CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models
Abstract: Despite the excelling performance of machine learning models, understanding their decisions remains a long-standing goal. While commonly used attribution methods from explainable AI attempt to address this issue, they typically rely on associational rather than causal relationships. In this study, within the context of time series classification, we introduce a novel model-agnostic framework to assess the causal effect of concepts, i.e., predefined segments within a time series, on specific classification outcomes. To achieve this, we leverage state-of-the-art diffusion-based models to estimate counterfactual outcomes. Our approach compares these causal attributions with closely related associational attributions, both theoretically and empirically. We demonstrate the insights gained by our approach for a diverse set of qualitatively different time series classification tasks. Although causal and associational attributions might often share some similarities, in all cases they differ in important details, underscoring the risks associated with drawing causal conclusions from associational data alone. We believe that the proposed approach is widely applicable also in other domains to shed some light on the limits of associational attributions.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Taylor_W._Killian1
Submission Number: 3292
Loading