cs.LGNov 11, 2026

CoLaX: Context-Aware Local Explanations for Time Series Classification

Authors: Kexuan Zhang, Paolo Frazzetto, Xiaobei Zou, Gustau Camps-Valls, Yang Tang

Organizations: East China University of Science and Technology, China · Image Processing Laboratory, Universitat de València, Spain

Abstract

Post-hoc explanations for time series classifiers usually score local patterns, such as subsequences or shapelets, without regard to the rest of the sequence. Yet the same motif can carry different predictive meaning under different global temporal conditions, such as trends or regimes. We propose CoLaX, a context-aware post-hoc explanation framework that builds on shapelet-driven Shapley attribution and conditions local-pattern relevance on a learned representation of the full sequence. Global context acts at two levels: it produces sample-specific prototype weights and a temporally resolved signal that reweights the local activation map. The resulting context-conditioned segments are the players of a Shapley attribution game whose values come only from the frozen black-box classifier. On synthetic benchmarks where identical motifs change relevance across contexts, CoLaX improves AUPRC over the strongest baseline by 30% on average. On real-world data, it achieves the highest AUPRC on ECG. Additional ablations indicate that the gains come from input-dependent conditioning rather than from additional learnable weights. CoLaX is therefore most useful when recurring local motifs change relevance across sequence-level contexts.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. L2GTX: From Local to Global Time Series Explanations

    Mar 13, 2026Ephrem Tibebe Mekonnen, Luca Longo, Lucas Rizzo +1Explainable Artificial IntelligenceInterpretable Time-Series Classification

  2. Learnable Time-Frequency Masks for Explaining Time-Series Classifiers

    Sep 24, 2026Theresa Dahl Frehr, Francisco Pelayo, Lukas Raad +3Feature AttributionTime Series Classification