Bridge Graph Attention Based Graph Convolution Network With Multi-Scale Transformer for EEG Emotion Recognition

In multichannel electroencephalograph (EEG) emotion recognition, most graph-based studies employ shallow graph model for spatial characteristics learning due to node over-smoothing caused by an increase in network depth. To address over-smoothing, we propose the bridge graph attention-based graph co...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on affective computing 2024-10, Vol.15 (4), p.2042-2054
Main Authors: Yan, Huachao, Guo, Kailing, Xing, Xiaofen, Xu, Xiangmin
Format: Article
Language:English
Subjects:
Brain modeling
Bridges
Convolution
EEG
Electroencephalography
Emotion recognition
Emotions
Feature extraction
graph attention network
Graph neural networks
Learning
multi-scale transformer
over-smoothing
Smoothing
Spatial smoothing
Transformers
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In multichannel electroencephalograph (EEG) emotion recognition, most graph-based studies employ shallow graph model for spatial characteristics learning due to node over-smoothing caused by an increase in network depth. To address over-smoothing, we propose the bridge graph attention-based graph convolution network (BGAGCN). It bridges previous graph convolution layers to attention coefficients of the final layer by adaptively combining each graph convolution output based on the graph attention network, thereby enhancing feature distinctiveness. Considering that graph-based network primarily focus on local EEG channel relationships, we introduce a transformer for global dependency. Inspired by the neuroscience finding that neural activities of different timescales reflect distinct spatial connectivities, we modify the transformer to a multi-scale transformer (MT) by applying multi-head attention to multichannel EEG signals after 1D convolutions at different scales. MT learns spatial features more elaborately to enhance feature representation ability. By combining BGAGCN and MT, our model BGAGCN-MT achieves state-of-the-art accuracy under subject-dependent and subject-independent protocols across three benchmark EEG emotion datasets (SEED, SEED-IV and DREAMER). Notably, our model effectively addresses over-smoothing in graph neural networks and provides an efficient solution to learning spatial relationships of EEG features at different scales.
ISSN:1949-3045
1949-3045
DOI:10.1109/TAFFC.2024.3394873