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 1104.4803cs.LGstat.ML
收藏

基于凸优化的部分可观察图聚类

Clustering Partially Observed Graphs via Convex Optimization

The University of Texas at Austin(德克萨斯大学奥斯汀分校);National University of Singapore(新加坡国立大学)

Yudong Chen, Ali Jalali, Sujay Sanghavi, Huan Xu

摘要:

本文考虑了部分可观察的无权图的聚类问题,即,其中对于一些节点对,我们知道它们之间存在边,对于另一些节点对,我们知道没有边,而对于其余的节点对,我们不知道是否存在边。我们希望将节点组织到不相交的集群中,以便集群内有相对密集的(观察到的)连接性,而集群之间的连接性相对稀疏。我们采取了一种新颖而自然的方法来解决这个问题,通过集中精力寻找最小化“分歧”数量的聚类,即,簇内(观察到的)缺失边缘的数量和跨簇(观察到的)当前边缘的数量之和。我们的算法使用凸优化;其基础是将不一致最小化简化为从部分观察到的和恢复(未知)低秩矩阵和(未知)稀疏矩阵的问题。我们评估我们的算法在经典的种植分区/随机块模型的性能。我们的主要定理提供了充分条件,我们的算法作为一个函数的最小集群大小,边缘密度和观测概率的成功,特别是,结果表征观测概率和边缘密度差距之间的权衡。当有一个恒定数量的集群大小相等,我们的结果是最佳的对数因子。

英文摘要:

This paper considers the problem of clustering a partially observed unweighted graph---i.e., one where for some node pairs we know there is an edge between them, for some others we know there is no edge, and for the remaining we do not know whether or not there is an edge. We want to organize the nodes into disjoint clusters so that there is relatively dense (observed) connectivity within clusters, and sparse across clusters. We take a novel yet natural approach to this problem, by focusing on finding the clustering that minimizes the number of "disagreements"---i.e., the sum of the number of (observed) missing edges within clusters, and (observed) present edges across clusters. Our algorithm uses convex optimization; its basis is a reduction of disagreement minimization to the problem of recovering an (unknown) low-rank matrix and an (unknown) sparse matrix from their partially observed sum. We evaluate the performance of our algorithm on the classical Planted Partition/Stochastic Block Model. Our main theorem provides sufficient conditions for the success of our algorithm as a function of the minimum cluster size, edge density and observation probability; in particular, the results characterize the tradeoff between the observation probability and the edge density gap. When there are a constant number of clusters of equal size, our results are optimal up to logarithmic factors.

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。

↑