DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoon, Jisang | ko |
dc.contributor.author | Lee, Kangwook | ko |
dc.contributor.author | Suh, Changho | ko |
dc.date.accessioned | 2018-12-20T05:32:51Z | - |
dc.date.available | 2018-12-20T05:32:51Z | - |
dc.date.created | 2018-12-11 | - |
dc.date.created | 2018-12-11 | - |
dc.date.created | 2018-12-11 | - |
dc.date.issued | 2018-10-03 | - |
dc.identifier.citation | 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp.686 - 694 | - |
dc.identifier.uri | http://hdl.handle.net/10203/247918 | - |
dc.description.abstract | We study the problem of recovering both K communities and their features from a labeled graph observation. We assume that the edges of an observed graph are generated as per the symmetric Stochastic Block Model (SBM), and that the label of each node is a noisy and partially-observed version of the corresponding community feature. We characterize the information-theoretic limit of this problem, and then propose a computationally efficient algorithm that achieves the information-theoretic limit. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | On the joint recovery of community structure and community features | - |
dc.type | Conference | - |
dc.identifier.wosid | 000461021200097 | - |
dc.identifier.scopusid | 2-s2.0-85062821808 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 686 | - |
dc.citation.endingpage | 694 | - |
dc.citation.publicationname | 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Allerton Park & Retreat Center, Monticello | - |
dc.identifier.doi | 10.1109/ALLERTON.2018.8636058 | - |
dc.contributor.localauthor | Suh, Changho | - |
dc.contributor.nonIdAuthor | Yoon, Jisang | - |
dc.contributor.nonIdAuthor | Lee, Kangwook | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.