AlignGraph: A Group of Generative Models for Graphs
This work solves the problem of expensive graph alignment for generative modeling, which is incremental as it builds on existing methods but introduces a novel combination for efficiency.
The paper tackles the challenge of learning graph distributions by addressing the lack of permutation invariance in nodes, proposing AlignGraph, a group of generative models that combine efficient graph alignment with permutation-invariant deep models, resulting in performance improvements of 25% to 560% over competitors.
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.