TimeREISE: Time-series Randomized Evolving Input Sample Explanation
This addresses the problem of interpretability in safety-critical contexts for time-series classification, though it is incremental as it adapts existing interpretability methods to a new modality.
The paper tackles the lack of interpretability in deep neural networks for time-series classification by introducing TimeREISE, a model-agnostic attribution method that shows superior performance compared to existing approaches in established measurements.
Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safety critical context. The research field of explainable artificial intelligence addresses this problem. However, most of the interpretability methods are aligned to the image modality by design. The paper introduces TimeREISE a model agnostic attribution method specifically aligned to success in the context of time series classification. The method shows superior performance compared to existing approaches concerning different well-established measurements. TimeREISE is applicable to any time series classification network, its runtime does not scale in a linear manner concerning the input shape and it does not rely on prior data knowledge.