Adaptive Graph Neural Network for Cross-Subject EEG Emotion Recognition Using Functional Connectivity

Abstract

Electroencephalography (EEG)-based emotion recognition has gained significant attention for applications in mental health monitoring and brain–computer interfaces; however, achieving ro- bust cross-subject generalization remains a major challenge due to high inter-subject variability. This study proposes an adaptive Graph Neural Network (GNN) framework for EEG-based emo- tion recognition, where EEG channels are modeled as graph nodes and functional connectivity is dynamically constructed using correlation-based relationships. Unlike conventional approaches that rely on fixed or fully connected graph structures, the proposed method generates window- wise adaptive graphs, enabling the model to capture time-varying and subject-invariant neural interactions. EEG signals are segmented into overlapping temporal windows, and frequency-domain features are extracted using power spectral density across standard EEG bands. A Graph Convolutional Network (GCN) is employed to learn spatial dependencies, and the model is evaluated under a strict subject-independent protocol using Leave-One-Subject-Out (LOSO) cross-validation on the DEAP dataset. Experimental results demonstrate a mean accuracy of 58.95% and a macro-F1 score of 0.438, highlighting the inherent difficulty of cross-subject EEG emotion recognition. Despite moderate accuracy, the proposed framework provides a more realistic evaluation compared to subject- dependent studies and establishes a robust baseline for generalizable emotion recognition. The findings confirm that adaptive graph construction improves functional brain connectivity representation while emphasizing the need for advanced generalization techniques such as domain adaptation and temporal modeling for future research.