Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Chenyu Liu, Xinliang Zhou, Yihao Wu, Ruizhi Yang, Zhongruo Wang, Liming Zhai, Ziyu Jia, Yang Liu

TL;DR

The paper addresses EEG-based emotion recognition by leveraging Graph Neural Networks to capture inter-regional brain dependencies. It proposes a unified, three-stage framework for constructing GNNs (node-level, edge-level, graph-level) and provides a taxonomy of node features, edge computations, and graph structures to guide model design. The work highlights open challenges and directions, such as temporal full-connected graphs and graph condensation, to advance robust GNN-based emotion recognition. Overall, the survey offers concrete guidelines to unify and accelerate future GNN development in EEG-based emotion recognition, with implications for both neuroscience insight and practical BCI applications.

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.

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

TL;DR

The paper addresses EEG-based emotion recognition by leveraging Graph Neural Networks to capture inter-regional brain dependencies. It proposes a unified, three-stage framework for constructing GNNs (node-level, edge-level, graph-level) and provides a taxonomy of node features, edge computations, and graph structures to guide model design. The work highlights open challenges and directions, such as temporal full-connected graphs and graph condensation, to advance robust GNN-based emotion recognition. Overall, the survey offers concrete guidelines to unify and accelerate future GNN development in EEG-based emotion recognition, with implications for both neuroscience insight and practical BCI applications.

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.
Paper Structure (6 sections, 3 figures)

This paper contains 6 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Overview of Categorization
  3. Framework for specific GNNs
  4. Stages of Framework
  5. Node-level Stage
  6. Univariate node

Figures (3)

  • Figure 1: Number of GNN-based methods and non-GNN-based methods, and their relative proportion in EEG-based emotion recognition in top journals and conferences over the last six years. So far, more than one-third of the methods utilize GNNs.
  • Figure 2: Unified framework of EEG-based emotion recognition. First, (a) indicates the selection of node features. Then, (b) refers to the computation of the edge matrix representing brain connectivity patterns. Finally, (c) denotes the construction of a graph, which differs across methods.
  • Figure 3: An overview of the categorization. The existing method was split into three stages for further categorization. These three steps correspond to (a) the selection of node features, (b) the calculation of edge matrices, and (c) the construction of graphs with different structures.