An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification

• URL: http://arxiv.org/abs/2509.03649v1
• Date: Wed, 03 Sep 2025 18:55:23 GMT
• Title: An Empirical Evaluation of Factors Affecting SHAP Explanation of Time Series Classification
• Authors: Davide Italo Serramazza, Nikos Papadeas, Zahraa Abdallah, Georgiana Ifrim,
• Abstract summary: We investigate eight different Time Series algorithms to understand how segment compositions affect explanation quality.<n>We find that the number of segments has a greater impact on explanation quality than the specific segmentation method.<n>We introduce a novel attribution normalisation technique that weights segments by their length and we show that it consistently improves attribution quality.
• Score: 1.5224436211478214
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• A system identification approach to clustering vector autoregressive time series [50.66782357329375]
  Clustering time series based on their underlying dynamics is keeping attracting researchers due to its impacts on assisting complex system modelling.<n>Most current time series clustering methods handle only scalar time series, treat them as white noise, or rely on domain knowledge for high-quality feature construction.<n>Instead of relying on feature/metric construction, the system identification approach allows treating vector time series clustering by explicitly considering their underlying autoregressive dynamics.
  arXiv  Detail & Related papers  (2025-05-20T14:31:44Z)
• 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)
• Fuzzy clustering of ordinal time series based on two novel distances with economic applications [0.12891210250935145]
  Two novel distances between ordinal time series are introduced and used to construct fuzzy clustering procedures. The resulting clustering algorithms are computationally efficient and able to group series generated from similar processes. Two specific applications involving economic time series illustrate the usefulness of the proposed approaches.
  arXiv  Detail & Related papers  (2023-04-24T16:39:22Z)
• A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos [17.712793578388126]
  We take a closer look at Procedure and Summarization (PSS) and propose three fundamental improvements over current methods. We propose a new segmentation metric based on dynamic programming that takes into account the order of segments. We propose a matching algorithm that constrains the temporal order of segment mapping, and is also differentiable.
  arXiv  Detail & Related papers  (2022-09-30T14:44:19Z)
• Efficient Approximate Kernel Based Spike Sequence Classification [56.2938724367661]
  Machine learning models, such as SVM, require a definition of distance/similarity between pairs of sequences. Exact methods yield better classification performance, but they pose high computational costs. We propose a series of ways to improve the performance of the approximate kernel in order to enhance its predictive performance.
  arXiv  Detail & Related papers  (2022-09-11T22:44:19Z)
• Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation [87.4854250338374]
  We explore relations among affinities in two aspects: single-scale intrinsic correlations and multi-scale relations. Our experiments demonstrate that the proposed method performs favorably against state-of-the-art VSS methods.
  arXiv  Detail & Related papers  (2022-07-21T12:12:36Z)
• COSTI: a New Classifier for Sequences of Temporal Intervals [0.0]
  We develop a novel method for classification operating directly on sequences of temporal intervals. The proposed method remains at a high level of accuracy and obtains better performance while avoiding shortcomings connected to operating on transformed data.
  arXiv  Detail & Related papers  (2022-04-28T12:55:06Z)
• Towards Similarity-Aware Time-Series Classification [51.2400839966489]
  We study time-series classification (TSC), a fundamental task of time-series data mining. We propose Similarity-Aware Time-Series Classification (SimTSC), a framework that models similarity information with graph neural networks (GNNs)
  arXiv  Detail & Related papers  (2022-01-05T02:14:57Z)
• Benchmarking Multivariate Time Series Classification Algorithms [69.12151492736524]
  Time Series Classification (TSC) involved building predictive models for a discrete target variable from ordered, real valued, attributes. Over recent years, a new set of TSC algorithms have been developed which have made significant improvement over the previous state of the art. We review recently proposed bespoke MTSC algorithms based on deep learning, shapelets and bag of words approaches.
  arXiv  Detail & Related papers  (2020-07-26T15:56:40Z)
• Supervised Feature Subset Selection and Feature Ranking for Multivariate Time Series without Feature Extraction [78.84356269545157]
  We introduce supervised feature ranking and feature subset selection algorithms for MTS classification. Unlike most existing supervised/unsupervised feature selection algorithms for MTS our techniques do not require a feature extraction step to generate a one-dimensional feature vector from the time series.
  arXiv  Detail & Related papers  (2020-05-01T07:46:29Z)
• Complexity Measures and Features for Times Series classification [0.0]
  We propose a set of characteristics capable of extracting information on the structure of the time series to face time series classification problems. The experimental results of our proposal show no statistically significant differences from the second and third best models of the state-of-the-art.
  arXiv  Detail & Related papers  (2020-02-27T11:08:08Z)

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.