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

ICLR 2026 Conference Submission18371 Authors

Keywords: graphs, hypergraphs, generative models

TL;DR: We propose the first hierarchical method for generating **featured** graphs and hypergraphs at scale. Previous methods couldn't scale or generate features.

Abstract: Graph generative models have shown strong results in molecular design but struggle to scale to large, complex structures. While hierarchical methods improve scalability, they usually ignore node and edge features, which are critical in real-world applications. This issue is amplified in hypergraphs, where hyperedges capture higher-order relationships among multiple nodes. Despite their importance in domains such as 3D geometry, molecular systems, and circuit design, existing generative models rarely support both hypergraphs and feature generation at scale. In this paper, we introduce FAHNES (feature-aware hypergraph generation via next-scale prediction), a hierarchical framework that jointly generates hypergraph topology and features. FAHNES builds multi-scale representations through node coarsening and refines them via localized expansion, guided by a novel node budget mechanism that controls granularity and ensures consistency across scales. Experiments on synthetic, 3D mesh and point cloud datasets show that FAHNES achieves state-of-the-art performance in jointly generating features and structure, advancing scalable hypergraph and graph generation.

Primary Area: generative models

Submission Number: 18371