ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization

2026-06-11

AI Summary

This work addresses the limited interpretability of existing self-supervised time series anomaly detection methods, which often fail to reveal the semantic characteristics underlying detected anomalies. To bridge this gap, we introduce prototype learning into this domain for the first time and propose a prototype-based self-explainable framework. By integrating self-supervised classification, transformation-aware representation learning, and an interpretable prototype mechanism, our approach achieves high detection accuracy while providing semantically clear and consistent explanations for anomalies. Experimental results demonstrate that the proposed method matches the performance of state-of-the-art black-box models across multiple synthetic and real-world datasets, while significantly outperforming existing interpretable baselines in terms of explanation consistency and semantic clarity.

Abstract

Recent advances in time series anomaly detection (TSAD) have highlighted the effectiveness of self-supervised classification-based approaches. These methods apply transformations to normal training samples, training a classifier to recognize transformation-specific patterns that help identify anomalies through increased classification errors. Despite their strong performance, a significant challenge is their lack of explainability, as they provide limited insight into the characteristics of flagged anomalies. To address this limitation, we propose ProtoX-AD, a prototype-based self-explainable framework for self-supervised TSAD. ProtoX-AD learns transformation-aware latent representations alongside interpretable prototypes, enabling both accurate anomaly detection and the identification of distinct anomalous profiles through prototype-based explanations. Additionally, it allows for systematic analysis of how transformation design impacts detection performance and explainability. Experimental results on synthetic and real-world datasets demonstrate that ProtoX-AD achieves detection performance comparable to its black-box counterparts while offering more consistent and semantically meaningful explanations than existing explainable baselines. Our code is publicly available at https://github.com/Aitorzan3/ProtoX-AD.

Problem

• time series anomaly detection
• self-supervised learning
• explainability
• anomaly characterization

Innovation

• prototype-based
• self-explainable
• time series anomaly detection
• self-supervised learning
• interpretable AI