Feature-aware Hypergraph Generation via Next-Scale Prediction
By: Dorian Gailhard , Enzo Tartaglione , Lirida Naviner and more
Potential Business Impact:
Creates smart computer models of complex things.
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.
Similar Papers
ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion
Machine Learning (CS)
Makes computer learning on big networks faster, better.
Hypergraph Foundation Model
Machine Learning (CS)
Helps computers understand complex connections better.
Multi-Granular Attention based Heterogeneous Hypergraph Neural Network
Machine Learning (CS)
Finds hidden connections in complex data.