Interpretability in Deep Time Series Models Demands Semantic Alignment
This addresses the black-box problem in deep time series models for end users, proposing a foundational shift in interpretability approaches.
The paper argues that interpretability in deep time series models should focus on semantic alignment, ensuring predictions use meaningful variables and preserve alignment over time, and outlines a blueprint for such models.
Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon. Instead, we state interpretability in deep time series models should pursue semantic alignment: predictions should be expressed in terms of variables that are meaningful to the end user, mediated by spatial and temporal mechanisms that admit user-dependent constraints. In this paper, we formalize this requirement and require that, once established, semantic alignment must be preserved under temporal evolution: a constraint with no analog in static settings. Provided with this definition, we outline a blueprint for semantically aligned deep time series models, identify properties that support trust, and discuss implications for model design.