Counterfactual Explanation for Auto-Encoder Based Time-Series Anomaly Detection

TL;DR

This paper enhances the interpretability of auto-encoder based time-series anomaly detection by using counterfactual explanations, providing more meaningful insights into model decisions and improving trustworthiness.

Contribution

It introduces a counterfactual explanation method combined with feature selection to improve interpretability of auto-encoder anomaly detection models.

Findings

Counterfactual explanations offer meaningful insights with fewer signals.

The approach improves model interpretability and trustworthiness.

Experimental results on benchmark and industrial datasets validate effectiveness.

Abstract

The complexity of modern electro-mechanical systems require the development of sophisticated diagnostic methods like anomaly detection capable of detecting deviations. Conventional anomaly detection approaches like signal processing and statistical modelling often struggle to effectively handle the intricacies of complex systems, particularly when dealing with multi-variate signals. In contrast, neural network-based anomaly detection methods, especially Auto-Encoders, have emerged as a compelling alternative, demonstrating remarkable performance. However, Auto-Encoders exhibit inherent opaqueness in their decision-making processes, hindering their practical implementation at scale. Addressing this opacity is essential for enhancing the interpretability and trustworthiness of anomaly detection models. In this work, we address this challenge by employing a feature selector to select features and counterfactual explanations to give a context to the model output. We tested this approach on the SKAB benchmark dataset and an industrial time-series dataset. The gradient based counterfactual explanation approach was evaluated via validity, sparsity and distance measures. Our experimental findings illustrate that our proposed counterfactual approach can offer meaningful and valuable insights into the model decision-making process, by explaining fewer signals compared to conventional approaches. These insights enhance the trustworthiness and interpretability of anomaly detection models.