vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
arXiv:1906.07159
Abstract
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.
Accepted Paper at NeurIPS 2019
References in corpus (12)
- Finding and evaluating community structure in networks
- Categorical Reparameterization with Gumbel-Softmax
- Probabilistic Latent Semantic Analysis
- Link communities reveal multiscale complexity in networks
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Clique percolation in random networks
- VERSE: Versatile Graph Embeddings from Similarity Measures
- Clustering with Multi-Layer Graphs: A Spectral Perspective
- Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts
- Infinite Edge Partition Models for Overlapping Community Detection and Link Prediction
- GEMSEC: Graph Embedding with Self Clustering
- CommunityGAN: Community Detection with Generative Adversarial Nets