TL;DR提出了一种在分布式环境下运行的算法来解决部分聚类问题,包括 k 中心,k 中位数和 k 均值等,旨在提高通信效率和解决噪音和数据不确定性带来的影响。
Abstract
Recent years have witnessed an increasing popularity of algorithm design for
distributed data, largely due to the fact that massive datasets are often
collected and stored in different locations. In the distributed setting
communication typically dominates the query processing time. Th