arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.02203q-bio.NCcs.LG
收藏

学习脑区的高阶关系

Learning High-Order Relationships of Brain Regions

Yale University(耶鲁大学);University of British Columbia(不列颠哥伦比亚大学);Vector Institute(矢量研究所)

Weikang Qiu, Huangrui Chu, Selena Wang, Haolan Zuo, Xiaoxiao Li, Yize Zhao, Rex Ying

AI总结:

本文提出 HYBRID 方法,通过 CONSTRUCTOR 和 WEIGHTER 从 fMRI 数据中提取最大信息量且最小冗余的脑区高阶关系,避免指数搜索,并在 CPM 协议下比现有最优模型平均提升 11.2%。

摘要:

从功能性磁共振成像(fMRI)信号中发现脑区之间可靠且具有信息量的关系对于表型预测至关重要。当前大多数方法未能准确刻画这些交互,因为它们只关注成对连接,而忽视了脑区的高阶关系。我们提出,这些高阶关系应当具有最大信息量且最小冗余(MIMR)。然而,由于搜索空间呈指数级增长且缺乏可处理的目标函数,识别此类高阶关系具有挑战性且尚未被充分探索。针对这一空白,我们提出了一种名为 HYBRID 的新方法,旨在从 fMRI 数据中提取 MIMR 高阶关系。HYBRID 使用 CONSTRUCTOR 来识别超边结构,并使用 WEIGHTER 为每条超边计算权重,从而避免了在指数空间中进行搜索。HYBRID 通过一种创新的信息瓶颈框架——多头丢弃瓶颈(multi-head drop-bottleneck)来实现 MIMR 目标,并具有理论保证。我们的综合实验证明了模型的有效性。在以 CPM(一种研究脑连接的标准协议)衡量超边质量时,我们的模型比最先进的预测模型平均高出 11.2%。

英文摘要:

Discovering reliable and informative relationships among brain regions from functional magnetic resonance imaging (fMRI) signals is essential in phenotypic predictions. Most of the current methods fail to accurately characterize those interactions because they only focus on pairwise connections and overlook the high-order relationships of brain regions. We propose that these high-order relationships should be maximally informative and minimally redundant (MIMR). However, identifying such high-order relationships is challenging and under-explored due to the exponential search space and the absence of a tractable objective. In response to this gap, we propose a novel method named HYBRID which aims to extract MIMR high-order relationships from fMRI data. HYBRID employs a CONSTRUCTOR to identify hyperedge structures, and a WEIGHTER to compute a weight for each hyperedge, which avoids searching in exponential space. HYBRID achieves the MIMR objective through an innovative information bottleneck framework named multi-head drop-bottleneck with theoretical guarantees. Our comprehensive experiments demonstrate the effectiveness of our model. Our model outperforms the state-of-the-art predictive model by an average of 11.2%, regarding the quality of hyperedges measured by CPM, a standard protocol for studying brain connections.

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。

↑