arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.09175cs.LG
收藏

超越成对连接:在全局约束下提取高阶功能脑网络结构

Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints

College of Computer and Information Science, Southwest University(西南大学计算机与信息科学学院);Chongqing Key Laboratory of Brain-Inspired Cognitive Computing and Educational Rehabilitation for Children with Special Needs, Chongqing Normal University(重庆脑启发认知计算与特殊需要儿童教育康复重点实验室,重庆师范大学);School of Science, Guangxi University of Science and Technology(广西科技大学科学学院);College of Computer and Information Science, Chongqing Normal University(重庆师范大学计算机与信息科学学院)

Ling Zhan, Junjie Huang, Xiaoyao Yu, Wenyu Chen, Tao Jia

AI总结:

本文提出在全局约束下提取高阶功能脑网络结构的GCM框架,结合4种全局约束支持4级建模分辨率,在准确率和计算效率上显著优于现有方法,为认知神经科学跨学科应用奠定基础。

摘要:

功能脑网络(FBN)建模通常依赖于局部成对交互,本文从理论上分析了其在捕捉高阶依赖性方面的局限。同时,当前超图建模方法的计算负担和启发式特性阻碍了直接从数据分布中端到端学习FBN结构。为此,我们提出在全局约束下提取高阶FBN结构,并将其实现为面向全局约束的多分辨率(GCM)FBN结构学习框架。该框架结合了4种全局约束(信号同步、受试者身份、预期边数和数据标签),以支持对4个不同建模分辨率级别(样本/受试者/群体/项目)的FBN结构进行学习。实验结果表明,与9个基线和10个最先进方法相比,GCM在5个数据集和2种任务设置下,相对准确率最高提升30.6%,计算时间减少96.3%。大量实验验证了各组件的贡献,并突显了GCM的可解释性。这项工作为FBN结构学习提供了新视角,并为认知神经科学的跨学科应用奠定了基础。代码公开于 https://github.com/lzhan94swu/GCM。

英文摘要:

Functional brain network (FBN) modeling often relies on local pairwise interactions, whose limitation in capturing high-order dependencies is theoretically analyzed in this paper. Meanwhile, the computational burden and heuristic nature of current hypergraph modeling approaches hinder end-to-end learning of FBN structures directly from data distributions. To address this, we propose to extract high-order FBN structures under global constraints, and implement this as a Global Constraints oriented Multi-resolution (GCM) FBN structure learning framework. It incorporates 4 types of global constraint (signal synchronization, subject identity, expected edge numbers, and data labels) to enable learning FBN structures for 4 distinct levels (sample/subject/group/project) of modeling resolution. Experimental results demonstrate that GCM achieves up to a 30.6% improvement in relative accuracy and a 96.3% reduction in computational time across 5 datasets and 2 task settings, compared to 9 baselines and 10 state-of-the-art methods. Extensive experiments validate the contributions of individual components and highlight the interpretability of GCM. This work offers a novel perspective on FBN structure learning and provides a foundation for interdisciplinary applications in cognitive neuroscience. Code is publicly available on https://github.com/lzhan94swu/GCM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑