Fast Exemplar-Based Clustering by Gravity Enrichment Between Data Objects

摘要

For the wide variety of emerging data in our daily life, realizing exemplar-based clustering effectively and understanding its clustering behavior appropriately become more desirable. In this paper, based on a new look at the Bayesian framework of data clustering, two new concepts are introduced and they correspond to a Bayesian information transmission system and its transmission learning. Facilitated by the new concepts, an exemplar-based transmission learning machine for clustering (ETLMC) is accordingly developed. As an attempt to explain the exemplar-based clustering behavior in a physics-based manner, ETLMC is well justified by revealing that the exemplar masses transfer between data objects during the clustering process can be governed by the proposed gravity enrichment effect rooted at Newton's law of gravity. Practically, ETLMC is distinctive in its easy implementation in terms of its global analytical solution, its fast exemplar finding for large scale data with arbitrary shapes, its easy parameter settings and its stable and efficient clustering results. Extensive experiments on synthetic and real datasets demonstrate the effectiveness of ETLMC, in contrast to a number of existing state-of-the-art clustering algorithms.