NexusNet: Lightweight Graph Modeling for Motor-Imagery-Based Brain–Computer Interfaces

Motor imagery-based brain-computer interfaces (MI-BCIs) hold significant potential for integration into Internet of Things (IoT) environments, enabling seamless interaction with users and external devices. In MI decoding, graph neural networks (GNNs) are increasingly employed due to their capacity to model the structures of non-grid data. However, current GNN approaches predominantly emphasize pairwise relationships, failing to account for the multi-node interactions essential for accurate decoding. To overcome these limitations, we propose NexusNet, a lightweight graph modeling network tailored for MI-BCI and IoT integration. NexusNet incorporates multi-node routing and Nexus Fusion, facilitating the modeling of intricate relationships that extend beyond pairwise connections. It effectively captures global information using a shortest path algorithm while complementing it with localized neighboring relationships. This architecture ensures efficient feature extraction and decoding while maintaining low computational overhead, making it suitable for resource-constrained scenarios. Experimental evaluations demonstrate that NexusNet achieves state-of-the-art performance, attaining 78.78% accuracy on BCIC-IV-2a, 87.21% on BCIC-IV-2b, and 94.12% on High Gamma Dataset with only 3.44K learnable parameters and 0.88M floating-point operations. These results highlight its potential for practical applications. Further analyses validate the contributions of its multi-node components, with visualizations illustrating their indispensable roles in decoding. NexusNet represents a step forward in connecting MI-BCI research with practical IoT deployment. Our code is available at https://github.com/ZikaiVan/NexusNet.