Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.13312 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916009170960384 |
|---|---|
| author | Seyedi, Amjad He, Lifang Zhao, Songlin Onwunta, Akwum Gillis, Nicolas |
| author_facet | Seyedi, Amjad He, Lifang Zhao, Songlin Onwunta, Akwum Gillis, Nicolas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13312 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis Seyedi, Amjad He, Lifang Zhao, Songlin Onwunta, Akwum Gillis, Nicolas Machine Learning 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. |
| title | Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.13312 |