AlignGraph: A Group of Generative Models for Graphs
AlignGraph: A Group of Generative Models for Graphs
复制标题
DOI：
10.48550/arxiv.2301.11273
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Kimia Shayestehfard;Dana Brooks;Stratis Ioannidis
中科院分区：
文献类型：
--
作者：
Kimia Shayestehfard;Dana Brooks;Stratis Ioannidis
由于缺乏置换不变性，生成模型学习图上的分布是具有挑战性的：节点可以在图上任意排序，标准图对齐是组合的，并且众所周知昂贵。我们提出了AlignGraph，一组生成模型，联合收割机结合快速，高效的图对齐方法与一系列的深度生成模型，是不变的节点排列。实验结果表明，该框架能够成功地学习图分布，在相关性能分数上比竞争对手高出25%-560%。
It is challenging for generative models to learn a distribution over graphs because of the lack of permutation invariance: nodes may be ordered arbitrarily across graphs, and standard graph alignment is combinatorial and notoriously expensive. We propose AlignGraph, a group of generative models that combine fast and efficient graph alignment methods with a family of deep generative models that are invariant to node permutations. Our experiments demonstrate that our framework successfully learns graph distributions, outperforming competitors by 25% -560% in relevant performance scores.