EEG-Based Emotion Recognition Using Regularized Graph Neural Networks

TL;DR

This paper introduces a regularized graph neural network that leverages brain topology and novel regularizers to improve EEG-based emotion recognition, demonstrating superior performance and insights into brain activity.

Contribution

It proposes a biologically inspired GNN model with regularizers for better cross-subject adaptation and noise handling in EEG emotion recognition.

Findings

Outperforms state-of-the-art models on SEED and SEED-IV datasets.

Regularizers significantly improve model robustness and accuracy.

Identifies key brain regions and inter-channel relations for emotion recognition.

Abstract

Electroencephalography (EEG) measures the neuronal activities in different brain regions via electrodes. Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels. In this paper, we propose a regularized graph neural network (RGNN) for EEG-based emotion recognition. RGNN considers the biological topology among different brain regions to capture both local and global relations among different EEG channels. Specifically, we model the inter-channel relations in EEG signals via an adjacency matrix in a graph neural network where the connection and sparseness of the adjacency matrix are inspired by neuroscience theories of human brain organization. In addition, we propose two regularizers, namely node-wise domain adversarial training (NodeDAT) and emotion-aware distribution learning (EmotionDL), to better handle cross-subject EEG variations and noisy labels, respectively. Extensive experiments on two public datasets, SEED and SEED-IV, demonstrate the superior performance of our model than state-of-the-art models in most experimental settings. Moreover, ablation studies show that the proposed adjacency matrix and two regularizers contribute consistent and significant gain to the performance of our RGNN model. Finally, investigations on the neuronal activities reveal important brain regions and inter-channel relations for EEG-based emotion recognition.