A0171
Title: Network community detection using higher-order structures
Authors: Ji Zhu - University of Michigan (United States) [presenting]
Abstract: Many real-world networks commonly exhibit an abundance of subgraphs or higher-order structures, such as triangles and by-fans, surpassing what is typically observed in randomly generated networks. However, statistical models accounting for this phenomenon are limited, especially when community structure is of interest. This limitation is coupled with a lack of community detection methods that leverage subgraphs or higher-order structures. A novel community detection method is proposed that effectively incorporates these higher-order structures within a network. A finite-sample error bound is also developed for community detection accuracy under an edge-dependent network model, including community and triangle structures. This error bound is characterized by the expected triangle degree, leading to the proposed method's consistency. To our knowledge, this is the first statistical error bound and consistency result considering a single network's community detection under a network model with dependent edges. Through simulations and a real-world data example, it is demonstrated that our method reveals network communities otherwise obscured by methods that disregard higher-order structures.