A Generic Distributed Clustering Framework for Massive Data

Abstract

In this paper, we introduce a novel Generic distributEd clustEring frameworK (GEEK) beyond $k$-means clustering to process massive amounts of data. To deal with different data types, GEEK first converts data in the original feature space into a unified format of buckets; then, we design a new Seeding method based on simILar bucKets (SILK) to determine initial seeds. Compared with state-of-the-art seeding methods such as $k$-means++ and its variants, SILK can automatically identify the number of initial seeds based on the closeness of shared data objects in similar buckets instead of pre-specifying $k$. Thus, its time complexity is independent of $k$. With these well-selected initial seeds, GEEK only needs a one-pass data assignment to get the final clusters. We implement GEEK on a distributed CPU-GPU platform for large-scale clustering. We evaluate the performance of GEEK over five large-scale real-life datasets and show that GEEK can deal with massive data of different types and is comparable to (or even better than) many state-of-the-art customized GPU-based methods, especially in large $k$ values.