Unsupervised Discovery of Steerable Factors When Graph Deep Generative Models Are Entangled. (arXiv:2401.17123v1 [cs.LG])

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 …

arxiv cs.lg data deep generative models dgms discovery generative generative models graph graph data guidelines investigation space tasks understanding unsupervised