Feature-aware Hypergraph Generation via Next-Scale Prediction

• URL: http://arxiv.org/abs/2506.01467v1
• Date: Mon, 02 Jun 2025 09:24:08 GMT
• Title: Feature-aware Hypergraph Generation via Next-Scale Prediction
• Authors: Dorian Gailhard, Enzo Tartaglione, Lirida Naviner, Jhony H. Giraldo,
• Abstract summary: We introduce FAHNES (feature-aware hypergraph generation via next-scale prediction), a hierarchical approach that jointly generates hypergraph topology and features.<n>FAHNES builds a multi-scale representation through node coarsening, then learns to reconstruct finer levels via localized expansion and refinement.<n>We evaluate FAHNES on synthetic hypergraphs, 3D meshes, and molecular datasets.
• Score: 6.997955138726617
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Community and hyperedge inference in multiple hypergraphs [9.782518418521175]
  We show how to utilize interconnections between multiple hypergraphs to synthesize integrated information from multiple higher-order systems.<n>We propose a model based on the block model, which integrates information from multiple hypergraphs to reveal latent high-order structures.<n>Our work provides a practical and flexible tool for analyzing multiple hypergraphs, greatly advancing the understanding of the organization in real-world high-order systems.
  arXiv  Detail & Related papers  (2025-05-08T05:52:41Z)
• Hypergraph Foundation Model [31.16656352968761]
  Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks.<n>We present Hyper-FM, a Hypergraph Foundation Model for multi-domain knowledge extraction.<n>We also curate 10 text-attributed hypergraph datasets to advance research between HGNNs and LLMs.
  arXiv  Detail & Related papers  (2025-03-03T05:56:08Z)
• Hypergraph Transformer for Semi-Supervised Classification [50.92027313775934]
  We propose a novel hypergraph learning framework, HyperGraph Transformer (HyperGT) HyperGT uses a Transformer-based neural network architecture to effectively consider global correlations among all nodes and hyperedges. It achieves comprehensive hypergraph representation learning by effectively incorporating global interactions while preserving local connectivity patterns.
  arXiv  Detail & Related papers  (2023-12-18T17:50:52Z)
• Topology-guided Hypergraph Transformer Network: Unveiling Structural Insights for Improved Representation [1.1606619391009658]
  We propose a Topology-guided Hypergraph Transformer Network (THTN) In this model, we first formulate a hypergraph from a graph while retaining its structural essence to learn higher-order relations within the graph. We present a structure-aware self-attention mechanism that discovers the important nodes and hyperedges from both semantic and structural viewpoints.
  arXiv  Detail & Related papers  (2023-10-14T20:08:54Z)
• From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
  We present an expressive family of parameterized, hypergraph-regularized energy functions. We then demonstrate how minimizers of these energies effectively serve as node embeddings. We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
  arXiv  Detail & Related papers  (2023-06-16T04:40:59Z)
• Tensorized Hypergraph Neural Networks [69.65385474777031]
  We propose a novel adjacency-tensor-based textbfTensorized textbfHypergraph textbfNeural textbfNetwork (THNN) THNN is faithful hypergraph modeling framework through high-order outer product feature passing message. Results from experiments on two widely used hypergraph datasets for 3-D visual object classification show the model's promising performance.
  arXiv  Detail & Related papers  (2023-06-05T03:26:06Z)
• Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative [126.0985540285981]
  We apply the contrastive learning approach from images/graphs (we refer to it as HyperGCL) to improve generalizability of hypergraph neural networks. We fabricate two schemes to augment hyperedges with higher-order relations encoded, and adopt three augmentation strategies from graph-structured data. We propose a hypergraph generative model to generate augmented views, and then an end-to-end differentiable pipeline to jointly learn hypergraph augmentations and model parameters.
  arXiv  Detail & Related papers  (2022-10-07T20:12:20Z)
• Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs [59.71134113268709]
  We present General Hypergraph Spectral Convolution(GHSC), a general learning framework that can handle EDVW and EIVW hypergraphs. In this paper, we show that the proposed framework can achieve state-of-the-art performance. Experiments from various domains including social network analysis, visual objective classification, protein learning demonstrate that the proposed framework can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-31T10:46:47Z)
• Hierarchical Graph Networks for 3D Human Pose Estimation [50.600944798627786]
  Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton. We argue that this skeletal topology is too sparse to reflect the body structure and suffer from serious 2D-to-3D ambiguity problem. We propose a novel graph convolution network architecture, Hierarchical Graph Networks, to overcome these weaknesses.
  arXiv  Detail & Related papers  (2021-11-23T15:09:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.