arXiv：cs.LG· Siddharth Viswanath, Panayiotis Ketonis, Cassidy All, William Dai, Gabriel Escobedo, Christine Gao, Jeffrey Lee, Joao Felipe Rocha, Andrew J Steindl, Ian Adelstein, Michael Perlmutter, Dhananjay Bhaskar, Smita Krishnaswamy·· 6 小时前
BrainDyn：用动态限制映射的层束神经常微分方程预测与生成脑动力学
BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics
AI 导读
BrainDyn 是一种基于 cellular sheaf 的图神经常微分方程（ODE）网络，用从预测上下文窗口动态重算的限制映射替代固定映射，以学习到的线性变换建模脑区间通信。研究在静息态 fMRI、EEG 和 NEST 模拟活动上测试多区域预测与自回归生成脑瞬态，并预测受控扰动后的瞬态变化，BrainDyn 在各模态上均优于对比模型，其学习特征具有表达性、可解释性且与生物学一致。
正文
Authors:Siddharth Viswanath, Panayiotis Ketonis, Cassidy All, William Dai, Gabriel Escobedo, Christine Gao, Jeffrey Lee, Joao Felipe Rocha, Andrew J Steindl, Ian Adelstein, Michael Perlmutter, Dhananjay Bhaskar, Smita Krishnaswamy
Abstract:Brain activity unfolds as coordinated patterns across regions over time, and modeling these dynamics is a central goal in computational neuroscience. Because activity is distributed over connected brain regions, it is naturally represented on a graph whose nodes are brain regions or recording electrodes and whose edges capture relationships between these nodes, with message-passing modeling regional communication. However, standard message-passing networks place every node in a single shared feature space and typically aggregate messages from neighbors by scalar summation, which does not align with neurobiological evidence of brain communication. In order to model the heterogeneous nature of the brain, we introduce BrainDyn, a graph ordinary differential equation (ODE) network built on a cellular sheaf with dynamic restriction maps, recomputed from the forecasting context window rather than fixed once, mediating region-to-region communication through learned linear transformations that drive the time evolution of neural activity. We evaluate BrainDyn on resting-state fMRI, EEG, and simulated activity from the NEST simulator. Across these modalities, we test multi-region forecasting and autoregressive generation of brain transients, and, using NEST, prediction of altered transients following controlled perturbations. BrainDyn outperforms competing models across modalities, while analysis of the learned features shows that they are expressive, interpretable, and biologically aligned.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.19324 [cs.LG] |
| (or arXiv:2605.19324v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19324 arXiv-issued DOI via DataCite |
Submission history
From: Siddharth Viswanath [view email]
[v1]
Tue, 19 May 2026 04:03:01 UTC (727 KB)
[v2]
Wed, 14 Oct 2026 17:34:35 UTC (2,159 KB)
来源：arXiv：cs.LG · arxiv.org