DATIS: Data Augmentation for Trust Intensity Prediction in Incomplete Signed Networks

Abstract

Prediction of trust and distrust in nodes in signed network analysis is an important task with diverse applications. However, the presence of imbalanced and incomplete rankings in signed networks makes prediction of node-level trust values using machine learning (ML) methods a very challenging task. To overcome these challenges, we introduce \method, an innovative approach employing generative adversarial networks (GANs) for data augmentation in node-level trust prediction tasks in signed networks. \method addresses imbalances in both sign and value of rankings, handling missing rankings by training on nodes' local and global network features without explicit information on edge rankings assigned to nodes. Unlike existing methods, we consider the trust prediction problem as a regression task to imply the strength of trust a node gained in a network. Our experimental evaluation shows that \methodcan significantly improve the accuracy of node-level trust intensity prediction on real-world datasets.