ACM-GNN: Adaptive Cluster-Oriented Modularity Graph Neural Network for EEG Depression Detection

• Published in: IEEE transactions on computational social systems pp. 1 - 13
• Main Authors: Zhang, Tong, Hu, Tingting, Wu, Mengqi, Xu, Zihua, Philip Chen, C. L.
• Format: Journal Article
• Language: English
• Published: IEEE 2025
• Subjects: Adaptive systems; Brain modeling; Brain network modularity; Contrastive learning; Convolution; deep graph clustering; Depression; EEG depression detection; Electrodes; Electroencephalography; Feature extraction; graph interaction learning (GIL); Long short term memory; Nearest neighbor methods
• ISSN: 2329-924X; 2373-7476
• DOI: 10.1109/TCSS.2025.3576373

Major depressive disorder (MDD) is typically accompanied by varying topological dynamics across brain network modularity due to the influence of time-variant and subject-specific factors. Current works primarily characterize the electroencephalograms (EEG) topological relationships based on prior predefined brain regions. However, this predefined strategy cannot dynamically fit to different individuals, which may affect the adaptability of unseen individual for depression detection. This article proposes an adaptive cluster-oriented modularity graph neural network (ACM-GNN) to enhance the adaptability of individual topological interaction for depression detection. Specifically, a cluster-oriented modularity construction (CMC) module dynamically clusters EEG channels into different brain regions based on channel-pairs contrastive learning. It can adaptively construct brain modularity to fit different individual instances. Furthermore, a modularity graph interaction learning (MGIL) module performs multilayer graph information interaction between EEG globality and modularity levels. In this way, more powerful hierarchical information can be integrated by further aggregating representations at different levels. Experiments on two public datasets, MODMA and PRED+CT, demonstrate that the proposed method outperforms the state-of-the-art EEG depression detection methods. Finally, investigations on brain activities reveal the importance of dynamic modular relations for depression detection.