Learning Pretopological Spaces to Extract Ego-Centered Communities

摘要：

　　We present a pretopological based approach to extract egocentered communities.Classical methods often consider only one structural feature of the network,whereas pretopology enables to do multicriteria analysis.Our approach consists in learning a logical combination of networks descriptors to define a pretopological space.Ego-centered communities are extracted by computing the elementary closure of each node.The quality of such communities is evaluated against the ground truth communities.We show the benefits of our method by comparing it to others on both real and synthetic networks.

关键词： Community extraction Pretopology Ego-centered communities

作者: Ga(e)tan Caillaut Guillaume Cleuziou Nicolas Dugué

作者单位: Université dOrléans,INSA Centre Val de Loire,LIFO EA 4022,Orléans,France Le Mans Université,LIUM,EA 4023,Le Mans,France

会议类型: 国际会议

会议名称: The 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (第23届亚太知识发现和数据挖掘国际会议(PAKDD2019)

会议地点: 澳门

会议语种:英文

页码: 488-500

在线出版日期: 2019-04-14（万方平台首次上网日期，不代表论文的发表时间）