Timezone: »

 
GraphCG: Unsupervised Discovery of Steerable Factors in Graphs
Shengchao Liu · Chengpeng Wang · Weili Nie · Hanchen Wang · Jiarui Lu · Bolei Zhou · Jian Tang

@
in New Frontiers in Graph Learning »
Event URL: https://openreview.net/forum?id=BhR44NzeK_1 »

Deep generative models have been extensively explored recently, especially for the graph data such as molecular graphs and point clouds. Yet, much less investigation has been carried out on understanding the learned latent space of deep graph generative models. Such understandings can open up a unified perspective and provide guidelines for essential tasks like controllable generation. In this paper, we first examine the representation space of the recent deep generative model trained for graph data, observing that the learned representation space is not perfectly disentangled. Based on this observation, we then propose an unsupervised method called GraphCG, which is model-agnostic and task-agnostic for discovering steerable factors in graph data. Specifically, GraphCG learns the semantic-rich directions via maximizing the corresponding mutual information, where the edited graph along the same direction will possess certain steerable factors. We conduct experiments on two types of graph data, molecular graphs and point clouds. Both the quantitative and qualitative results show the effectiveness of GraphCG for discovering steerable factors. The code will be public in the near future.

Keywords: energy-based model · Point cloud · Mutual Information · graph editing · graph controllable generation · molecular graph

Author Information

Shengchao Liu (MILA-UdeM)
Chengpeng Wang (University of Illinois at Urbana-Champaign)
Weili Nie (NVIDIA)
Hanchen Wang (Cambridge, Caltech)
Jiarui Lu (Mila - Quebec AI Institute)
Bolei Zhou (UCLA)
Bolei Zhou

Assistant professor at UCLA's computer science department

Jian Tang (Mila)

More from the Same Authors