Information Bottleneck-Guided Heterogeneous Graph Learning for Interpretable Neurodevelopmental Disorder Diagnosis

ArXi:2502.20769v3 Announce Type: replace Developing interpretable models for neurodevelopmental disorders (NDDs) diagnosis presents significant challenges in effectively encoding, decoding, and integrating multimodal neuroimaging data. While many existing machine learning approaches have shown promise in brain network analysis, they typically suffer from limited interpretability, particularly in extracting meaningful biomarkers from functional magnetic resonance imaging (fMRI) data and establishing clear relationships between imaging features and graphic characteristics.