L2GTX: From Local to Global Time Series Explanations
This addresses the challenge of understanding deep learning model decisions in time series classification, which is important for domain experts in fields like healthcare or finance, though it is incremental as it builds on existing local explanation methods.
The paper tackled the problem of generating class-wise global explanations for time series classification models, proposing L2GTX, a model-agnostic framework that aggregates local explanations to produce compact and interpretable global explanations, with experiments on six benchmark datasets showing stable global faithfulness measured as mean local surrogate fidelity.
Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging. Explanations for time series must respect temporal dependencies and identify patterns that recur across instances. Existing approaches face three limitations: model-agnostic XAI methods developed for images and tabular data do not readily extend to time series, global explanation synthesis for time series remains underexplored, and most existing global approaches are model-specific. We propose L2GTX, a model-agnostic framework that generates class-wise global explanations by aggregating local explanations from a representative set of instances. L2GTX extracts clusters of parameterised temporal event primitives, such as increasing or decreasing trends and local extrema, together with their importance scores from instance-level explanations produced by LOMATCE. These clusters are merged across instances to reduce redundancy, and an instance-cluster importance matrix is used to estimate global relevance. Under a user-defined instance selection budget, L2GTX selects representative instances that maximise coverage of influential clusters. Events from the selected instances are then aggregated into concise class-wise global explanations. Experiments on six benchmark time series datasets show that L2GTX produces compact and interpretable global explanations while maintaining stable global faithfulness measured as mean local surrogate fidelity.