Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventions

TL;DR

This paper emphasizes the importance of human-centered, temporally coherent counterfactual explanations for time series in clinical settings, highlighting current limitations and proposing a shift towards more practical, causally plausible interventions.

Contribution

It identifies critical gaps in existing counterfactual methods for time series, especially their lack of temporal coherence and user-centered design, and advocates for more realistic, actionable explanations.

Findings

State-of-the-art methods are highly sensitive to noise.

Current approaches often ignore temporal and causal plausibility.

Existing methods lack focus on real-world feasibility.

Abstract

Counterfactual explanations are increasingly proposed as interpretable mechanisms to achieve algorithmic recourse. However, current counterfactual techniques for time series classification are predominantly designed with static data assumptions and focus on generating minimal input perturbations to flip model predictions. This paper argues that such approaches are fundamentally insufficient in clinical recommendation settings, where interventions unfold over time and must be causally plausible and temporally coherent. We advocate for a shift towards counterfactuals that reflect sustained, goal-directed interventions aligned with clinical reasoning and patient-specific dynamics. We identify critical gaps in existing methods that limit their practical applicability, specifically, temporal blind spots and the lack of user-centered considerations in both method design and evaluation metrics. To support our position, we conduct a robustness analysis of several state-of-the-art methods for time series and show that the generated counterfactuals are highly sensitive to stochastic noise. This finding highlights their limited reliability in real-world clinical settings, where minor measurement variations are inevitable. We conclude by calling for methods and evaluation frameworks that go beyond mere prediction changes without considering feasibility or actionability. We emphasize the need for actionable, purpose-driven interventions that are feasible in real-world contexts for the users of such applications.