Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis
For neuroscientists analyzing multimodal brain networks, SD3MF offers a supervised, interpretable method that outperforms deep learning baselines.
SD3MF extends unsupervised matrix factorization to supervised prediction over populations of multimodal brain graphs, outperforming CNNs and GNNs on connectome datasets while providing interpretable community-level features.
We present Supervised Deep Multimodal Matrix Factorization (SD3MF), an interpretable framework for integrative brain network analysis that generalizes Symmetric Nonnegative Matrix Tri-Factorization (SNMTF) from unsupervised single-graph clustering to supervised prediction over populations of multimodal graphs. SD3MF learns deep hierarchical factorizations for each modality together with a shared latent representation that aligns subjects across views. An encoder-decoder formulation jointly optimizes graph reconstruction and supervised prediction, while adaptive weights enable data-driven multimodal fusion. By representing each subject through community-level interaction matrices, the model yields interpretable and discriminative features. Experiments on multimodal connectome datasets show that SD3MF consistently outperforms strong deep learning baselines such as CNNs and GNNs, while enabling biologically interpretable insights. Code for reproducibility is available at: https://github.com/amjadseyedi/SD3MF.