Locally Boosted Graph Aggregation for Community Detection
It addresses the challenge of noisy and large-scale data in community detection, but appears incremental as it builds on previous work with local quality measurements.
The paper tackles the problem of learning robust graph representations from noisy, multi-source data for community detection by proposing a boosting-inspired framework that combines weak evidence into a similarity metric, with empirical results showing utility on real datasets.
Learning the right graph representation from noisy, multi-source data has garnered significant interest in recent years. A central tenet of this problem is relational learning. Here the objective is to incorporate the partial information each data source gives us in a way that captures the true underlying relationships. To address this challenge, we present a general, boosting-inspired framework for combining weak evidence of entity associations into a robust similarity metric. Building on previous work, we explore the extent to which different local quality measurements yield graph representations that are suitable for community detection. We present empirical results on a variety of datasets demonstrating the utility of this framework, especially with respect to real datasets where noise and scale present serious challenges. Finally, we prove a convergence theorem in an ideal setting and outline future research into other application domains.