Rethinking Saliency Map: An Context-aware Perturbation Method to Explain EEG-based Deep Learning Model

TL;DR

This paper introduces a novel context-aware perturbation method for explaining EEG-based deep learning models, providing more accurate saliency maps and artifact suppression tailored to EEG data characteristics.

Contribution

It proposes a new explanation method specifically designed for EEG data, incorporating context-awareness and optional area limitation for clearer interpretability.

Findings

The method produces more accurate saliency maps compared to existing approaches.

It effectively suppresses artifacts in EEG-based deep learning models.

Experimental results on the DEAP dataset validate the advantages of the proposed approach.

Abstract

Deep learning is widely used to decode the electroencephalogram (EEG) signal. However, there are few attempts to specifically investigate how to explain the EEG-based deep learning models. We conduct a review to summarize the existing works explaining the EEG-based deep learning model. Unfortunately, we find that there is no appropriate method to explain them. Based on the characteristic of EEG data, we suggest a context-aware perturbation method to generate a saliency map from the perspective of the raw EEG signal. Moreover, we also justify that the context information can be used to suppress the artifacts in the EEG-based deep learning model. In practice, some users might want a simple version of the explanation, which only indicates a few features as salient points. To this end, we propose an optional area limitation strategy to restrict the highlighted region. To validate our idea and make a comparison with the other methods, we select three representative EEG-based models to implement experiments on the emotional EEG dataset DEAP. The results of the experiments support the advantages of our method.