Learning Deep Generative Models of Graphs

Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful new approach for learning generative models over graphs, which can capture both their structure and attributes. Our approach uses graph neural networks to express probabilistic dependencies among a graph's nodes and edges, and can, in principle, learn distributions over any arbitrary graph. In a series of experiments our results show that once trained, our models can generate good quality samples of both synthetic graphs as well as real molecular graphs, both unconditionally and conditioned on data. Compared to baselines that do not use graph-structured representations, our models often perform far better. We also explore key challenges of learning generative models of graphs, such as how to handle symmetries and ordering of elements during the graph generation process, and offer possible solutions. Our work is the first and most general approach for learning generative models over arbitrary graphs, and opens new directions for moving away from restrictions of vector- and sequence-like knowledge representations, toward more expressive and flexible relational data structures.

[1]  C. L. Mallows NON-NULL RANKING MODELS. I , 1957 .

[2]  R. Luce,et al.  Individual Choice Behavior: A Theoretical Analysis. , 1960 .

[3]  R. Plackett The Analysis of Permutations , 1975 .

[4]  R. Duncan Luce,et al.  Individual Choice Behavior: A Theoretical Analysis , 1979 .

[5]  B. Bollobás The evolution of random graphs , 1984 .

[6]  P. Erdos,et al.  On the evolution of random graphs , 1984 .

[7]  Clemens Lautemann,et al.  Decomposition Trees: Structured Graph Representation and Efficient Algorithms , 1988, CAAP.

[8]  Grzegorz Rozenberg,et al.  Handbook of Graph Grammars and Computing by Graph Transformations, Volume 1: Foundations , 1997 .

[9]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[10]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[11]  D. Margaritis Learning Bayesian Network Model Structure from Data , 2003 .

[12]  Weighted automata and weighted logics , 2007, Theor. Comput. Sci..

[13]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[14]  Christos Faloutsos,et al.  Kronecker Graphs: An Approach to Modeling Networks , 2008, J. Mach. Learn. Res..

[15]  Andrew Y. Ng,et al.  Parsing Natural Scenes and Natural Language with Recursive Neural Networks , 2011, ICML.

[16]  Daniel Tarlow,et al.  Structured Generative Models of Natural Source Code , 2014, ICML.

[17]  Geoffrey E. Hinton,et al.  Grammar as a Foreign Language , 2014, NIPS.

[18]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[19]  Navdeep Jaitly,et al.  Pointer Networks , 2015, NIPS.

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

[21]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[22]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[23]  Noah A. Smith,et al.  Recurrent Neural Network Grammars , 2016, NAACL.

[24]  Tim Weninger,et al.  Growing Graphs from Hyperedge Replacement Graph Grammars , 2016, CIKM.

[25]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[26]  Stephan Oepen,et al.  Towards a Catalogue of Linguistic Graph Banks , 2016, Computational Linguistics.

[27]  Samy Bengio,et al.  Order Matters: Sequence to sequence for sets , 2015, ICLR.

[28]  Andrew Y. Ng,et al.  End-to-End People Detection in Crowded Scenes , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[30]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[31]  Esben Jannik Bjerrum,et al.  SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules , 2017, ArXiv.

[32]  Esben Jannik Bjerrum,et al.  Molecular Generation with Recurrent Neural Networks (RNNs) , 2017, ArXiv.

[33]  Lihong Li,et al.  Neuro-Symbolic Program Synthesis , 2016, ICLR.

[34]  Thierry Kogej,et al.  Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks , 2017, ArXiv.

[35]  Thomas Blaschke,et al.  Molecular de-novo design through deep reinforcement learning , 2017, Journal of Cheminformatics.

[36]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[37]  Daniel D. Johnson,et al.  Learning Graphical State Transitions , 2016, ICLR.

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

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