A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI

TL;DR

This paper investigates the use of systematic perturbations to evaluate the quality of explanations generated by XAI techniques for time series data, providing a practical approach to assess interpretability in critical domains.

Contribution

It introduces a perturbation-based evaluation method for time series XAI attributions, comparing multiple techniques across datasets to assess their reliability and interpretability.

Findings

Perturbation analysis effectively evaluates attribution quality.

Different XAI methods show varying robustness to perturbations.

The approach guides the selection of suitable XAI techniques for time series.

Abstract

Explainable Artificial Intelligence (XAI) has gained significant attention recently as the demand for transparency and interpretability of machine learning models has increased. In particular, XAI for time series data has become increasingly important in finance, healthcare, and climate science. However, evaluating the quality of explanations, such as attributions provided by XAI techniques, remains challenging. This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models. A perturbation analysis involves systematically modifying the input data and evaluating the impact on the attributions generated by the XAI method. We apply this approach to several state-of-the-art XAI techniques and evaluate their performance on three time series classification datasets. Our results demonstrate that the perturbation analysis approach can effectively evaluate the quality of attributions and provide insights into the strengths and limitations of XAI techniques. Such an approach can guide the selection of XAI methods for time series data, e.g., focusing on return time rather than precision, and facilitate the development of more reliable and interpretable machine learning models for time series analysis.