Towards plausibility in time series counterfactual explanations

TL;DR

This paper introduces a gradient-based method for generating plausible and realistic counterfactual explanations for time series classifiers by integrating soft-DTW alignment with nearest neighbors to ensure temporal plausibility.

Contribution

The novel approach combines soft-DTW and nearest neighbors within a multi-objective loss to produce more temporally realistic counterfactuals for time series data.

Findings

Achieves competitive validity in counterfactuals.

Outperforms existing methods in temporal plausibility.

Produces counterfactuals with realistic temporal structure.

Abstract

We present a new method for generating plausible counterfactual explanations for time series classification problems. The approach performs gradient-based optimization directly in the input space. To enforce plausibility, we integrate soft-DTW (dynamic time warping) alignment with $k$-nearest neighbors from the target class, which effectively encourages the generated counterfactuals to adopt a realistic temporal structure. The overall optimization objective is a multi-faceted loss function that balances key counterfactual properties. It incorporates losses for validity, sparsity, and proximity, alongside the novel soft-DTW-based plausibility component. We conduct an evaluation of our method against several strong reference approaches, measuring the key properties of the generated counterfactuals across multiple dimensions. The results demonstrate that our method achieves competitive performance in validity while significantly outperforming existing approaches in distributional alignment with the target class, indicating superior temporal realism. Furthermore, a qualitative analysis highlights the critical limitations of existing methods in preserving realistic temporal structure. This work shows that the proposed method consistently generates counterfactual explanations for time series classifiers that are not only valid but also highly plausible and consistent with temporal patterns.