Paper Info
Title
Semisupervised Clustering by Queries and Locally Encodable Source Coding
Abstract
Source coding is the canonical problem of data compression in information theory. In a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">locally encodable</i> source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semisupervised clustering is equivalent to locally encodable source coding. In this model, the task is to perform multiclass labeling of unlabeled elements. At the beginning, we can ask in parallel a set of simple queries to an oracle who provides (possibly erroneous) binary answers to the queries. The queries cannot involve more than two (or a fixed constant number of) elements. Now the labeling of all the elements (or clustering) must be performed based on the noisy query answers. The goal is to recover all the correct labelings while minimizing the number of such queries. The equivalence to locally encodable source codes leads us to find lower bounds on the number of queries required in variety of scenarios. We provide querying schemes based on pairwise ‘same cluster’ queries - and pairwise AND queries, and show provable performance guarantees for each of the schemes.
Year
DOI
Venue
2019
10.1109/TIT.2020.3037533
IEEE Transactions on Information Theory
Keywords
DocType
Volume
Local encoding,source coding,data compression,semi-supervised clustering,‘same-cluster’ queries
Journal
67
Issue
ISSN
Citations 
2
0018-9448
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Arya Mazumdar130741.81
Soumyabrata Pal223.76