Guardado en:
Detalles Bibliográficos
Autores principales: Pandey, Akash, Mohapatra, Payal, Chen, Wei, Zhu, Qi, Keten, Sinan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.21289
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918377414459392
author Pandey, Akash
Mohapatra, Payal
Chen, Wei
Zhu, Qi
Keten, Sinan
author_facet Pandey, Akash
Mohapatra, Payal
Chen, Wei
Zhu, Qi
Keten, Sinan
contents Identifying the extent to which every temporal segment influences a model's predictions is essential for explaining model decisions and increasing transparency. While post-hoc explainable methods based on gradients and feature-based attributions have been popular, they suffer from reference state sensitivity and struggle to generalize across time-series datasets, as they treat time points independently and ignore sequential dependencies. Another perspective on explainable time-series classification is through interpretable components of the model, for instance, leveraging self-attention mechanisms to estimate temporal attribution; however, recent findings indicate that these attention weights often fail to provide faithful measures of temporal importance. In this work, we advance this perspective and present a novel explainability-driven deep learning framework, TimeSliver, which jointly utilizes raw time-series data and its symbolic abstraction to construct a representation that maintains the original temporal structure. Each element in this representation linearly encodes the contribution of each temporal segment to the final prediction, allowing us to assign a meaningful importance score to every time point. For time-series classification, TimeSliver outperforms other temporal attribution methods by 11% on 7 distinct synthetic and real-world multivariate time-series datasets. TimeSliver also achieves predictive performance within 2% of state-of-the-art baselines across 26 UEA benchmark datasets, positioning it as a strong and explainable framework for general time-series classification.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21289
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification
Pandey, Akash
Mohapatra, Payal
Chen, Wei
Zhu, Qi
Keten, Sinan
Machine Learning
Identifying the extent to which every temporal segment influences a model's predictions is essential for explaining model decisions and increasing transparency. While post-hoc explainable methods based on gradients and feature-based attributions have been popular, they suffer from reference state sensitivity and struggle to generalize across time-series datasets, as they treat time points independently and ignore sequential dependencies. Another perspective on explainable time-series classification is through interpretable components of the model, for instance, leveraging self-attention mechanisms to estimate temporal attribution; however, recent findings indicate that these attention weights often fail to provide faithful measures of temporal importance. In this work, we advance this perspective and present a novel explainability-driven deep learning framework, TimeSliver, which jointly utilizes raw time-series data and its symbolic abstraction to construct a representation that maintains the original temporal structure. Each element in this representation linearly encodes the contribution of each temporal segment to the final prediction, allowing us to assign a meaningful importance score to every time point. For time-series classification, TimeSliver outperforms other temporal attribution methods by 11% on 7 distinct synthetic and real-world multivariate time-series datasets. TimeSliver also achieves predictive performance within 2% of state-of-the-art baselines across 26 UEA benchmark datasets, positioning it as a strong and explainable framework for general time-series classification.
title TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification
topic Machine Learning
url https://arxiv.org/abs/2601.21289