DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation

TL;DR

This paper introduces DEFactor, a differentiable probabilistic graph generation model that efficiently generates and optimizes molecular graphs, overcoming size limitations and enabling conditional generation for drug discovery applications.

Contribution

The paper presents a novel differentiable graph generation model that is size-independent and suitable for conditional molecular design tasks.

Findings

Favorable performance on prototype-based molecular graph generation tasks.

Enables direct optimization of graphs in a computationally efficient manner.

Overcomes limitations of previous graph generative models.

Abstract

Generating novel molecules with optimal properties is a crucial step in many industries such as drug discovery. Recently, deep generative models have shown a promising way of performing de-novo molecular design. Although graph generative models are currently available they either have a graph size dependency in their number of parameters, limiting their use to only very small graphs or are formulated as a sequence of discrete actions needed to construct a graph, making the output graph non-differentiable w.r.t the model parameters, therefore preventing them to be used in scenarios such as conditional graph generation. In this work we propose a model for conditional graph generation that is computationally efficient and enables direct optimisation of the graph. We demonstrate favourable performance of our model on prototype-based molecular graph conditional generation tasks.