English

Approximate Clustering with Same-Cluster Queries

Data Structures and Algorithms 2017-10-05 v3

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 kk-means clustering problem, with additional margin assumption, can be solved efficiently if one is allowed O(k2logk+klogn)O(k^2 \log{k} + k \log{n}) same-cluster queries. This is interesting since the kk-means problem, even with the margin assumption, is NP\mathsf{NP}-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 (1+ε)(1 + \varepsilon)-approximation algorithm for the kk-means problem without any margin assumption on the input dataset. Again, this is interesting since the kk-means problem is NP\mathsf{NP}-hard to approximate within a factor (1+c)(1 + c) for a fixed constant 0<c<10 < c < 1. The number of same-cluster queries used is poly(k/ε)\textrm{poly}(k/\varepsilon) which is independent of the size nn of the dataset. Our algorithm is based on the D2D^2-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 Ω(kpolylogk)\Omega \left(\frac{k}{poly \log k} \right) same-cluster queries. Our algorithm can be extended for the case when the oracle is faulty. Another result we show with respect to the kk-means++ seeding algorithm is that a small modification to the kk-means++ seeding algorithm within the SSAC framework converts it to a constant factor approximation algorithm instead of the well known O(logk)O(\log{k})-approximation algorithm.

Keywords

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

R2 v1 2026-06-22T19:09:46.167Z