arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.03293cs.LGstat.ML
收藏

关于分层多分辨率图生成模型

On Hierarchical Multi-Resolution Graph Generative Models

Noah’s Ark Lab(诺亚方舟实验室)

Mahdi Karami, Jun Luo

AI总结:

本文提出一种分层多分辨率图生成模型,通过从粗到细递归生成社区结构并支持并行生成子结构,有效捕捉图的层次结构并提升生成性能与可扩展性。

摘要:

在现实世界领域中,大多数图自然呈现出层次结构。然而,数据驱动的图生成尚未有效捕捉此类结构。为解决这一问题,我们提出一种新颖方法,该方法在多个分辨率上递归生成社区结构,且生成的结构在层次结构的每一层都符合训练数据分布。图生成被设计为一系列从粗到细的生成模型,允许并行生成所有子结构,从而实现高度的可扩展性。我们的方法在多个图数据集上展示了生成性能的提升。

英文摘要:

In real world domains, most graphs naturally exhibit a hierarchical structure. However, data-driven graph generation is yet to effectively capture such structures. To address this, we propose a novel approach that recursively generates community structures at multiple resolutions, with the generated structures conforming to training data distribution at each level of the hierarchy. The graphs generation is designed as a sequence of coarse-to-fine generative models allowing for parallel generation of all sub-structures, resulting in a high degree of scalability. Our method demonstrates generative performance improvement on multiple graph datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑