Efficiently detecting overlapping communities using seeding and semi-supervised learning

Seeding then expanding is a commonly used scheme to discover overlapping communities from a network. Most seeding methods existed are either too complexity to scale to large networks or too simple to select high-quality seeds; and the non-principled functions used by most expanding methods lead the poor performances when applied them on diverse networks. This paper proposes a new method which transforms a network into a corpus where each edge is treated as a document, all nodes of the network are treated as terms of the corpus. An effective seeding method is also proposed which selects seeds as a training set, then a principled expanding method based on semi-supervised learning is applied to classify edges. We compare our new algorithm with four other community detection algorithms on a wide range of synthetic and empirical networks, the experimental results show that the new algorithm can significantly improve the clustering performance, sometimes nearly makes double promotion. Furthermore, the time complexity of the new algorithm is linear to the number of edges, which makes it scale to analyze large networks.