Unsupervised Learning of Joint Embeddings for Node Representation and Community Detection

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

Abstract: In graph analysis community detection and node representation learning are two highly correlated tasks. In this work, we propose an efficient generative model called J-ENC for learning Joint Embedding for Node representation and Community detection. J-ENC learns a community-aware node representation, i.e., learning of the node embeddings are constrained in such a way that connected nodes are not only “closer” to each other but also share similar community assignments. This joint learning framework leverages community-aware node embeddings for better performance on these tasks: node classification, overlapping community detection and non-overlapping community detection. We demonstrate on several graph datasets that J-ENC effectively outperforms many competitive baselines on these tasks. Furthermore, we show that J-ENC not only has quite robust performance with varying hyperparameters but also is computationally efficient than its competitors.