Overcoming Order in Autoregressive Graph Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cohen-Karlik, Edo, Rozenberg, Eyal, Freedman, Daniel
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913223557513216
author Cohen-Karlik, Edo
Rozenberg, Eyal
Freedman, Daniel
author_facet Cohen-Karlik, Edo
Rozenberg, Eyal
Freedman, Daniel
contents Graph generation is a fundamental problem in various domains, including chemistry and social networks. Recent work has shown that molecular graph generation using recurrent neural networks (RNNs) is advantageous compared to traditional generative approaches which require converting continuous latent representations into graphs. One issue which arises when treating graph generation as sequential generation is the arbitrary order of the sequence which results from a particular choice of graph flattening method. In this work we propose using RNNs, taking into account the non-sequential nature of graphs by adding an Orderless Regularization (OLR) term that encourages the hidden state of the recurrent model to be invariant to different valid orderings present under the training distribution. We demonstrate that sequential graph generation models benefit from our proposed regularization scheme, especially when data is scarce. Our findings contribute to the growing body of research on graph generation and provide a valuable tool for various applications requiring the synthesis of realistic and diverse graph structures.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Overcoming Order in Autoregressive Graph Generation
Cohen-Karlik, Edo
Rozenberg, Eyal
Freedman, Daniel
Social and Information Networks
Machine Learning
Graph generation is a fundamental problem in various domains, including chemistry and social networks. Recent work has shown that molecular graph generation using recurrent neural networks (RNNs) is advantageous compared to traditional generative approaches which require converting continuous latent representations into graphs. One issue which arises when treating graph generation as sequential generation is the arbitrary order of the sequence which results from a particular choice of graph flattening method. In this work we propose using RNNs, taking into account the non-sequential nature of graphs by adding an Orderless Regularization (OLR) term that encourages the hidden state of the recurrent model to be invariant to different valid orderings present under the training distribution. We demonstrate that sequential graph generation models benefit from our proposed regularization scheme, especially when data is scarce. Our findings contribute to the growing body of research on graph generation and provide a valuable tool for various applications requiring the synthesis of realistic and diverse graph structures.
title Overcoming Order in Autoregressive Graph Generation
topic Social and Information Networks
Machine Learning
url https://arxiv.org/abs/2402.03387