AI RESEARCH
Feature-Aware (Hyper)graph Generation via Next-Scale Prediction
arXiv CS.LG
•
ArXi:2506.01467v3 Announce Type: replace Graph generative models perform well on small structured data but struggle to scale to large, complex structures. Hierarchical approaches improve scalability but often ignore node and edge features, which are critical in real-world applications, particularly for hypergraphs that model higher-order relationships. In this paper, we propose FAHNES (feature-aware (hyper)graph generation via next-scale prediction), a hierarchical framework that jointly generates topology and features for graphs and hypergraphs.