Guided by Stars: Interpretable Concept Learning Over Time Series via Temporal Logic Semantics
This addresses the need for interpretable models in safety-critical applications where black-box methods are insufficient, offering a novel approach to combine accuracy with explainability.
The paper tackles the problem of interpretability in time series classification by proposing STELLE, a neuro-symbolic framework that embeds trajectories into temporal logic concepts, achieving competitive accuracy and providing human-readable logical explanations for predictions.
Time series classification is a task of paramount importance, as this kind of data often arises in safety-critical applications. However, it is typically tackled with black-box deep learning methods, making it hard for humans to understand the rationale behind their output. To take on this challenge, we propose a novel approach, STELLE (Signal Temporal logic Embedding for Logically-grounded Learning and Explanation), a neuro-symbolic framework that unifies classification and explanation through direct embedding of trajectories into a space of temporal logic concepts. By introducing a novel STL-inspired kernel that maps raw time series to their alignment with predefined STL formulae, our model jointly optimises accuracy and interpretability, as each prediction is accompanied by the most relevant logical concepts that characterise it. This yields (i) local explanations as human-readable STL conditions justifying individual predictions, and (ii) global explanations as class-characterising formulae. Experiments demonstrate that STELLE achieves competitive accuracy while providing logically faithful explanations, validated on diverse real-world benchmarks.