DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation

• DOI: 10.48550/arxiv.1811.09766
• Publication Date: 2018-01-01
• Authors: Rim Assouel; Mohamed M. Ahmed; Marwin Segler; Amir Saffari; Yoshua Bengio
• Keywords: Null graph; Generative model

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