Show simple item record

dc.contributor.authorYang, Sen
dc.contributor.authorSun, Qian
dc.contributor.authorJi, Shuiwang
dc.contributor.authorWonka, Peter
dc.contributor.authorDavidson, Ian
dc.contributor.authorYe, Jieping
dc.date.accessioned2015-08-24T09:25:51Z
dc.date.available2015-08-24T09:25:51Z
dc.date.issued2015-08-07
dc.identifier.citationYang S, Sun Q, Ji S, Wonka P, Davidson I, et al. (2015) Structural Graphical Lasso for Learning Mouse Brain Connectivity. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’15. Available: http://dx.doi.org/10.1145/2783258.2783391.
dc.identifier.doi10.1145/2783258.2783391
dc.identifier.urihttp://hdl.handle.net/10754/575775
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.
dc.description.sponsorshipNSF IIS-0953662, NSF III-1421100, NSF III-1421057
dc.publisherAssociation for Computing Machinery (ACM)
dc.subjectBrain networks
dc.subjectGraphical lasso
dc.subjectProximal operator
dc.subjectScreening
dc.subjectSecond-order method
dc.subjectTree-structural regularization
dc.titleStructural Graphical Lasso for Learning Mouse Brain Connectivity
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentComputer Science Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.contributor.departmentComputer Science Program
dc.identifier.journalProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '15
dc.conference.date2015-08-10 to 2015-08-13
dc.conference.name21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015
dc.conference.locationSydney, NSW, AUS
dc.eprint.versionPost-print
dc.contributor.institutionIDST, Alibaba Group, United States
dc.contributor.institutionArizona State University, United States
dc.contributor.institutionOld Dominion University, United States
dc.contributor.institutionUniversity of California, United States
dc.contributor.institutionUniversity of Michigan, United States
kaust.personWonka, Peter
refterms.dateFOA2018-06-14T08:33:24Z
dc.date.published-online2015-08-07
dc.date.published-print2015


Files in this item

Thumbnail
Name:
2015.KDD.Yang.StructuralGraphicalLasso.pdf
Size:
4.191Mb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record