用深度多模态分解模型，让脑网络分析更可解释且预测更准。
Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis
- 通过深度层次因子分解融合多模态脑网络数据
- 在多模态连接组数据上优于CNN、GNN等基线模型
- 输出可解释的社区级交互特征，适合神经科学探索
我们提出监督式深度多模态矩阵分解（SD3MF），一种可解释的整合脑网络分析框架，将对称非负矩阵三因子分解（SNMTF）从无监督单图聚类推广至多模态图上的监督预测。SD3MF为每种模态学习深层层次因子分解，并共享跨视图的潜在表示以对齐受试者。采用编码器-解码器结构联合优化图重建与监督预测，自适应权重实现数据驱动的多模态融合。通过社区级交互矩阵表示每位受试者，模型生成可解释且判别性强的特征。在多模态连接组数据集上的实验表明，SD3MF持续优于强基线深度学习模型（如CNN、GNN），同时提供生物学可解释性洞察。代码已开源：https://github.com/amjadseyedi/SD3MF。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。