AI Chat AI Image Generator AI Video Text to Speech

Permutation Equivariant Generative Adversarial Networks for Graphs

12/07/2021

∙

by Yoann Boget, et al.

∙

∙

One of the most discussed issues in graph generative modeling is the ordering of the representation. One solution consists of using equivariant generative functions, which ensure the ordering invariance. After having discussed some properties of such functions, we propose 3G-GAN, a 3-stages model relying on GANs and equivariant functions. The model is still under development. However, we present some encouraging exploratory experiments and discuss the issues still to be addressed.

Yoann Boget
4 publications
Magda Gregorova
13 publications
Alexandros Kalousis
32 publications

page 1

page 2

page 3

page 4

research

∙ 05/27/2020

Generative Adversarial Networks Applied to Observational Health Data

Having been collected for its primary purpose in patient care, Observati...

0 Jeremy Georges-Filteau, et al. ∙

research

∙ 03/02/2020

Permutation Invariant Graph Generation via Score-Based Generative Modeling

Learning generative models for graph-structured data is challenging beca...

18 Chenhao Niu, et al. ∙

research

∙ 01/27/2021

Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation

Generative Adversarial Networks (GAN) is an adversarial model, and it ha...

19 Junjie Li, et al. ∙

research

∙ 07/19/2017

Can GAN Learn Topological Features of a Graph?

This paper is first-line research expanding GANs into graph topology ana...

0 Weiyi Liu, et al. ∙

research

∙ 06/02/2023

LIC-GAN: Language Information Conditioned Graph Generative GAN Model

Deep generative models for Natural Language data offer a new angle on th...

0 Robert Lo, et al. ∙

research

∙ 12/01/2022

GrannGAN: Graph annotation generative adversarial networks

We consider the problem of modelling high-dimensional distributions and ...

0 Yoann Boget, et al. ∙