XAI for time-series classification leveraging image highlight methods
This work addresses the need for explainability in time-series analysis, which is crucial for domains like healthcare or finance, but it is incremental as it adapts existing image methods to a new data type.
The paper tackles the problem of explaining time-series classification by transforming time series into 2D plots and applying image highlight methods like LIME and GradCam, achieving interpretability while maintaining competitive accuracy with a baseline model, though at the cost of increased training time.
Although much work has been done on explainability in the computer vision and natural language processing (NLP) fields, there is still much work to be done to explain methods applied to time series as time series by nature can not be understood at first sight. In this paper, we present a Deep Neural Network (DNN) in a teacher-student architecture (distillation model) that offers interpretability in time-series classification tasks. The explainability of our approach is based on transforming the time series to 2D plots and applying image highlight methods (such as LIME and GradCam), making the predictions interpretable. At the same time, the proposed approach offers increased accuracy competing with the baseline model with the trade-off of increasing the training time.