Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shengchao, Wang, Chengpeng, Lu, Jiarui, Nie, Weili, Wang, Hanchen, Li, Zhuoxinran, Zhou, Bolei, Tang, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913215807488000
author Liu, Shengchao
Wang, Chengpeng
Lu, Jiarui
Nie, Weili
Wang, Hanchen
Li, Zhuoxinran
Zhou, Bolei
Tang, Jian
author_facet Liu, Shengchao
Wang, Chengpeng
Lu, Jiarui
Nie, Weili
Wang, Hanchen
Li, Zhuoxinran
Zhou, Bolei
Tang, Jian
contents Deep generative models (DGMs) have been widely developed for graph data. However, much less investigation has been carried out on understanding the latent space of such pretrained graph DGMs. These understandings possess the potential to provide constructive guidelines for crucial tasks, such as graph controllable generation. Thus in this work, we are interested in studying this problem and propose GraphCG, a method for the unsupervised discovery of steerable factors in the latent space of pretrained graph DGMs. We first examine the representation space of three pretrained graph DGMs with six disentanglement metrics, and we observe that the pretrained representation space is entangled. Motivated by this observation, GraphCG learns the steerable factors via maximizing the mutual information between semantic-rich directions, where the controlled graph moving along the same direction will share the same steerable factors. We quantitatively verify that GraphCG outperforms four competitive baselines on two graph DGMs pretrained on two molecule datasets. Additionally, we qualitatively illustrate seven steerable factors learned by GraphCG on five pretrained DGMs over five graph datasets, including two for molecules and three for point clouds.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17123
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled
Liu, Shengchao
Wang, Chengpeng
Lu, Jiarui
Nie, Weili
Wang, Hanchen
Li, Zhuoxinran
Zhou, Bolei
Tang, Jian
Machine Learning
Artificial Intelligence
Quantitative Methods
Deep generative models (DGMs) have been widely developed for graph data. However, much less investigation has been carried out on understanding the latent space of such pretrained graph DGMs. These understandings possess the potential to provide constructive guidelines for crucial tasks, such as graph controllable generation. Thus in this work, we are interested in studying this problem and propose GraphCG, a method for the unsupervised discovery of steerable factors in the latent space of pretrained graph DGMs. We first examine the representation space of three pretrained graph DGMs with six disentanglement metrics, and we observe that the pretrained representation space is entangled. Motivated by this observation, GraphCG learns the steerable factors via maximizing the mutual information between semantic-rich directions, where the controlled graph moving along the same direction will share the same steerable factors. We quantitatively verify that GraphCG outperforms four competitive baselines on two graph DGMs pretrained on two molecule datasets. Additionally, we qualitatively illustrate seven steerable factors learned by GraphCG on five pretrained DGMs over five graph datasets, including two for molecules and three for point clouds.
title Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled
topic Machine Learning
Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2401.17123