TY - CPAPER U1 - Konferenzveröffentlichung A1 - Höllig, Jacqueline A1 - Thoma, Steffen A1 - Grimm, Florian T1 - XTSC-bench: quantitative benchmarking for explainers on time series classification T2 - 22nd IEEE International Conference on Machine Learning and Applications (ICMLA 2023) : 15-17 December 2023, Jacksonville, Florida, proceedings N2 - 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. KW - explainable AI KW - time Series Classification KW - XAI Metrics Y1 - 2024 U6 - https://doi.org/10.1109/ICMLA58977.2023.00168 DO - https://doi.org/10.1109/ICMLA58977.2023.00168 SP - 1126 EP - 1131 S1 - 6 PB - IEEE CY - Piscataway ER -