Unsupervised Learning of Joint Embeddings for Node Representation and Community Detection

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 hyper-parameters but also is computationally efficient than its competitors.