Graph Neural Networks in EEG-based Emotion Recognition: A Survey

2024-02-02

arXiv.org

AI Summary

Graph neural networks (GNNs) for EEG-based emotion recognition suffer from physiologically unjustified graph modeling, inconsistent graph construction protocols, and poor methodological comparability. Method: This paper proposes the first unified GNN classification framework tailored to EEG emotion recognition. Through a systematic three-stage review—graph structure design, feature learning, and model optimization—of over 30 works, it establishes physiological constraints from functional brain connectivity as principled guidelines for graph construction and identifies fundamental distinctions between EEG-GNNs and general-purpose temporal GNNs. Contribution/Results: It introduces novel directions including temporally dense graphs and physiology-guided graph compression, yielding a comprehensive methodology covering EEG signal processing, physiology-driven graph construction, and cross-modal modeling. The framework provides theoretical foundations and practical pathways for developing interpretable, lightweight EEG-GNNs.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• 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: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Social Networks and Social Media: Computational social science

Abstract

Compared to other modalities, EEG-based emotion recognition can intuitively respond to the emotional patterns in the human brain and, therefore, has become one of the most concerning tasks in the brain-computer interfaces field. Since dependencies within brain regions are closely related to emotion, a significant trend is to develop Graph Neural Networks (GNNs) for EEG-based emotion recognition. However, brain region dependencies in emotional EEG have physiological bases that distinguish GNNs in this field from those in other time series fields. Besides, there is neither a comprehensive review nor guidance for constructing GNNs in EEG-based emotion recognition. In the survey, our categorization reveals the commonalities and differences of existing approaches under a unified framework of graph construction. We analyze and categorize methods from three stages in the framework to provide clear guidance on constructing GNNs in EEG-based emotion recognition. In addition, we discuss several open challenges and future directions, such as Temporal full-connected graph and Graph condensation.

Problem

• EEG-based emotion recognition challenges
• Graph Neural Networks in EEG analysis
• Lack of GNN construction guidance

Innovation

• Graph Neural Networks
• EEG-based emotion recognition
• Temporal full-connected graph