TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification

• URL: http://arxiv.org/abs/2601.21289v1
• Date: Thu, 29 Jan 2026 05:42:58 GMT
• Title: TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification
• Authors: Akash Pandey, Payal Mohapatra, Wei Chen, Qi Zhu, Sinan Keten,
• Abstract summary: We present a novel explainability-driven deep learning framework, TimeSliver, for time-series classification.<n>TimeSliver encodes the contribution of each temporal segment to the final prediction, allowing us to assign a meaningful importance score to every time point.<n>TimeSliver achieves predictive performance within 2% of state-of-the-art baselines across 26 UEA benchmark datasets.
• Score: 10.148392358711787
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting [0.0]
  This paper proposes a two-stage forecasting framework that separates local temporal representation learning from global dependency modelling.<n>A convolutional neural network operates on fixed-length temporal patches to extract short-range temporal dynamics and non-linear feature interactions.<n> Token-level self-attention is applied during representation learning to refine these embeddings, after which a Transformer encoder models inter-patch temporal dependencies to generate forecasts.
  arXiv  Detail & Related papers  (2026-01-18T16:16:01Z)
• FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification [56.925103708982164]
  We present a novel perspective from the frequency domain and identify three advantages for downstream classification: global, independent, and compact.<n>We propose the lightweight yet effective Frequency Refined Augmentation (FreRA) tailored for time series contrastive learning on classification tasks.<n>FreRA consistently outperforms ten leading baselines on time series classification, anomaly detection, and transfer learning tasks.
  arXiv  Detail & Related papers  (2025-05-29T07:18:28Z)
• Capturing Temporal Components for Time Series Classification [5.70772577110828]
  This work introduces a textitcompositional representation learning approach trained on statistically coherent components extracted from sequential data. Based on a multi-scale change space, an unsupervised approach is proposed to segment the sequential data into chunks with similar statistical properties. A sequence-based encoder model is trained in a multi-task setting to learn compositional representations from these temporal components for time series classification.
  arXiv  Detail & Related papers  (2024-06-20T16:15:21Z)
• TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling [67.02157180089573]
  Time series pre-training has recently garnered wide attention for its potential to reduce labeling expenses and benefit various downstream tasks. This paper proposes TimeSiam as a simple but effective self-supervised pre-training framework for Time series based on Siamese networks.
  arXiv  Detail & Related papers  (2024-02-04T13:10:51Z)
• Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions [9.734940058811707]
  We propose the Attribution Stability Indicator (ASI) to incorporate robustness and trustworthiness as properties of attribution techniques for time series into account. We demonstrate the wanted properties based on an analysis of the attributions in a dimension-reduced space and the ASI scores distribution over three whole time series classification datasets.
  arXiv  Detail & Related papers  (2023-10-06T11:48:26Z)
• Cluster-and-Conquer: A Framework For Time-Series Forecasting [94.63501563413725]
  We propose a three-stage framework for forecasting high-dimensional time-series data. Our framework is highly general, allowing for any time-series forecasting and clustering method to be used in each step. When instantiated with simple linear autoregressive models, we are able to achieve state-of-the-art results on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T20:41:19Z)
• Interpretable Time-series Representation Learning With Multi-Level Disentanglement [56.38489708031278]
  Disentangle Time Series (DTS) is a novel disentanglement enhancement framework for sequential data. DTS generates hierarchical semantic concepts as the interpretable and disentangled representation of time-series. DTS achieves superior performance in downstream applications, with high interpretability of semantic concepts.
  arXiv  Detail & Related papers  (2021-05-17T22:02:24Z)
• From Static to Dynamic Node Embeddings [61.58641072424504]
  We introduce a general framework for leveraging graph stream data for temporal prediction-based applications. Our proposed framework includes novel methods for learning an appropriate graph time-series representation. We find that the top-3 temporal models are always those that leverage the new $epsilon$-graph time-series representation.
  arXiv  Detail & Related papers  (2020-09-21T16:48:29Z)
• Predicting Temporal Sets with Deep Neural Networks [50.53727580527024]
  We propose an integrated solution based on the deep neural networks for temporal sets prediction. A unique perspective is to learn element relationship by constructing set-level co-occurrence graph. We design an attention-based module to adaptively learn the temporal dependency of elements and sets.
  arXiv  Detail & Related papers  (2020-06-20T03:29:02Z)
• What went wrong and when? Instance-wise Feature Importance for Time-series Models [32.76628660490065]
  We propose a framework that evaluates the importance of observations for a time-series black-box model. FIT defines the importance of an observation based on its contribution to the distributional shift. We demonstrate the need to control for time-dependent distribution shifts.
  arXiv  Detail & Related papers  (2020-03-05T18:45:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.