Multi-Subdomain Adversarial Network for Cross-Subject EEG-based Emotion Recognition

TL;DR

This paper introduces MSAN, a novel adversarial network that improves cross-subject EEG-based emotion recognition by modeling subdomain discrepancies and enhancing class separation, significantly boosting accuracy.

Contribution

The paper proposes a multi-subdomain adversarial network with autoencoder initialization to better handle individual differences in EEG emotion recognition, outperforming previous domain adaptation methods.

Findings

MSAN improves accuracy by 30.02% on SEED dataset.

Model effectively reduces intra-class and increases inter-class distances.

Autoencoder initialization enhances model stability.

Abstract

The individual difference between subjects is significant in EEG-based emotion recognition, resulting in the difficulty of sharing the model across subjects. Previous studies use domain adaptation algorithms to minimize the global domain discrepancy while ignoring the class information, which may cause misalignment of subdomains and reduce model performance. This paper proposes a multi-subdomain adversarial network (MSAN) for cross-subject EEG-based emotion recognition. MSAN uses adversarial training to model the discrepancy in the global domain and subdomain to reduce the intra-class distance and enlarge the inter-class distance. In addition, MSAN initializes parameters through a pre-trained autoencoder to ensure the stability and convertibility of the model. The experimental results show that the accuracy of MSAN is improved by 30.02\% on the SEED dataset comparing with the nontransfer method.