Related papers: Signed Network Embedding with Application to Simultaneous Detection of Communities and Anomalies

Signed Network Embedding with Application to Simultaneous Detection of Communities and Anomalies

URL: http://arxiv.org/abs/2207.09324v3
Date: Mon, 16 Oct 2023 12:51:34 GMT
Title: Signed Network Embedding with Application to Simultaneous Detection of Communities and Anomalies
Authors: Haoran Zhang and Junhui Wang
Abstract summary: This paper develops a unified embedding model for signed networks to disentangle the intertwined balance structure and anomaly effect. The proposed model captures both balance structure and anomaly effect through a low rank plus sparse matrix decomposition. The advantage of the proposed embedding model is also demonstrated through extensive numerical experiments on both synthetic networks and an international relation network.
Score: 25.541992448747695
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Signed networks are frequently observed in real life with additional sign information associated with each edge, yet such information has been largely ignored in existing network models. This paper develops a unified embedding model for signed networks to disentangle the intertwined balance structure and anomaly effect, which can greatly facilitate the downstream analysis, including community detection, anomaly detection, and network inference. The proposed model captures both balance structure and anomaly effect through a low rank plus sparse matrix decomposition, which are jointly estimated via a regularized formulation. Its theoretical guarantees are established in terms of asymptotic consistency and finite-sample probability bounds for network embedding, community detection and anomaly detection. The advantage of the proposed embedding model is also demonstrated through extensive numerical experiments on both synthetic networks and an international relation network.