Implet: A Post-hoc Subsequence Explainer for Time Series Models

TL;DR

Implet is a novel post-hoc explanation method for time series models that identifies critical subsequences, improving interpretability and trust in model predictions, with demonstrated effectiveness on benchmark datasets.

Contribution

It introduces Implet, a new post-hoc subsequence explainer for time series models, and a cohort-based framework to enhance explanation conciseness and interpretability.

Findings

Effective in identifying critical temporal segments

Improves interpretability over traditional methods

Validated on standard benchmarks

Abstract

Explainability in time series models is crucial for fostering trust, facilitating debugging, and ensuring interpretability in real-world applications. In this work, we introduce Implet, a novel post-hoc explainer that generates accurate and concise subsequence-level explanations for time series models. Our approach identifies critical temporal segments that significantly contribute to the model's predictions, providing enhanced interpretability beyond traditional feature-attribution methods. Based on it, we propose a cohort-based (group-level) explanation framework designed to further improve the conciseness and interpretability of our explanations. We evaluate Implet on several standard time-series classification benchmarks, demonstrating its effectiveness in improving interpretability. The code is available at https://github.com/LbzSteven/implet