English

Temporal Clustering

Data Structures and Algorithms 2017-10-17 v1 Computational Geometry

Abstract

We study the problem of clustering sequences of unlabeled point sets taken from a common metric space. Such scenarios arise naturally in applications where a system or process is observed in distinct time intervals, such as biological surveys and contagious disease surveillance. In this more general setting existing algorithms for classical (i.e.~static) clustering problems are not applicable anymore. We propose a set of optimization problems which we collectively refer to as 'temporal clustering'. The quality of a solution to a temporal clustering instance can be quantified using three parameters: the number of clusters kk, the spatial clustering cost rr, and the maximum cluster displacement δ\delta between consecutive time steps. We consider spatial clustering costs which generalize the well-studied kk-center, discrete kk-median, and discrete kk-means objectives of classical clustering problems. We develop new algorithms that achieve trade-offs between the three objectives kk, rr, and δ\delta. Our upper bounds are complemented by inapproximability results.

Keywords

Cite

@article{arxiv.1704.05964,
  title  = {Temporal Clustering},
  author = {Tamal K. Dey and Alfred Rossi and Anastasios Sidiropoulos},
  journal= {arXiv preprint arXiv:1704.05964},
  year   = {2017}
}

Comments

27 pages, 10 figures