arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1702.00196cs.DScs.LG
收藏

通信最优分布式聚类

Communication-Optimal Distributed Clustering

Indiana University(印第安纳大学);University of Bristol(布里斯托大学);IBM Research Almaden(IBM阿尔马登研究院)

Jiecao Chen, He Sun, David P. Woodruff, Qin Zhang

摘要:

聚类大数据集是机器学习中许多应用的基本问题。数据通常在不同的站点上收集,并且需要以低通信的分布式方式执行集群。我们希望分布式设置中的集群质量与集中式设置中的集群质量相匹配,因为集中式设置中的所有数据都驻留在单个站点上。在这项工作中,我们研究了两个分布式模型中的图和几何聚类问题:(1)点对点模型,和(2)广播信道模型。我们给协议在这两个模型中,我们证明几乎匹配的通信下界是接近最优的。我们的工作突出了令人惊讶的权力的广播信道的集群问题,粗略地说,频谱集群$n$点或$n$顶点分布在一个图形中的$s$服务器,最坏情况下的分区的通信复杂性在点对点模型是$n \cdot s$,而在广播模型是$n + s$。类似的现象也适用于几何设置。我们实现了我们的算法,并在现实生活中的数据集上展示了这种现象,表明我们的算法在实践中也非常有效。

英文摘要:

Clustering large datasets is a fundamental problem with a number of applications in machine learning. Data is often collected on different sites and clustering needs to be performed in a distributed manner with low communication. We would like the quality of the clustering in the distributed setting to match that in the centralized setting for which all the data resides on a single site. In this work, we study both graph and geometric clustering problems in two distributed models: (1) a point-to-point model, and (2) a model with a broadcast channel. We give protocols in both models which we show are nearly optimal by proving almost matching communication lower bounds. Our work highlights the surprising power of a broadcast channel for clustering problems; roughly speaking, to spectrally cluster $n$ points or $n$ vertices in a graph distributed across $s$ servers, for a worst-case partitioning the communication complexity in a point-to-point model is $n \cdot s$, while in the broadcast model it is $n + s$. A similar phenomenon holds for the geometric setting as well. We implement our algorithms and demonstrate this phenomenon on real life datasets, showing that our algorithms are also very efficient in practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑