2017/07/24 by Timothy La Fond, Geoffrey Sanders, La Fond, Timothy +5
Computer Science · Physics and Astronomy · #Complex Network Analysis Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Opinion Dynamics and Social Influence #Peer-to-Peer Network Technologies #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1708.08136
openalex publication_date 2017/07/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Dynamic networks, especially those representing social networks, undergo\nconstant evolution of their community structure over time. Nodes can migrate\nbetween different communities, communities can split into multiple new\ncommunities, communities can merge together, etc. In order to represent dynamic\nnetworks with evolving communities it is essential to use a dynamic model\nrather than a static one. Here we use a dynamic stochastic block model where\nthe underlying block model is different at different times. In order to\nrepresent the structural changes expressed by this dynamic model the network\nwill be split into discrete time segments and a clustering algorithm will\nassign block memberships for each segment. In this paper we show that using an\nensemble of clustering assignments accommodates for the variance in scalable\nclustering algorithms and produces superior results in terms of\npairwise-precision and pairwise-recall. We also demonstrate that the dynamic\nclustering produced by the ensemble can be visualized as a flowchart which\nencapsulates the community evolution succinctly.\n