SpecRp: A spectral-based community embedding algorithm

Abstract

Community embeddings are useful in node classification since they allow nodes to aggregate relevant information regarding the network structure. Modularity maximization-based algorithms are the most common approach to detect communities in networks. Moreover, spectral theory plays an important role in community detection by providing a matrix representation of the network structure. However, the literature is still scarce on spectral and modularity maximization-based community embedding methods. Besides, the node features of attributed graphs are usually not considered for producing the community embeddings. This paper introduces a community embedding algorithm based on spectral theory, called SpecRp, that has an overlapping modularity maximization-based step also herein proposed. SpecRp is a community detection method that considers node attributes and vertex proximity to obtain community embeddings. Computational experiments showed that SpecRp outperformed the literature in most of the tested benchmark datasets for the node classification task. Moreover, we observed that to detect disjoint communities, SpecRp and the reference literature algorithms presented a conflicting behavior concerning performance measures. While the reference methods achieved better results for modularity, SpecRp performed better concerning the Normalized Mutual Information to the ground-truth partitions. On detecting overlapping communities, SpecRp was considerably faster than the state-of-the-art algorithms, despite presenting worse results in most of the datasets.