Graph Residual Flow for Molecular Graph Generation
Abstract
Statistical generative models for molecular graphs attract attention from many researchers from the fields of bio- and chemo-informatics. Among these models, invertible flow-based approaches are not fully explored yet. In this paper, we propose a powerful invertible flow for molecular graphs, called graph residual flow (GRF). The GRF is based on residual flows, which are known for more flexible and complex non-linear mappings than traditional coupling flows. We theoretically derive non-trivial conditions such that GRF is invertible, and present a way of keeping the entire flows invertible throughout the training and sampling. Experimental results show that a generative model based on the proposed GRF achieves comparable generation performance, with much smaller number of trainable parameters compared to the existing flow-based model.
Cite
@article{arxiv.1909.13521,
title = {Graph Residual Flow for Molecular Graph Generation},
author = {Shion Honda and Hirotaka Akita and Katsuhiko Ishiguro and Toshiki Nakanishi and Kenta Oono},
journal= {arXiv preprint arXiv:1909.13521},
year = {2019}
}