AlignGraph: A Group of Generative Models for Graphs
Social and Information Networks
2023-01-27 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.2301.11273,
title = {AlignGraph: A Group of Generative Models for Graphs},
author = {Kimia Shayestehfard and Dana Brooks and Stratis Ioannidis},
journal= {arXiv preprint arXiv:2301.11273},
year = {2023}
}
Comments
12 pages, 2 figures, 4 tables