期刊
KNOWLEDGE AND INFORMATION SYSTEMS
卷 24, 期 3, 页码 393-413出版社
SPRINGER LONDON LTD
DOI: 10.1007/s10115-009-0255-6
关键词
Relational graph clustering; Heterogeneous links; Homogeneous links; Bregman divergences
资金
- U.S. National Science Foundation [IIS-0535162, IIS-0812114, IIS-0905215]
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [1017828, GRANTS:13814855] Funding Source: National Science Foundation
Relation graphs, in which multi-type (or single type) nodes are related to each other, frequently arise in many important applications, such as Web mining, information retrieval, bioinformatics, and epidemiology. In this study, We propose a general framework for clustering on relation graphs. Under this framework, we derive a family of clustering algorithms including both hard and soft versions, which are capable of learning cluster patterns from relation graphs with various structures and statistical properties. A number of classic approaches on special cases of relation graphs, such as traditional graphs with singly-type nodes and bi-type relation graphs with two types of nodes, can be viewed as special cases of the proposed framework. The theoretic analysis and experiments demonstrate the great potential and effectiveness of the proposed framework and algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据