Node Embedding via Word Embedding for Network Community Discovery
arXiv:1611.03028
Abstract
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.
This version has been accepted for publication in a joint special issue between IEEE JSTSP and TSIPN
References in corpus (5)
- Semi-Supervised Classification with Graph Convolutional Networks
- Stochastic blockmodels and community structure in networks
- Random Walks, Markov Processes and the Multiscale Modular Organization of Complex Networks
- Community detection in networks: Modularity optimization and maximum likelihood are equivalent
- Phase Transitions and a Model Order Selection Criterion for Spectral Graph Clustering