TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification

2026-01-29

AI Summary

Existing time series classification methods struggle to balance predictive performance with interpretability and lack reliable mechanisms for assessing the importance of individual time segments. This work proposes TimeSliver, a novel framework that uniquely integrates symbolic abstraction with linear interpretable decomposition to assign faithful and interpretable contribution scores to each time point while preserving the original temporal structure. By doing so, TimeSliver overcomes key limitations of post-hoc explanation techniques and attention-based mechanisms. Empirical evaluation demonstrates that TimeSliver improves attribution performance by 11% over existing methods across seven synthetic and real-world multivariate datasets, while achieving prediction accuracy on the 26 UEA benchmark datasets that is within 2% of state-of-the-art levels.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Computer Vision: Interpretability, Explainability, and Transparency
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

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.

Problem

• time series classification
• explainability
• temporal attribution
• interpretability
• sequential dependencies

Innovation

• symbolic-linear decomposition
• explainable time series classification
• temporal attribution
• symbolic abstraction
• interpretable deep learning