Adaptive Progressive Attention Graph Neural Network for EEG Emotion Recognition

2025-01-24

AI Summary

This study addresses the limitation of dynamic brain functional connectivity modeling in individualized EEG-based emotion recognition. We propose a Progressive Attention Graph Neural Network (PAGNN) that constructs an EEG spatiotemporal graph and employs three expert subnetworks to jointly model: (i) global brain topological structure, (ii) region-specific functional patterns, and (iii) emotion-sensitive channel features. An attention-guided adaptive fusion mechanism enables synergistic integration across global, local, and emotion-channel levels. Crucially, PAGNN is the first framework to jointly model inter-subject variability and intra-subject emotional dynamics. Evaluated on SEED, SEED-IV, and MPED datasets, it achieves average classification accuracy improvements of 3.2–5.7% over state-of-the-art methods, demonstrating both the effectiveness and generalizability of explicitly modeling dynamic spatial relationships among brain regions.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web

Abstract

In recent years, numerous neuroscientific studies have shown that human emotions are closely linked to specific brain regions, with these regions exhibiting variability across individuals and emotional states. To fully leverage these neural patterns, we propose an Adaptive Progressive Attention Graph Neural Network (APAGNN), which dynamically captures the spatial relationships among brain regions during emotional processing. The APAGNN employs three specialized experts that progressively analyze brain topology. The first expert captures global brain patterns, the second focuses on region-specific features, and the third examines emotion-related channels. This hierarchical approach enables increasingly refined analysis of neural activity. Additionally, a weight generator integrates the outputs of all three experts, balancing their contributions to produce the final predictive label. Extensive experiments on three publicly available datasets (SEED, SEED-IV and MPED) demonstrate that the proposed method enhances EEG emotion recognition performance, achieving superior results compared to baseline methods.

Problem

• Emotion Recognition
• Brain Waves
• Neural Connectivity

Innovation

• APAGNN
• Attention Mechanism
• Emotion Recognition