End-to-end learnable EEG channel selection for deep neural networks with Gumbel-softmax

TL;DR

This paper introduces an end-to-end neural network framework that learns optimal EEG channel selection using Gumbel-softmax, reducing computational costs and improving task performance.

Contribution

It presents a novel differentiable approach for EEG channel selection integrated into neural networks, enabling joint learning of channels and model weights.

Findings

Competitive performance with state-of-the-art methods

Applicable to multiple EEG tasks like motor imagery and auditory attention decoding

Reduces computational cost of channel selection

Abstract

Many electroencephalography (EEG) applications rely on channel selection methods to remove the least informative channels, e.g., to reduce the amount of electrodes to be mounted, to decrease the computational load, or to reduce overfitting effects and improve performance. Wrapper-based channel selection methods aim to match the channel selection step to the target model, yet they require to re-train the model multiple times on different candidate channel subsets, which often leads to an unacceptably high computational cost, especially when said model is a (deep) neural network. To alleviate this, we propose a framework to embed the EEG channel selection in the neural network itself to jointly learn the network weights and optimal channels in an end-to-end manner by traditional backpropagation algorithms. We deal with the discrete nature of this new optimization problem by employing continuous relaxations of the discrete channel selection parameters based on the Gumbel-softmax trick. We also propose a regularization method that discourages selecting channels more than once. This generic approach is evaluated on two different EEG tasks: motor imagery brain-computer interfaces and auditory attention decoding. The results demonstrate that our framework is generally applicable, while being competitive with state-of-the art EEG channel selection methods, tailored to these tasks.