analiza aiqbench
This research introduces SD3MF, a novel framework that reconciles the accuracy of deep learning with the interpretability of matrix factorization for analyzing multimodal brain networks. By jointly optimizing graph reconstruction and supervised prediction, the model achieves superior performance over standard baselines while revealing biologically meaningful community structures. This advancement is significant for neuroscience applications requiring transparent, data-driven insights into complex connectome datasets.
Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis
arXiv:2605.13312v2 Announce Type: replace Abstract: Multimodal brain network analysis faces a persistent trade-off between predictive accuracy and interpretability. Deep neural networks achieve high accuracy but behave as black boxes that reveal little about the brain modules driving their decisions, whereas matrix factorization methods provide parts-based interpretability yet remain largely shallow, unsupervised, and restricted to a single view, integrating modalities through predefined or heuristic fusion rules. To bridge this gap with a formulation that couples hierarchical modeling capacity with structured, interpretable representations and data-driven fusion, 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 modalities. 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 {Convolutional Neural Networks and Graph Neural Networks}, while enabling biologically interpretable insights. Code for reproducibility is available at https://github.com/amjadseyedi/SD3MF.
Abstract:Multimodal brain network analysis faces a persistent trade-off between predictive accuracy and interpretability. Deep neural networks achieve high accuracy but behave as black boxes that reveal little about the brain modules driving their decisions, whereas matrix factorization methods provide parts-based interpretability yet remain largely shallow, unsupervised, and restricted to a single view, integrating modalities through predefined or heuristic fusion rules. To bridge this gap with a formulation that couples hierarchical modeling capacity with structured, interpretable representations and data-driven fusion, 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 modalities. 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 {Convolutional Neural Networks and Graph Neural Networks}, while enabling biologically interpretable insights. Code for reproducibility is available at this https URL.
Machine Learning (cs.LG)
arXiv:2605.13312 [cs.LG]
(or arXiv:2605.13312v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.13312 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 294 cuvinte
Subiecte conexe
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · 15 iul. 2026
How do neural networks regress cubic polynomials? Apparently, they use a trick invented in Milan 500 years ago
LessWrong · 22 iul. 2026
Cross-attention encoding models reveal dynamic spatiotemporal routing across human higher visual cortex
arXiv · 30 sept. 2026
Dialogue with Eliezer Yudkowsky on Neural Networks
LessWrong · 2 oct. 2026