VECoDeR - Variational Embeddings for Community Detection and Node Representation

Rayyan Ahmad Khan, Muhammad Umer Anwaar, Omran Kaddah, Martin Kleinsteuber

Keywords: Generative Models, Node representation, VECoDeR, Graph Neural Networks, Variational Embeddings

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 outperforms 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.

One-sentence Summary: A variational approach to jointly learn node and community embeddings for community detection and node representation.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ZH5ZmNkC7H