Datis

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 DATIS, an innovative approach employing generative adversarial networks (GANs) for data augmentation in node-level trust prediction tasks in signed networks. DATIS 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 DATIS can significantly improve the accuracy of node-level trust intensity prediction on real-world datasets

Data mining · Optics · Physics · Access Control and Trust · Advanced Graph Neural Networks · Computer Science · Network Security and Intrusion Detection · Artificial Intelligence

• Generative adversarial networks

  Open Access•Ian Goodfellow, Jean Pouget-Abadie et al.•Communications of the ACM•2020

  Add to list

• Ranking Nodes in Signed Social Networks

  Open Access•Mohsen Shahriari, Moshen Shahriari et al.•Social Network Analysis and Mining•2014

  Add to list

• Link sign prediction and ranking in signed directed social networks

  Open Access•Dongjin Song, David A Meyer et al.•Social Network Analysis and Mining•2015

  Add to list

• Sign prediction in social networks based on users reputation and optimism

  Open Access•Mohsen Shahriari, Omid Askari Sichani et al.•Social Network Analysis and Mining•2016

  Add to list