Feature-Aware (Hyper)graph Generation via Next-Scale Prediction

Abstract:Graph generative models perform well on small-scale 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. 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. FAHNES progressively constructs the final sample through localized expansion and refinement, guided by a novel node budget controlling granularity and ensuring cross-scale consistency. Experiments on synthetic, 3D mesh, and graph point cloud datasets demonstrate competitive or state-of-the-art performance while uniquely scaling to large-scale graphs and hypergraphs with features. Our code is open source.

Machine Learning (cs.LG); Discrete Mathematics (cs.DM)

arXiv:2506.01467 [cs.LG]

(or arXiv:2506.01467v4 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2506.01467 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.