• Corpus ID: 203593519

Graph Residual Flow for Molecular Graph Generation

@article{Honda2019GraphRF,
  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},
  year={2019},
  volume={abs/1909.13521}
}
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… 

Figures and Tables from this paper

GraphEBM: Molecular Graph Generation with Energy-Based Models

TLDR
GraphEBM is proposed to generate molecular graphs using energy-based models using Langevin dynamics to parameterize the energy function in a permutations invariant manner, thus making GraphEBM permutation invariant.

MoFlow: An Invertible Flow Model for Generating Molecular Graphs

TLDR
The proposed MoFlow is a flow-based graph generative model to learn invertible mappings between molecular graphs and their latent representations and achieves state-of-the-art performance, which implies its potential efficiency and effectiveness to explore large chemical space for drug discovery.

GraphDF: A Discrete Flow Model for Molecular Graph Generation

TLDR
This work proposes GraphDF, a novel discrete latent variable model for molecular graph generation based on normalizing flow methods that uses invertible modulo shift transforms to map discrete latent variables to graph nodes and edges.

FastFlows: Flow-Based Models for Molecular Graph Generation

TLDR
This work proposes a framework using normalizing-flow based models, SELF-Referencing Embedded Strings, and multi-objective optimization that efficiently generates small molecules and enables fast generation and identification of druglike, synthesizable molecules.

Flow-Based Models for Active Molecular Graph Generation

We propose a framework using normalizing-flow based models, SELF-Referencing Embedded Strings, and active learning that generates a high percentage of novel, unique, and valid molecules and

A Systematic Survey on Deep Generative Models for Graph Generation

TLDR
An extensive overview of the literature in the field of deep generative models for graph generation is provided and two taxonomies of deep Generative Models for unconditional, and conditional graph generation respectively are proposed.

GraphGT: Machine Learning Datasets for Graph Generation and Transformation

TLDR
GraphGT, a large dataset collection for graph generation and transformation problem, is introduced, which contains 36 datasets from 9 domains across 6 subjects and provides an easy-to-use graph generation pipeline that simplifies the process for graph data loading, experimental setup and model evaluation.

Continuous Graph Flow

TLDR
Continuous Graph Flow is proposed, a generative continuous flow based method that aims to model complex distributions of graph-structured data and achieves significantly better performance compared to state-of-the-art models.

A Survey on Deep Graph Generation: Methods and Applications

TLDR
A comprehensive review on the existing literature of graph generation from a variety of emerging methods to its wide application areas and divides the state-of-the-art methods into three categories based on model architectures and summarizes their generation strategies.

Target-aware Molecular Graph Generation

TLDR
This paper proposes SiamFlow, which forces the flow to fit the distribution of target sequence embeddings in latent space to generate molecular drugs in a targetaware manner that bridges biological activity and molecular design.

References

SHOWING 1-10 OF 33 REFERENCES

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

TLDR
This work decomposes the generation of a graph into two steps: generation of an adjacency tensor and node attributes, which yields the exact likelihood maximization on graph-structured data, combined with two novel reversible flows.

Junction Tree Variational Autoencoder for Molecular Graph Generation

TLDR
The junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network, which allows for incrementally expand molecules while maintaining chemical validity at every step.

MolGAN: An implicit generative model for small molecular graphs

TLDR
MolGAN is introduced, an implicit, likelihood-free generative model for small molecular graphs that circumvents the need for expensive graph matching procedures or node ordering heuris-tics of previous likelihood-based methods.

Constrained Graph Variational Autoencoders for Molecule Design

TLDR
A variational autoencoder model in which both encoder and decoder are graph-structured is proposed and it is shown that by using appropriate shaping of the latent space, this model allows us to design molecules that are (locally) optimal in desired properties.

On Asymptotic Behaviors of Graph CNNs from Dynamical Systems Perspective

TLDR
The theory enables us to relate the expressive power of GCNs with the topological information of the underlying graphs inherent in the graph spectra and provides a principled guideline for weight normalization of graph NNs.

Graph Normalizing Flows

TLDR
This work introduces graph normalizing flows: a new, reversible graph neural network model for prediction and generation, which is permutation-invariant, generating entire graphs with a single feed-forward pass, and achieves competitive results with the state of the art auto-regressive models, while being better suited to parallel computing architectures.

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation

TLDR
Graph Convolutional Policy Network (GCPN) is proposed, a general graph convolutional network based model for goal-directed graph generation through reinforcement learning that can achieve 61% improvement on chemical property optimization over state-of-the-art baselines while resembling known molecules, and achieve 184% improved on the constrained property optimization task.

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

TLDR
A regularization framework for variational autoencoders is proposed that focuses on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints.

Semi-Supervised Classification with Graph Convolutional Networks

TLDR
A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.

Simplifying Graph Convolutional Networks

TLDR
This paper successively removes nonlinearities and collapsing weight matrices between consecutive layers, and theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier.