当前位置:
X-MOL 学术
›
arXiv.cs.CV
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Multi-View Brain HyperConnectome AutoEncoder For Brain State Classification
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-09-24 , DOI: arxiv-2009.11553 Alin Banka, Inis Buzi and Islem Rekik
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-09-24 , DOI: arxiv-2009.11553 Alin Banka, Inis Buzi and Islem Rekik
Graph embedding is a powerful method to represent graph neurological data
(e.g., brain connectomes) in a low dimensional space for brain connectivity
mapping, prediction and classification. However, existing embedding algorithms
have two major limitations. First, they primarily focus on preserving
one-to-one topological relationships between nodes (i.e., regions of interest
(ROIs) in a connectome), but they have mostly ignored many-to-many
relationships (i.e., set to set), which can be captured using a hyperconnectome
structure. Second, existing graph embedding techniques cannot be easily adapted
to multi-view graph data with heterogeneous distributions. In this paper, while
cross-pollinating adversarial deep learning with hypergraph theory, we aim to
jointly learn deep latent embeddings of subject0specific multi-view brain
graphs to eventually disentangle different brain states. First, we propose a
new simple strategy to build a hyperconnectome for each brain view based on
nearest neighbour algorithm to preserve the connectivities across pairs of
ROIs. Second, we design a hyperconnectome autoencoder (HCAE) framework which
operates directly on the multi-view hyperconnectomes based on hypergraph
convolutional layers to better capture the many-to-many relationships between
brain regions (i.e., nodes). For each subject, we further regularize the
hypergraph autoencoding by adversarial regularization to align the distribution
of the learned hyperconnectome embeddings with that of the input
hyperconnectomes. We formalize our hyperconnectome embedding within a geometric
deep learning framework to optimize for a given subject, thereby designing an
individual-based learning framework. Our experiments showed that the learned
embeddings by HCAE yield to better results for brain state classification
compared with other deep graph embedding methods methods.
中文翻译:
用于大脑状态分类的多视图大脑超连接组自动编码器
图嵌入是一种在低维空间中表示图神经学数据(例如,大脑连接组)的强大方法,用于大脑连接映射、预测和分类。然而,现有的嵌入算法有两个主要限制。首先,他们主要关注保持节点之间的一对一拓扑关系(即连接组中的感兴趣区域(ROI)),但他们大多忽略了多对多关系(即设置到设置),可以使用超连接组结构捕获。其次,现有的图嵌入技术不能轻易适应具有异构分布的多视图图数据。在本文中,在用超图理论异花授粉对抗性深度学习的同时,我们的目标是共同学习特定主题的多视图大脑图的深层潜在嵌入,以最终解开不同的大脑状态。首先,我们提出了一种新的简单策略,基于最近邻算法为每个大脑视图构建超连接组,以保持 ROI 对之间的连接性。其次,我们设计了一个超连接组自动编码器 (HCAE) 框架,该框架直接在基于超图卷积层的多视图超连接组上运行,以更好地捕获大脑区域(即节点)之间的多对多关系。对于每个主题,我们通过对抗性正则化进一步规范超图自动编码,以将学习到的超连接组嵌入的分布与输入超连接组的分布对齐。我们将嵌入几何深度学习框架的超连接组形式化,以针对给定主题进行优化,从而设计基于个人的学习框架。我们的实验表明,与其他深度图嵌入方法方法相比,HCAE 学习的嵌入对大脑状态分类产生了更好的结果。
更新日期:2020-09-25
中文翻译:
用于大脑状态分类的多视图大脑超连接组自动编码器
图嵌入是一种在低维空间中表示图神经学数据(例如,大脑连接组)的强大方法,用于大脑连接映射、预测和分类。然而,现有的嵌入算法有两个主要限制。首先,他们主要关注保持节点之间的一对一拓扑关系(即连接组中的感兴趣区域(ROI)),但他们大多忽略了多对多关系(即设置到设置),可以使用超连接组结构捕获。其次,现有的图嵌入技术不能轻易适应具有异构分布的多视图图数据。在本文中,在用超图理论异花授粉对抗性深度学习的同时,我们的目标是共同学习特定主题的多视图大脑图的深层潜在嵌入,以最终解开不同的大脑状态。首先,我们提出了一种新的简单策略,基于最近邻算法为每个大脑视图构建超连接组,以保持 ROI 对之间的连接性。其次,我们设计了一个超连接组自动编码器 (HCAE) 框架,该框架直接在基于超图卷积层的多视图超连接组上运行,以更好地捕获大脑区域(即节点)之间的多对多关系。对于每个主题,我们通过对抗性正则化进一步规范超图自动编码,以将学习到的超连接组嵌入的分布与输入超连接组的分布对齐。我们将嵌入几何深度学习框架的超连接组形式化,以针对给定主题进行优化,从而设计基于个人的学习框架。我们的实验表明,与其他深度图嵌入方法方法相比,HCAE 学习的嵌入对大脑状态分类产生了更好的结果。