End-to-end learnable EEG channel selection for deep neural networks with Gumbel-softmax
This work addresses the need for efficient channel selection in EEG applications, such as brain-computer interfaces, to reduce computational load and improve performance, though it is incremental as it builds on existing Gumbel-softmax techniques.
The paper tackles the problem of high computational cost in wrapper-based EEG channel selection methods by proposing an end-to-end learnable framework that embeds channel selection within neural networks, using Gumbel-softmax to handle discrete optimization, and demonstrates competitive performance with state-of-the-art methods on motor imagery and auditory attention decoding tasks.
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.