Counterfactual Explainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification

TL;DR

The paper introduces CONFETTI, a multi-objective counterfactual explanation method for deep learning-based multivariate time series classification, enhancing interpretability by balancing confidence, proximity, and sparsity.

Contribution

It presents a novel multi-objective counterfactual explanation approach specifically designed for multivariate time series classification, outperforming existing methods across multiple metrics.

Findings

CONFETTI achieves at least 10% higher confidence than state-of-the-art methods.

It improves sparsity in explanations by at least 40%.

Demonstrates effectiveness across seven diverse datasets.

Abstract

Recent advances in deep learning have improved multivariate time series (MTS) classification and regression by capturing complex patterns, but their lack of transparency hinders decision-making. Explainable AI (XAI) methods offer partial insights, yet often fall short of conveying the full decision space. Counterfactual Explanations (CE) provide a promising alternative, but current approaches typically prioritize either accuracy, proximity or sparsity -- rarely all -- limiting their practical value. To address this, we propose CONFETTI, a novel multi-objective CE method for MTS. CONFETTI identifies key MTS subsequences, locates a counterfactual target, and optimally modifies the time series to balance prediction confidence, proximity and sparsity. This method provides actionable insights with minimal changes, improving interpretability, and decision support. CONFETTI is evaluated on seven MTS datasets from the UEA archive, demonstrating its effectiveness in various domains. CONFETTI consistently outperforms state-of-the-art CE methods in its optimization objectives, and in six other metrics from the literature, achieving $\geq10\%$ higher confidence while improving sparsity in $\geq40\%$.