Active learning for top-K rank aggregation from noisy comparisons

Soheil Mohajer, Changho Suh, Adel Elmahdy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

We explore an active top-A" ranking problem based on pairwise comparisons that are collected possibly in a sequential manner as per our design choice. We consider two settings: (1) top-K sorting in which the goal is to recover the top-A" items in order out of n items; (2) top-K partitioning where only the set of top-A' items is desired. Under a fairly general model which subsumes as special cases various models (e.g., Strong Stochastic Transitivity model, BTL model and uniform noise model), we characterize upper bounds on the sample size required for top-A∗sorting as well as for top-A" partitioning. As a consequence, we demonstrate that active ranking can offer significant multiplicative gains in sample complexity over passive ranking. Depending on the underlying stochastic noise model, such gain varies from around logn/log log n to n2 log n/log log n. We also Present an algorithm that is applicable to both settings.

Original languageEnglish (US)
Title of host publication34th International Conference on Machine Learning, ICML 2017
PublisherInternational Machine Learning Society (IMLS)
Pages3842-3853
Number of pages12
ISBN (Electronic)9781510855144
StatePublished - 2017
Event34th International Conference on Machine Learning, ICML 2017 - Sydney, Australia
Duration: Aug 6 2017Aug 11 2017

Publication series

Name34th International Conference on Machine Learning, ICML 2017
Volume5

Other

Other34th International Conference on Machine Learning, ICML 2017
CountryAustralia
CitySydney
Period8/6/178/11/17

Bibliographical note

Funding Information:
The authors would like to thank the reviewers who gave useful comments. C. Suh was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP; Ministry of Science, ICT & Future Planning) (No. 2015R1C1A1A02036561).

Fingerprint Dive into the research topics of 'Active learning for top-K rank aggregation from noisy comparisons'. Together they form a unique fingerprint.

Cite this