Explainable AI for Time Series via Virtual Inspection Layers
This work addresses the problem of interpretability in time series data for researchers and practitioners in fields like speech processing and healthcare, representing an incremental advancement by extending existing XAI methods to a new domain.
The paper tackles the lack of explainable AI methods for time series by proposing a virtual inspection layer that transforms time series into interpretable representations, enabling the use of local XAI methods like LRP, and demonstrates its utility in domains such as audio and health records by revealing model strategies and spurious correlations.
The field of eXplainable Artificial Intelligence (XAI) has greatly advanced in recent years, but progress has mainly been made in computer vision and natural language processing. For time series, where the input is often not interpretable, only limited research on XAI is available. In this work, we put forward a virtual inspection layer, that transforms the time series to an interpretable representation and allows to propagate relevance attributions to this representation via local XAI methods like layer-wise relevance propagation (LRP). In this way, we extend the applicability of a family of XAI methods to domains (e.g. speech) where the input is only interpretable after a transformation. Here, we focus on the Fourier transformation which is prominently applied in the interpretation of time series and LRP and refer to our method as DFT-LRP. We demonstrate the usefulness of DFT-LRP in various time series classification settings like audio and electronic health records. We showcase how DFT-LRP reveals differences in the classification strategies of models trained in different domains (e.g., time vs. frequency domain) or helps to discover how models act on spurious correlations in the data.