GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series
This addresses the need for actionable counterfactuals in time series applications, such as radar gesture recognition and handwritten letter trajectories, though it appears incremental by improving on existing approaches.
The paper tackled the problem of generating plausible and interpretable counterfactual explanations for multivariate time series classifiers, and the result showed that GenFacts outperformed baseline methods by 18.7% in plausibility metrics and achieved the highest interpretability scores in user studies.
Counterfactual explanations aim to enhance model transparency by illustrating how input modifications can change model predictions. In the multivariate time series domain, existing approaches often produce counterfactuals that lack validity, plausibility, or intuitive interpretability. We present \textbf{GenFacts}, a novel generative framework for producing plausible and actionable counterfactual explanations for time series classifiers. GenFacts introduces a structured approach to latent space modeling and targeted counterfactual synthesis. We evaluate GenFacts on radar gesture recognition as an industrial use case and handwritten letter trajectories as an intuitive benchmark. Across both datasets, GenFacts consistently outperforms baseline methods in plausibility metrics (+18.7\%) and achieves the highest interpretability scores in user studies. These results underscore that realism and user-centered interpretability, rather than sparsity alone, are vital for actionable counterfactuals in time series applications.