GraphNVP: an Invertible Flow-based Model for Generating Molecular Graphs

We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model. We decompose the generation of a graph into two steps: generation of (i) an adjacency tensor and (ii) node attributes. This decomposition yields the exact likelihood maximization on graph-structured data, combined with two novel reversible flows. We empirically demonstrate that our model efficiently generates valid molecular graphs with almost no duplicated molecules. In addition, we observe that the learned latent space can be used to generate molecules with desired chemical properties.

[1]  Ryan G. Coleman,et al.  ZINC: A Free Tool to Discover Chemistry for Biology , 2012, J. Chem. Inf. Model..

[2]  E. Tabak,et al.  A Family of Nonparametric Density Estimation Algorithms , 2013 .

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[5]  Pavlo O. Dral,et al.  Quantum chemistry structures and properties of 134 kilo molecules , 2014, Scientific Data.

[6]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Yoshua Bengio,et al.  NICE: Non-linear Independent Components Estimation , 2014, ICLR.

[9]  Matthias Bethge,et al.  A note on the evaluation of generative models , 2015, ICLR.

[10]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[11]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[12]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[13]  Matt J. Kusner,et al.  Grammar Variational Autoencoder , 2017, ICML.

[14]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[15]  Cao Xiao,et al.  Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders , 2018, NeurIPS.

[16]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[17]  Nikos Komodakis,et al.  GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders , 2018, ICANN.

[18]  Qi Liu,et al.  Constrained Graph Variational Autoencoders for Molecule Design , 2018, NeurIPS.

[19]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[20]  Jure Leskovec,et al.  Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation , 2018, NeurIPS.

[21]  Nicola De Cao,et al.  MolGAN: An implicit generative model for small molecular graphs , 2018, ArXiv.

[22]  Jure Leskovec,et al.  GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models , 2018, ICML.

[23]  Regina Barzilay,et al.  Junction Tree Variational Autoencoder for Molecular Graph Generation , 2018, ICML.

[24]  David Duvenaud,et al.  Invertible Residual Networks , 2018, ICML.

[25]  David Duvenaud,et al.  FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models , 2018, ICLR.