2. Xiao Huang (112 papers)
  3. Ninghao Liu (98 papers)
  4. Huachi Zhou (5 papers)
  5. Fu-Lai Chung (16 papers)
  6. Long-Kai Huang (14 papers)
Citations (17)
View on Semantic Scholar

Summary

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

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