AI RESEARCH
Gaussian Relational Graph Transformer
arXiv CS.LG
•
ArXi:2605.15575v1 Announce Type: new Relational graph learning models relational databases as graphs and has nstrated superior performance on a wide range of relational predictive tasks. However, existing methods struggle to capture long-range dependencies due to information decay in their message-passing mechanisms, and recent relational graph transformers remain limited in jointly modeling structural, semantic, and temporal information. In this paper, we propose GelGT, a Gaussian relational graph transformer that explicitly addresses these challenges. GelGT