方法对比

	可解释自编码器异常检测	可解释单类支持向量机
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2017-2019	1999 (OCSVM); 2017–present (explainability integration)
提出者	Combination of autoencoder anomaly detection (Hinton & Salakhutdinov, 2006) and XAI methods (e.g., Lundberg & Lee, 2017)	Schölkopf, B. et al. (OCSVM); explainability layer via Lundberg & Lee (SHAP, 2017) and related works
类型	Unsupervised anomaly detection with post-hoc or intrinsic explainability	Anomaly/novelty detection with post-hoc or intrinsic explainability
开创性文献	Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.	Schölkopf, B., Williamson, R., Smola, A., Shawe-Taylor, J., & Platt, J. (1999). Support vector method for novelty detection. Advances in Neural Information Processing Systems, 12, 582–588.
别名	XAI autoencoder anomaly detection, interpretable autoencoder anomaly detection, explainable deep anomaly detection, SHAP-autoencoder anomaly detection	XOC-SVM, Interpretable One-Class SVM, SHAP-augmented OCSVM, Explainable Novelty Detection SVM
相关	6	4
摘要	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.	Explainable One-Class SVM pairs the classic One-Class Support Vector Machine anomaly detector — which learns a tight boundary around normal data without requiring labeled anomalies — with post-hoc explainability methods such as SHAP or LIME to reveal which features drive each novelty or anomaly score, converting an opaque decision boundary into an auditable, feature-attributable signal.