Feature-aware Hypergraph Generation via Next-Scale Prediction

TL;DR

FAHNES is a hierarchical hypergraph generation framework that jointly models topology and features, enabling scalable and consistent generation of complex structures like 3D meshes and molecular systems.

Contribution

Introduces FAHNES, a novel multi-scale hypergraph generator that incorporates feature-aware next-scale prediction with a node budget mechanism for scalable, consistent hypergraph synthesis.

Findings

Achieves state-of-the-art results in feature and structure generation

Effectively scales to large, complex hypergraphs and graphs

Demonstrates superior performance on synthetic, 3D mesh, and point cloud datasets

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 graph point cloud datasets show that FAHNES achieves state-of-the-art performance in jointly generating features and structure, advancing scalable hypergraph and graph generation.