XTSC-Bench: Quantitative Benchmarking for Explainers on Time Series Classification

TL;DR

This paper introduces XTSC-Bench, a standardized benchmarking tool for evaluating explainability methods in time series classification, addressing the lack of systematic quantitative assessment in the field.

Contribution

It provides datasets, models, and metrics for consistent evaluation of explanation methods on TSC, enabling rigorous comparison and analysis.

Findings

Explainability methods need improved robustness and reliability.

Multivariate data poses particular challenges for explanation methods.

Benchmarking reveals variability in explanation method performance.

Abstract

Despite the growing body of work on explainable machine learning in time series classification (TSC), it remains unclear how to evaluate different explainability methods. Resorting to qualitative assessment and user studies to evaluate explainers for TSC is difficult since humans have difficulties understanding the underlying information contained in time series data. Therefore, a systematic review and quantitative comparison of explanation methods to confirm their correctness becomes crucial. While steps to standardized evaluations were taken for tabular, image, and textual data, benchmarking explainability methods on time series is challenging due to a) traditional metrics not being directly applicable, b) implementation and adaption of traditional metrics for time series in the literature vary, and c) varying baseline implementations. This paper proposes XTSC-Bench, a benchmarking tool providing standardized datasets, models, and metrics for evaluating explanation methods on TSC. We analyze 3 perturbation-, 6 gradient- and 2 example-based explanation methods to TSC showing that improvements in the explainers' robustness and reliability are necessary, especially for multivariate data.