CS224W Reaction Paper and Proposal Project Title: Community Detection Using High-Order Structure

This project is to perform methodological and empirical research on community detection using local high-order structure. Intuitively, a community in social network is a group of people who interact with each other much more often than with the rest of the world. Community detection has been extensively studied in graph theory and network analysis, and there are tens of models and tools in performing that, such as spectral clustering, Personalized PageRange algorithms, and so on. Most of the previous works aim at finding the subset of nodes that has less incoming and outgoing edges than the edges within the subsets. However, high-order local structure, a.k.a., motif, may contain more information in community level, thus might give better result in community detection. In this project, we are going to examine the existing methods in community detection which analyze edges, and generalize them to fit the motif setting in community detection.