GraphNVP: An Invertible Flow Model for Generating Molecular Graphs

Madhawa, Kaushalya; Ishiguro, Katushiko; Nakago, Kosuke; Abe, Miki

doi:10.48550/arxiv.1905.11600

Cited by 65 publications

(111 citation statements)

References 10 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…Deep generative models model a distribution of general molecular structure with a deep network model so that one can generate molecules by sampling from the learned distribution. Typical algorithms include variational autoencoder (VAE), generative adversarial network (GAN), energy-based models, flow-based model [14,21,9,37,23,17,34,38,22,49,27,5,32,1]. Also, DGMs can leverage Bayesian optimization in latent spaces to optimize latent vectors and reconstruct to obtain the optimized molecules [21].…”

Section: Related Workmentioning

confidence: 99%

Differentiable Scaffolding Tree for Molecular Optimization

Gao

Xiao

et al. 2021

Preprint

View full text Add to dashboard Cite

The structural design of functional molecules, also called molecular optimization, is an essential chemical science and engineering task with important applications, such as drug discovery. Deep generative models and combinatorial optimization methods achieve initial success but still struggle with directly modeling discrete chemical structures and often heavily rely on brute-force enumeration. The challenge comes from the discrete and non-differentiable nature of molecule structures. To address this, we propose differentiable scaffolding tree (DST) that utilizes a learned knowledge network to convert discrete chemical structures to locally differentiable ones. DST enables a gradient-based optimization on a chemical graph structure by back-propagating the derivatives from the target properties through a graph neural network (GNN). Our empirical studies show the gradient-based molecular optimizations are both effective and sample efficient. Furthermore, the learned graph parameters can also provide an explanation that helps domain experts understand the model output.

show abstract

Section: Related Workmentioning

confidence: 99%

Differentiable Scaffolding Tree for Molecular Optimization

Gao

Xiao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…InfoMin employs a flow-based generative model as the view generator for data augmentation and trains the view generator in a semi-supervised manner. However, transferring this idea to graph C: is a nontrivial task since current graph generative models are either of limited generation qualities [19] or designed for specific tasks such as the molecular data [6,25]. To overcome this issue, in this work we build a learnable graph view generator that learns a probability distribution over the nodelevel augmentations.…”

Section: Learnable Data Augmentationmentioning

confidence: 99%

AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators

Yin¹,

Wang²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ predefined view generation methods, e.g., node drop or edge perturbation, which usually cannot adapt to input data or preserve the original semantic structures well. To address this issue, we propose a novel framework named Automated Graph Contrastive Learning (AutoGCL) in this paper. Specifically, AutoGCL employs a set of learnable graph view generators orchestrated by an auto augmentation strategy, where every graph view generator learns a probability distribution of graphs conditioned by the input. While the graph view generators in AutoGCL preserve the most representative structures of the original graph in generation of every contrastive sample, the auto augmentation learns policies to introduce adequate augmentation variances in the whole contrastive learning procedure. Furthermore, AutoGCL adopts a joint training strategy to train the learnable view generators, the graph encoder, and the classifier in an end-to-end manner, resulting in topological heterogeneity yet semantic similarity in the generation of contrastive samples. Extensive experiments on semi-supervised learning, unsupervised learning, and transfer learning demonstrate the superiority of our AutoGCL framework over the state-of-the-arts in graph contrastive learning. In addition, the visualization results further confirm that the learnable view generators can deliver more compact and semantically meaningful contrastive samples compared against the existing view generation methods.

show abstract

“…Most existing non-autoregressive models are permutation invarant. Various classes of model have been proposed including VAE- [24,3], Flows- [11,14], and Score-based [16] models. They all use permutation equivariant generated functions as detailed in section 3.1.…”

Section: Related Workmentioning

confidence: 99%

Permutation Equivariant Generative Adversarial Networks for Graphs

Yoann¹,

Gregorova²,

Kalousis³

2021

Preprint

View full text Add to dashboard Cite

One of the most discussed issues in graph generative modeling is the ordering of the representation. One solution consists of using equivariant generative functions, which ensure the ordering invariance. After having discussed some properties of such functions, we propose 3G-GAN, a 3-stages model relying on GANs and equivariant functions. The model is still under development. However, we present some encouraging exploratory experiments and discuss the issues still to be addressed.

show abstract

GraphNVP: An Invertible Flow Model for Generating Molecular Graphs

Cited by 65 publications

References 10 publications

Differentiable Scaffolding Tree for Molecular Optimization

Differentiable Scaffolding Tree for Molecular Optimization

AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators

Permutation Equivariant Generative Adversarial Networks for Graphs

Contact Info

Product

Resources

About