A Spectral Algorithm with Additive Clustering for the Recovery of Overlapping Communities in Networks
This addresses the challenge of detecting overlapping communities in networks, which is important for applications like social network analysis, but the approach is incremental as it builds on existing spectral methods.
The paper tackles the problem of identifying overlapping communities in networks by proposing a spectral algorithm with additive clustering, which is proven to be consistent under a stochastic blockmodel with overlap and performs well on simulated and real-world data.
This paper presents a novel spectral algorithm with additive clustering designed to identify overlapping communities in networks. The algorithm is based on geometric properties of the spectrum of the expected adjacency matrix in a random graph model that we call stochastic blockmodel with overlap (SBMO). An adaptive version of the algorithm, that does not require the knowledge of the number of hidden communities, is proved to be consistent under the SBMO when the degrees in the graph are (slightly more than) logarithmic. The algorithm is shown to perform well on simulated data and on real-world graphs with known overlapping communities.