Signed random walk diffusion for effective representation learning in signed graphs

• Published in: PloS one Vol. 17; no. 3; p. e0265001
• Main Authors: Jung, Jinhong, Yoo, Jaemin, Kang, U
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 17.03.2022; Public Library of Science (PLoS)
• Subjects: Analysis; Biology and Life Sciences; Computer and Information Sciences; Diffusion; Embedding; Graph neural networks; Graph theory; Graphical representations; Graphs; Humans; Information management; Learning; Modelling; Neural networks; Neural Networks, Computer; Nodes; Online social networks; Performance degradation; Physical Sciences; Random walk; Research and Analysis Methods; Signs; Social Sciences; South Korea
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0265001

How can we model node representations to accurately infer the signs of missing edges in a signed social graph? Signed social graphs have attracted considerable attention to model trust relationships between people. Various representation learning methods such as network embedding and graph convolutional network (GCN) have been proposed to analyze signed graphs. However, existing network embedding models are not end-to-end for a specific task, and GCN-based models exhibit a performance degradation issue when their depth increases. In this paper, we propose Signed Diffusion Network (SidNet), a novel graph neural network that achieves end-to-end node representation learning for link sign prediction in signed social graphs. We propose a new random walk based feature aggregation, which is specially designed for signed graphs, so that SidNet effectively diffuses hidden node features and uses more information from neighboring nodes. Through extensive experiments, we show that SidNet significantly outperforms state-of-the-art models in terms of link sign prediction accuracy.