提出可生成带特征的大规模图与超图的层次化方法
Feature-Aware (Hyper)graph Generation via Next-Scale Prediction
- 通过预测下一尺度结构，分步生成拓扑与节点特征
- 在3D网格和点云数据上达到领先性能，支持大规模结构
- 适合需要真实特征建模的大规模图学习任务
图生成模型在小规模结构数据上表现良好，但在扩展到大规模复杂结构时面临挑战。层级化方法虽提升可扩展性，却常忽略节点与边的特征，而这些特征在真实应用中至关重要。本文提出FAHNES（基于下一尺度预测的特征感知图生成），一种联合生成图与超图拓扑和特征的层级框架。该方法通过局部扩展与精炼，逐步构建最终样本，由一种新型节点预算机制控制粒度并保证跨尺度一致性。在合成数据、3D网格和图点云数据集上的实验表明，其性能具有竞争力或达到当前最优水平，且能唯一实现带特征的大规模图与超图生成。代码已开源。
原文摘要 · Abstract (English)
Graph generative models perform well on small-scale structured data but struggle to scale to large, complex structures. Hierarchical approaches improve scalability but often ignore node and edge features, which are critical in real-world applications. In this paper, we propose FAHNES (feature-aware (hyper)graph generation via next-scale prediction), a hierarchical framework that jointly generates topology and features for graphs and hypergraphs. FAHNES progressively constructs the final sample through localized expansion and refinement, guided by a novel node budget controlling granularity and ensuring cross-scale consistency. Experiments on synthetic, 3D mesh, and graph point cloud datasets demonstrate competitive or state-of-the-art performance while uniquely scaling to large-scale graphs and hypergraphs with features. Our code is open source.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。