Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled
This work addresses the challenge of interpretable and controllable graph generation for domains like molecules and point clouds, but it appears incremental as it builds on existing graph DGMs.
The authors tackled the problem of understanding the latent space of pretrained graph deep generative models (DGMs) to enable controllable graph generation, proposing GraphCG for unsupervised discovery of steerable factors, which outperformed baselines on molecule datasets.
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.