vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
This work addresses the need for integrated graph analysis methods that capture both global and local structures, offering a flexible framework that can be extended to hierarchical community detection.
The paper tackled the joint problem of community detection and node representation learning in graphs by proposing vGraph, a generative model that collaboratively learns both tasks, achieving improved performance over competitive baselines in experiments on real-world graphs.
This paper focuses on two fundamental tasks of graph analysis: community detection and node representation learning, which capture the global and local structures of graphs, respectively. In the current literature, these two tasks are usually independently studied while they are actually highly correlated. We propose a probabilistic generative model called vGraph to learn community membership and node representation collaboratively. Specifically, we assume that each node can be represented as a mixture of communities, and each community is defined as a multinomial distribution over nodes. Both the mixing coefficients and the community distribution are parameterized by the low-dimensional representations of the nodes and communities. We designed an effective variational inference algorithm which regularizes the community membership of neighboring nodes to be similar in the latent space. Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks. We show that the framework of vGraph is quite flexible and can be easily extended to detect hierarchical communities.