Variational Embeddings for Community Detection and Node Representation

TL;DR

This paper introduces VECoDeR, a generative model that jointly learns node embeddings and community detection, improving accuracy and efficiency in graph analysis tasks.

Contribution

The paper presents VECoDeR, a novel variational embedding model that simultaneously captures community structure and node representations in graphs.

Findings

Outperforms baseline methods in node classification and community detection

Efficient and robust across different hyperparameters

Effective for overlapping and non-overlapping communities

Abstract

In this paper, we study how to simultaneously learn two highly correlated tasks of graph analysis, i.e., community detection and node representation learning. We propose an efficient generative model called VECoDeR for jointly learning Variational Embeddings for Community Detection and node Representation. VECoDeR assumes that every node can be a member of one or more communities. The node embeddings are learned in such a way that connected nodes are not only "closer" to each other but also share similar community assignments. A joint learning framework leverages community-aware node embeddings for better community detection. We demonstrate on several graph datasets that VECoDeR effectively out-performs many competitive baselines on all three tasks i.e. node classification, overlapping community detection and non-overlapping community detection. We also show that VECoDeR is computationally efficient and has quite robust performance with varying hyperparameters.