Recent數據載入中... |
【應數系演講-104-10-16】A factor model for graph data
國立東華大學應用數學系 專 題 演 講 主講人:Dr. Wei-Fang Niu Institute of Statistics, National Chiao Tung University and 講 題:A factor model for graph data 時 間:104 年 10月 16日 (星期五) 15:20-17:00 地 點:理工一館 A324 會議室 摘 要 Graph data has been becoming an important channel towards exploring relations among a large number of subjects in the big data era. In past decades community structures have been found in many complex real-world networks and play a key role on the modeling of graph data, for example the stochastic block model and its extensions. However, recent studies unveil more sophisticated modules and typical examples include star and bipartite structures. In most graph models, these link-pattern modules are piled up in terms of multiple communities. This paper proposes a graph factor model in which each node is endowed with several (latent) features. Factors are channels for edge connections and can be characterized by link functions that map features of pairs of nodes to the edge probabilities. This model may naturally incorporate different kinds of link-pattern modules including communities, stars and bipartite structures. The inference for the model can be carried out through an MCMC procedure. Both synthetic data and real-world networks are used for numerical illustrations. Keywords: Social networks, random graph models, latent space network models
瀏覽數
|