Discovering B-Coupling Relationships in the Bipartite Hypergraph through Link Prediction in the Unimodal Graph

被引:0
作者
Kim, Bo Bae [1 ]
Jeong, Hyun Ji [1 ]
Kim, Myoung Ho [1 ]
机构
[1] Korea Inst Sci & Technol KAIST, Dept Comp Sci, 373-1 Guseong Dong, Daejeon 305701, South Korea
来源
2017 2ND IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA ANALYSIS (ICCCBDA 2017) | 2017年
基金
新加坡国家研究基金会;
关键词
bipartite graph; unimodal graph; hyperedges; recommendation systems;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
There are great demands in various applications on discovering unknown relationships in graphs that have not been found yet or will appear in the near future. The B-coupling relationship is one of predictable relationships in bipartite graphs. Some previous works predict B-coupling relationships by using a unimodal graph. The unimodal graph includes only one node type where links denote B-coupling relationships in the original bipartite graph. In some previous works, there are some restrictions because they consider bipartite graphs including only simple edges. However, in the real world, there are many applications to be modeled by hyperedges. In this paper, we propose a method that predicts B-coupling relationships in a bipartite graph including hyperedges. Moreover, we also recommend coupling nodes by using predicted links in the unimodal graph. We show through various experiments that our B-coupling prediction outperforms other method proposed earlier.
引用
收藏
页码:288 / 292
页数:5
相关论文
共 5 条
  • [1] [Anonymous], 2005, P 5 ACM IEEE CS JOIN
  • [2] [Anonymous], ADV SOC NETW AN MIN
  • [3] Borgatti S.P., 2009, ENCY COMPLEXITY SYST, V6
  • [4] Link prediction based on structural properties of online social networks
    Murata, Tsuyoshi
    Moriyasu, Sakiko
    [J]. NEW GENERATION COMPUTING, 2008, 26 (03) : 245 - 257
  • [5] Yu Hasun, 2015, P ACM 9 INT WORKSH D