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.

翻译：生成模型学习图分布面临重大挑战，根源在于缺乏置换不变性：不同图中的节点可能任意排序，而标准图对齐方法属于组合优化问题且计算代价极高。本文提出AlignGraph——一种融合高效快速图对齐方法与深度生成模型系列的框架，该系列模型天然具备节点置换不变性。实验表明，我们提出的框架能够成功学习图分布，在相关性能指标上超越现有方法25%至560%。