Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

This paper introduces a new model to learn graph neural networks equivariant to rotations,
translations, reflections and permutations called E (n)-Equivariant Graph Neural Networks …

Drug toxicity prediction is an important step in ensuring patient safety during drug design
studies. While traditional preclinical studies have historically relied on animal models to …

Deep graph neural networks (GNNs) have achieved excellent results on various tasks on
increasingly large graph datasets with millions of nodes and edges. However, memory …

Molecular graph generation is a fundamental problem for drug discovery and has been
attracting growing attention. The problem is challenging since it requires not only generating …

Contemporary neural networks still fall short of human-level generalization, which extends
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …

We introduce the framework of continuous--depth graph neural networks (GNNs). Graph
neural ordinary differential equations (GDEs) are formalized as the counterpart to GNNs …

This paper introduces a generative model equivariant to Euclidean symmetries: E (n)
Equivariant Normalizing Flows (E-NFs). To construct E-NFs, we take the discriminative E (n) …

We consider the problem of molecular graph generation using deep models. While graphs
are discrete, most existing methods use continuous latent variables, resulting in inaccurate …

Generating molecular graphs with desired chemical properties driven by deep graph
generative models provides a very promising way to accelerate drug discovery process …