Explainable Anomaly Detection
| Title | Explainable Anomaly Detection |
|---|---|
| Summary | Explainable anomaly detection in time series data utilising causal inference |
| Keywords | Explainable AI, time series anomaly detection |
| TimeFrame | VT24 |
| References | Li, Z., Zhu, Y., & Van Leeuwen, M. (2023). A survey on explainable anomaly detection. ACM Transactions on Knowledge Discovery from Data, 18(1), 1-54.
Jacob, V., Song, F., Stiegler, A., Rad, B., Diao, Y., & Tatbul, N. (2020). Exathlon: A benchmark for explainable anomaly detection over time series. arXiv preprint arXiv:2010.05073. Yao, L., Chu, Z., Li, S., Li, Y., Gao, J., & Zhang, A. (2021). A survey on causal inference. ACM Transactions on Knowledge Discovery from Data (TKDD), 15(5), 1-46. Chatterjee, J., & Dethlefs, N. (2020, September). Temporal causal inference in wind turbine scada data using deep learning for explainable AI. In Journal of Physics: Conference Series (Vol. 1618, No. 2, p. 022022). IOP Publishing. Liu, Y., Ding, K., Lu, Q., Li, F., Zhang, L. Y., & Pan, S. (2024). Towards self-interpretable graph-level anomaly detection. Advances in Neural Information Processing Systems, 36. Deng, A., & Hooi, B. (2021, May). Graph neural network-based anomaly detection in multivariate time series. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, No. 5, pp. 4027-4035). Ma, X., Wu, J., Xue, S., Yang, J., Zhou, C., Sheng, Q. Z., ... & Akoglu, L. (2021). A comprehensive survey on graph anomaly detection with deep learning. IEEE Transactions on Knowledge and Data Engineering, 35(12), 12012-12038. Rad, B., Song, F., Jacob, V., & Diao, Y. (2021, June). Explainable anomaly detection on high-dimensional time series data. In Proceedings of the 15th ACM International Conference on Distributed and Event-based Systems (pp. 2-14). |
| Prerequisites | |
| Author | Afroj Divan; Athulya Ashok |
| Supervisor | Yuantao Fan |
| Level | Master |
| Status | Internal Draft |
In our increasingly digital and interconnected society, time series data is one of the most prevalent forms of information. Detecting anomalies and explaining them is important to understanding unseen and valuable phenomena of temporal nature. This project will investigate how causal graphs learned from multivariate time series data can be used for explainable anomaly detection.
The thesis work includes: 1) a literature review of SOTA explainable anomaly detection; 2) an explainable anomaly detection method based on causal graphs; and 3) a case study on real-world problems.
