Graph Residual Flow for Molecular Graph Generation
arXiv:1909.13521
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.
References in corpus (6)
- Auto-Encoding Variational Bayes
- Simplifying Graph Convolutional Networks
- MolGAN: An implicit generative model for small molecular graphs
- Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
- Graph Normalizing Flows
- MintNet: Building Invertible Neural Networks with Masked Convolutions
Cited by in corpus (6)
- Normalizing Flows for Probabilistic Modeling and Inference
- GraphDF: A Discrete Flow Model for Molecular Graph Generation
- Differentiable Scaffolding Tree for Molecular Optimization
- Artificial Intelligence in Drug Discovery: Applications and Techniques
- HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space
- An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design