Approximate Clustering with Same-Cluster Queries
Abstract
Ashtiani et al. proposed a Semi-Supervised Active Clustering framework (SSAC), where the learner is allowed to make adaptive queries to a domain expert. The queries are of the kind "do two given points belong to the same optimal cluster?" There are many clustering contexts where such same-cluster queries are feasible. Ashtiani et al. exhibited the power of such queries by showing that any instance of the -means clustering problem, with additional margin assumption, can be solved efficiently if one is allowed same-cluster queries. This is interesting since the -means problem, even with the margin assumption, is -hard. In this paper, we extend the work of Ashtiani et al. to the approximation setting showing that a few of such same-cluster queries enables one to get a polynomial-time -approximation algorithm for the -means problem without any margin assumption on the input dataset. Again, this is interesting since the -means problem is -hard to approximate within a factor for a fixed constant . The number of same-cluster queries used is which is independent of the size of the dataset. Our algorithm is based on the -sampling technique. We also give a conditional lower bound on the number of same-cluster queries showing that if the Exponential Time Hypothesis (ETH) holds, then any such efficient query algorithm needs to make same-cluster queries. Our algorithm can be extended for the case when the oracle is faulty. Another result we show with respect to the -means++ seeding algorithm is that a small modification to the -means++ seeding algorithm within the SSAC framework converts it to a constant factor approximation algorithm instead of the well known -approximation algorithm.
Cite
@article{arxiv.1704.01862,
title = {Approximate Clustering with Same-Cluster Queries},
author = {Nir Ailon and Anup Bhattacharya and Ragesh Jaiswal and Amit Kumar},
journal= {arXiv preprint arXiv:1704.01862},
year = {2017}
}
Comments
Updated version has results for faulty queries