Structural Graphical Lasso for Learning Mouse Brain Connectivity

Handle URI:
http://hdl.handle.net/10754/575775
Title:
Structural Graphical Lasso for Learning Mouse Brain Connectivity
Authors:
Yang, Sen; Sun, Qian; Ji, Shuiwang; Wonka, Peter ( 0000-0003-0627-9746 ) ; Davidson, Ian; Ye, Jieping
Abstract:
Investigations into brain connectivity aim to recover networks of brain regions connected by anatomical tracts or by functional associations. The inference of brain networks has recently attracted much interest due to the increasing availability of high-resolution brain imaging data. Sparse inverse covariance estimation with lasso and group lasso penalty has been demonstrated to be a powerful approach to discover brain networks. Motivated by the hierarchical structure of the brain networks, we consider the problem of estimating a graphical model with tree-structural regularization in this paper. The regularization encourages the graphical model to exhibit a brain-like structure. Specifically, in this hierarchical structure, hundreds of thousands of voxels serve as the leaf nodes of the tree. A node in the intermediate layer represents a region formed by voxels in the subtree rooted at that node. The whole brain is considered as the root of the tree. We propose to apply the tree-structural regularized graphical model to estimate the mouse brain network. However, the dimensionality of whole-brain data, usually on the order of hundreds of thousands, poses significant computational challenges. Efficient algorithms that are capable of estimating networks from high-dimensional data are highly desired. To address the computational challenge, we develop a screening rule which can quickly identify many zero blocks in the estimated graphical model, thereby dramatically reducing the computational cost of solving the proposed model. It is based on a novel insight on the relationship between screening and the so-called proximal operator that we first establish in this paper. We perform experiments on both synthetic data and real data from the Allen Developing Mouse Brain Atlas; results demonstrate the effectiveness and efficiency of the proposed approach.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program; Visual Computing Center (VCC); Computer Science Program
Publisher:
Association for Computing Machinery (ACM)
Journal:
Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '15
Conference/Event name:
Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Issue Date:
2015
DOI:
10.1145/2783258.2783391
Type:
Conference Paper
Appears in Collections:
Conference Papers; Computer Science Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorYang, Senen
dc.contributor.authorSun, Qianen
dc.contributor.authorJi, Shuiwangen
dc.contributor.authorWonka, Peteren
dc.contributor.authorDavidson, Ianen
dc.contributor.authorYe, Jiepingen
dc.date.accessioned2015-08-24T09:25:51Zen
dc.date.available2015-08-24T09:25:51Zen
dc.date.issued2015en
dc.identifier.doi10.1145/2783258.2783391en
dc.identifier.urihttp://hdl.handle.net/10754/575775en
dc.description.abstractInvestigations into brain connectivity aim to recover networks of brain regions connected by anatomical tracts or by functional associations. The inference of brain networks has recently attracted much interest due to the increasing availability of high-resolution brain imaging data. Sparse inverse covariance estimation with lasso and group lasso penalty has been demonstrated to be a powerful approach to discover brain networks. Motivated by the hierarchical structure of the brain networks, we consider the problem of estimating a graphical model with tree-structural regularization in this paper. The regularization encourages the graphical model to exhibit a brain-like structure. Specifically, in this hierarchical structure, hundreds of thousands of voxels serve as the leaf nodes of the tree. A node in the intermediate layer represents a region formed by voxels in the subtree rooted at that node. The whole brain is considered as the root of the tree. We propose to apply the tree-structural regularized graphical model to estimate the mouse brain network. However, the dimensionality of whole-brain data, usually on the order of hundreds of thousands, poses significant computational challenges. Efficient algorithms that are capable of estimating networks from high-dimensional data are highly desired. To address the computational challenge, we develop a screening rule which can quickly identify many zero blocks in the estimated graphical model, thereby dramatically reducing the computational cost of solving the proposed model. It is based on a novel insight on the relationship between screening and the so-called proximal operator that we first establish in this paper. We perform experiments on both synthetic data and real data from the Allen Developing Mouse Brain Atlas; results demonstrate the effectiveness and efficiency of the proposed approach.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.titleStructural Graphical Lasso for Learning Mouse Brain Connectivityen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer Science Programen
dc.identifier.journalProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '15en
dc.conference.date10-13 August 2015en
dc.conference.nameProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Miningen
dc.conference.locationSydney, Australiaen
dc.contributor.institutionIDST at Alibaba Group, Seattle, WA, USAen
dc.contributor.institutionArizona State University, Tempe, AZ, USAen
dc.contributor.institutionOld Dominion University, Norfolk, VA, USAen
dc.contributor.institutionUniversity of California, Davis, CA, USAen
dc.contributor.institutionUniversity of Michigan, Ann Arbor, MI, USAen
kaust.authorWonka, Peteren
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.