A Framework for Accurate Community Detection on Signed Networks Using Adversarial Learning

David Y. Kang, Woncheol Lee, Yeon-Chang Lee, Kyungsik Han, Sang-Wook Kim

Abstract: In this article, we propose a framework for embedding-based community detection on signed networks, namely <u><i>A</i></u> dversarial learning of <u><i>B</i></u> alanced triangle for <u><i>C</i></u> ommunity detection, in short <inline-formula><tex-math notation="LaTeX">${{\sf ABC}}$</tex-math></inline-formula> . It first represents all the nodes of a signed network as vectors in low-dimensional embedding space and conducts a clustering algorithm (e.g., <i>k</i> -means) on vectors, thereby detecting a community structure in the network. When performing the embedding process, <inline-formula><tex-math notation="LaTeX">${{\sf ABC}}$</tex-math></inline-formula> learns only the edges belonging to balanced triangles whose edge signs follow the balance theory, significantly excluding noise edges in learning. To address the sparsity of balanced triangles in a signed network, <inline-formula><tex-math notation="LaTeX">${{\sf ABC}}$</tex-math></inline-formula> learns not only the edges in balanced <i>real</i> -triangles but those in balanced <i>virtual</i> -triangles that do not actually exist but are produced by our generator. Finally, <inline-formula><tex-math notation="LaTeX">${{\sf ABC}}$</tex-math></inline-formula> employs adversarial learning to generate more-realistic balanced virtual-triangles with less noise edges. Through extensive experiments using seven real-world networks, we validate the effectiveness of (1) learning edges belonging to balanced real/virtual-triangles and (2) employing adversarial learning for signed network embedding. We show that <inline-formula><tex-math notation="LaTeX">${{\sf ABC}}$</tex-math></inline-formula> consistently and significantly outperforms the state-of-the-art community detection methods in all datasets.