MAGNET：流形感知图扩散网络用于功能脑连接组生成
MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation
AI 导读
研究者提出 MAGNET，一种流形感知图扩散网络，利用相关矩阵流形的 normalized-Cholesky 表示生成有效脑功能连接组。在 ABIDE、ADNI 和 OASIS-3 三个数据集上，其类条件保真度（α,β-F1）较以往流形感知方法提升 7-21%，仅用二值标签训练即可在零样本设置下将子类协方差对齐（λ-MSE）提升超过 30%。代码仓库已开源。
正文 · 原文
Abstract:Functional brain connectome represents neural connectivity as a matrix of pairwise interactions between brain regions. Generation of functional connectomes is not only a question of validity; rather, having satisfied the constraints on the correlation matrix, the next step is to recover the class-conditional geometry buried under coarse labels. We propose MAGNET, a Manifold-Aware Graph Diffusion Network which uses a normalized-Cholesky representation of the manifold of correlation matrices that guarantees validity. MAGNET lifts noisy latent states into ROI-level region tokens and performs denoising with a relational inductive bias over brain atlas regions. To deal with structural problems induced by coarse labels, MAGNET employs class-anchored conditioning, amortized structural bridge, and relevance-preserving corruption. Across ABIDE, ADNI, and OASIS-3, MAGNET consistently achieves favorable results compared to previous manifold-aware approaches, demonstrating improvements of 7-21% in class-conditional fidelity ($\alpha,\beta$-F1) across three cohorts and better sampling efficiency. Moreover, while training only with strict binary labels, MAGNET is capable of maintaining clinical heterogeneity through fine substructure of the connectomes in a zero-shot setting, improving subclass covariance alignment ($\lambda$-MSE) by over 30%. These results suggest that geometric validity is a necessary but insufficient condition for clinical utility in connectome synthesis. Moreover, efforts in making the diffusion denoising class-conditional manifold aware finds utility beyond the highly curved brain connectome generation as this is a critical problem in various general settings. The code repository can be found at this https URL.
| Comments: | Accepted at NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.17014 [cs.LG] |
| (or arXiv:2610.17014v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17014 arXiv-issued DOI via DataCite |
Submission history
From: Protyay Dey [view email]
[v1]
Mon, 12 Oct 2026 15:56:09 UTC (22,487 KB)
[v2]
Sat, 24 Oct 2026 19:13:26 UTC (22,487 KB)
来源：arXiv cs.AI · arxiv.org