方法对比

	可解释自编码器异常检测	自监督自编码器异常检测
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2017-2019	2018–2020
提出者	Combination of autoencoder anomaly detection (Hinton & Salakhutdinov, 2006) and XAI methods (e.g., Lundberg & Lee, 2017)	Golan & El-Yaniv; broader self-supervised anomaly detection community
类型	Unsupervised anomaly detection with post-hoc or intrinsic explainability	Unsupervised / self-supervised deep learning
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.	Golan, I. & El-Yaniv, R. (2018). Deep one-class classification via geometric transformations. Advances in Neural Information Processing Systems (NeurIPS), 31.
别名	XAI autoencoder anomaly detection, interpretable autoencoder anomaly detection, explainable deep anomaly detection, SHAP-autoencoder anomaly detection	SSL Autoencoder anomaly detection, self-supervised reconstruction anomaly detection, pretext-task autoencoder anomaly detection, contrastive autoencoder anomaly detection
相关	6	6
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.	Self-supervised autoencoder anomaly detection trains an autoencoder using self-supervised pretext tasks — such as predicting geometric transformations or solving jigsaw puzzles — on unlabeled normal data, then flags as anomalous any input whose reconstruction error or pretext-task score deviates substantially from the learned normal distribution.