Feature-aware Hypergraph Generation via Next-Scale Prediction

2025-06-02

AI Summary

Existing hypergraph generation methods model only topological structure, neglecting the joint generation of node and hyperedge features. To address this, we propose FAHNES, a hierarchical generative framework that— for the first time—unifies hypergraph topology and semantic feature generation. FAHNES employs a multi-scale coarsening–prediction–refinement pipeline, integrating local expansion, feature-aware refinement, and cross-scale prediction. Crucially, it introduces a node-budget mechanism during coarsening to control cluster splitting, ensuring controllability and scalability. Evaluated on synthetic hypergraphs, 3D meshes, and molecular datasets, FAHNES achieves significantly higher fidelity in reconstructing both topological structure and node/hyperedge features. It outperforms prior state-of-the-art methods across all benchmarks, establishing new performance frontiers in hypergraph generation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Hypergraphs generalize traditional graphs by allowing hyperedges to connect multiple nodes, making them well-suited for modeling complex structures with higher-order relationships, such as 3D meshes, molecular systems, and electronic circuits. While topology is central to hypergraph structure, many real-world applications also require node and hyperedge features. Existing hypergraph generation methods focus solely on topology, often overlooking feature modeling. In this work, we introduce FAHNES (feature-aware hypergraph generation via next-scale prediction), a hierarchical approach that jointly generates hypergraph topology and features. FAHNES builds a multi-scale representation through node coarsening, then learns to reconstruct finer levels via localized expansion and refinement, guided by a new node budget mechanism that controls cluster splitting. We evaluate FAHNES on synthetic hypergraphs, 3D meshes, and molecular datasets. FAHNES achieves competitive results in reconstructing topology and features, establishing a foundation for future research in featured hypergraph generative modeling.

Problem

• Generates hypergraphs with both topology and node features
• Overcomes limitations of existing topology-only hypergraph methods
• Introduces hierarchical approach for multi-scale feature modeling

Innovation

• Hierarchical hypergraph generation with multi-scale representation
• Joint modeling of topology and features via localized refinement
• Node budget mechanism controlling cluster splitting