Node Embedding via Word Embedding for Network Community Discovery
This work addresses the problem of community discovery in networks for researchers and practitioners, offering incremental improvements over existing methods.
The paper tackles unsupervised community discovery in graphs by leveraging neural node embeddings, demonstrating consistent improvements over state-of-the-art methods. Specifically, it attains information-theoretic limits for community recovery under Stochastic Block Models and shows better stability and accuracy compared to Spectral Clustering and Acyclic Belief Propagation.
Neural node embeddings have recently emerged as a powerful representation for supervised learning tasks involving graph-structured data. We leverage this recent advance to develop a novel algorithm for unsupervised community discovery in graphs. Through extensive experimental studies on simulated and real-world data, we demonstrate that the proposed approach consistently improves over the current state-of-the-art. Specifically, our approach empirically attains the information-theoretic limits for community recovery under the benchmark Stochastic Block Models for graph generation and exhibits better stability and accuracy over both Spectral Clustering and Acyclic Belief Propagation in the community recovery limits.