Search papers, labs, and topics across Lattice.
This paper introduces a unified information bottleneck framework for time series explanations that integrates attribution-based and counterfactual explanation methods, addressing their individual limitations. By leveraging an information-theoretic approach, the authors develop a novel explanation framework, {\modelname}, which prevents trivial solutions and ensures stability in counterfactual explanations. Experimental results demonstrate that {\modelname} significantly outperforms existing state-of-the-art methods, providing both reliable attributions and robust counterfactuals across various benchmarks.
Bridging the gap between attribution and counterfactual explanations, this framework achieves unprecedented stability and reliability in time series model interpretability.
Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two categories: attribution-based explanations, which identify the temporal regions most responsible for a prediction, and counterfactual explanations, which reveal how an input should be modified to alter the model's decision.} {Despite valuable insights, these two fields are largely studied independently. This disconnect leaves attribution methods lacking causal validation, while counterfactual methods suffer from severe instability, producing adversarial-like noise instead of meaningful explanations.} In this work, we revisit time-series explainability from an information-theoretic perspective and show that existing explainers are vulnerable to trivial solutions and distributional shifts. To address these limitations, we propose a unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning within a single framework. Building upon the Information Bottleneck principle, our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals. {Based on this objective function, we introduce {\modelname}, a novel explanation framework that learns a parametric transformation network to construct explanation-embedded instances, where preserved information yields attribution explanations and controlled information removal produces stable counterfactual explanations.} We evaluate {\modelname} on synthetic and real-world benchmarks against state-of-the-art baselines. Extensive quantitative and qualitative results show that {\modelname} consistently outperforms competing methods, yielding faithful attributions and stable counterfactual explanations.
