An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908518404063232 |
|---|---|
| author | Serramazza, Davide Italo Papadeas, Nikos Abdallah, Zahraa Ifrim, Georgiana |
| author_facet | Serramazza, Davide Italo Papadeas, Nikos Abdallah, Zahraa Ifrim, Georgiana |
| contents | Explainable AI (XAI) has become an increasingly important topic for understanding and attributing the predictions made by complex Time Series Classification (TSC) models. Among attribution methods, SHapley Additive exPlanations (SHAP) is widely regarded as an excellent attribution method; but its computational complexity, which scales exponentially with the number of features, limits its practicality for long time series. To address this, recent studies have shown that aggregating features via segmentation, to compute a single attribution value for a group of consecutive time points, drastically reduces SHAP running time. However, the choice of the optimal segmentation strategy remains an open question. In this work, we investigated eight different Time Series Segmentation algorithms to understand how segment compositions affect the explanation quality. We evaluate these approaches using two established XAI evaluation methodologies: InterpretTime and AUC Difference. Through experiments on both Multivariate (MTS) and Univariate Time Series (UTS), we find that the number of segments has a greater impact on explanation quality than the specific segmentation method. Notably, equal-length segmentation consistently outperforms most of the custom time series segmentation algorithms. Furthermore, we introduce a novel attribution normalisation technique that weights segments by their length and we show that it consistently improves attribution quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03649 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification Serramazza, Davide Italo Papadeas, Nikos Abdallah, Zahraa Ifrim, Georgiana Artificial Intelligence Explainable AI (XAI) has become an increasingly important topic for understanding and attributing the predictions made by complex Time Series Classification (TSC) models. Among attribution methods, SHapley Additive exPlanations (SHAP) is widely regarded as an excellent attribution method; but its computational complexity, which scales exponentially with the number of features, limits its practicality for long time series. To address this, recent studies have shown that aggregating features via segmentation, to compute a single attribution value for a group of consecutive time points, drastically reduces SHAP running time. However, the choice of the optimal segmentation strategy remains an open question. In this work, we investigated eight different Time Series Segmentation algorithms to understand how segment compositions affect the explanation quality. We evaluate these approaches using two established XAI evaluation methodologies: InterpretTime and AUC Difference. Through experiments on both Multivariate (MTS) and Univariate Time Series (UTS), we find that the number of segments has a greater impact on explanation quality than the specific segmentation method. Notably, equal-length segmentation consistently outperforms most of the custom time series segmentation algorithms. Furthermore, we introduce a novel attribution normalisation technique that weights segments by their length and we show that it consistently improves attribution quality. |
| title | An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.03649 |