SAGN: Sparse Adaptive Gated Graph Neural Network With Graph Regularization for Identifying Dual-View Brain Networks

Due to the absence of a gold standard for threshold selection, brain networks constructed with inappropriate thresholds risk topological degradation or contain noise connections. Therefore, graph neural networks (GNNs) exhibit weak robustness and overfitting problems when identifying brain networks. Furthermore, existing studies have predominantly focused on strongly coupled connections, neglecting substantial evidence from other intricate systems that highlight the value of weakly coupled connections. Consequently, the potential of weakly coupled brain networks remains untapped. In this study, we pioneeringly construct weakly coupled brain networks and validate their values in emotion identification tasks. Subsequently, we propose a sparse adaptive gated GNN (SAGN) that can simultaneously perceive the valuable topology of dual-view (i.e., strongly coupled and weakly coupled) brain networks. The SAGN contains a sparse adaptive global receptive field. Moreover, SAGN employs a gated mechanism with feature enhancement and adaptive noise suppression capabilities. To address the lack of inductive bias and the large capacity of SAGN, a graph regularization term built with prior topology of dual-view brain networks is introduced to enhance generalization. Besides a public dataset (SEED), we also built a custom dataset (MuSer) with 60 subjects to evaluate weakly coupled brain networks' value and validate the SAGN's performance. Experiments demonstrate that brain physiological patterns associated with different emotional states are separable and rooted in weakly coupled brain networks. In addition, SAGN exhibits excellent generalization and robustness in identifying brain networks.