Explainable Autoencoder Anomaly Detection augments a standard autoencoder-based anomaly detector with an interpretability layer — such as SHAP values or feature-wise reconstruction error decomposition — that identifies which input features drove the anomaly flag for each observation, turning an opaque reconstruction-error score into an actionable, human-readable explanation.
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30. link ↗
Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407. link ↗