DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Daesung | ko |
dc.contributor.author | Chung, Hye Won | ko |
dc.date.accessioned | 2020-09-18T04:16:00Z | - |
dc.date.available | 2020-09-18T04:16:00Z | - |
dc.date.created | 2020-08-10 | - |
dc.date.created | 2020-08-10 | - |
dc.date.created | 2020-08-10 | - |
dc.date.issued | 2020-06-21 | - |
dc.identifier.citation | IEEE International Symposium on Information Theory (ISIT), pp.2551 - 2555 | - |
dc.identifier.issn | 2157-8095 | - |
dc.identifier.uri | http://hdl.handle.net/10203/276208 | - |
dc.description.abstract | We consider the crowdsourced classification of m binary labels with XOR queries that ask whether the number of objects having a given attribute in the chosen subset of size d is even or odd. The subset size d, which we call query degree, can be varying over queries. Since a worker needs to make more efforts to answer a query of a higher degree, we consider a noise model where the accuracy of worker's answer changes depending both on the worker reliability and query degree d. For this general model, we characterize the information-theoretic limit on the optimal number of queries to reliably recover m labels in terms of a given combination of degree-d queries and noise parameters. Further, we propose an efficient inference algorithm that achieves this limit even when the noise parameters are unknown.(1) | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Crowdsourced Classification with XOR Queries: An Algorithm with Optimal Sample Complexity | - |
dc.type | Conference | - |
dc.identifier.wosid | 000714963402109 | - |
dc.identifier.scopusid | 2-s2.0-85090400454 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 2551 | - |
dc.citation.endingpage | 2555 | - |
dc.citation.publicationname | IEEE International Symposium on Information Theory (ISIT) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual Online Conference | - |
dc.identifier.doi | 10.1109/ISIT44484.2020.9174227 | - |
dc.contributor.localauthor | Chung, Hye Won | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.