Deep Generative Model for Periodic Graphs

Wang, Shiyu; Guo, Xinwen; Zhao, Ling

doi:10.48550/arxiv.2201.11932

Cited by 6 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A major requirement for the graphbased inverse design of crystal structures is the possibility to generate new periodic graphs based on a vector representation. Recently, this problem has been addressed with a new architecture called PGD-VAE 162 , a variational autoencoder capable of generating new periodic graph structures. Another work using a VAE focuses on predicting stable crystal structures using GNNs 258 .…”

Section: Periodic Graph Generationmentioning

confidence: 99%

“…Overall, graph generative models have been extensively applied for molecular materials and stayed up to date with recent developments in the field of graph generation. However, these remain under-explored for crystalline materials, mainly due to graph representation challenges 162 . While finding such a reliable graph representation is still an open question 128 and will likely remain case-specific, we believe that using generative models based on GNNs is a promising research direction in inverse design, especially given current breakthroughs such as normalizing flows.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Graph neural networks for materials science and chemistry

et al. 2022

View full text Add to dashboard Cite

Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict materials properties, accelerate simulations, design new structures, and predict synthesis routes of new materials. Graph neural networks (GNNs) are one of the fastest growing classes of machine learning models. They are of particular relevance for chemistry and materials science, as they directly work on a graph or structural representation of molecules and materials and therefore have full access to all relevant information required to characterize materials. In this Review, we provide an overview of the basic principles of GNNs, widely used datasets, and state-of-the-art architectures, followed by a discussion of a wide range of recent applications of GNNs in chemistry and materials science, and concluding with a road-map for the further development and application of GNNs.

show abstract

Section: Periodic Graph Generationmentioning

confidence: 99%

mentioning

confidence: 99%

Graph neural networks for materials science and chemistry

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Moreover, MeshSeq [273] is the dataset that contains 380 meshes for quantitative analysis of how people decompose objects into parts and for comparison of mesh segmentation algorithms [273]. This dataset has been borrowed to generate periodic graphs with different basic units [166]. QMOF [274] dataset is a publicly available database of computed quantum-chemical properties and molecular structures of metal-organic frameworks (MOFs) [274].…”

Section: Chinesementioning

confidence: 99%

“…QMOF [274] dataset is a publicly available database of computed quantum-chemical properties and molecular structures of metal-organic frameworks (MOFs) [274]. This dataset has also been used for controllable periodic graph generation [166].…”

Section: Chinesementioning

confidence: 99%

Controllable Data Generation by Deep Learning: A Review

Wang¹,

Du²,

Guo³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Designing and generating new data under targeted properties has been attracting various critical applications such as molecule design, image editing and speech synthesis. Traditional hand-crafted approaches heavily rely on expertise experience and intensive human efforts, yet still suffer from the insufficiency of scientific knowledge and low throughput to support effective and efficient data generation. Recently, the advancement of deep learning induces expressive methods that can learn the underlying representation and properties of data. Such capability provides new opportunities in figuring out the mutual relationship between the structural patterns and functional properties of the data and leveraging such relationship to generate structural data given the desired properties. This article provides a systematic review of this promising research area, commonly known as controllable deep data generation. Firstly, the potential challenges are raised and preliminaries are provided. Then the controllable deep data generation is formally defined, a taxonomy on various techniques is proposed and the evaluation metrics in this specific domain are summarized. After that, exciting applications of controllable deep data generation are introduced and existing works are experimentally analyzed and compared. Finally, the promising future directions of controllable deep data generation are highlighted and five potential challenges are identified.

show abstract

“…Extensive efforts have been spent on learning underlying low-dimensional representation and the generation process of high-dimensional data through deep generative models such as variational autoencoders (VAE) [27,35,9], generative adversarial networks (GANs) [11,12], normalizing flows [40,5], etc [48,17,8]. Particularly, enhancing the disentanglement and independence of latent dimensions has been attracting the attention of the community [4,43,3,34,45,23], enabling controllable generation that generates data with desired properties by interpolating latent variables [44,13,29,25,38,20,7,49]. For instance, CSVAE transfers image attributes by correlating latent variables with desired properties [28].…”

Section: Introductionmentioning

confidence: 99%

Multi-objective Deep Data Generation with Correlated Property Control

Wang¹,

Guo²,

Lin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Developing deep generative models has been an emerging field due to the ability to model and generate complex data for various purposes, such as image synthesis and molecular design. However, the advancement of deep generative models is limited by challenges to generate objects that possess multiple desired properties: 1) the existence of complex correlation among real-world properties is common but hard to identify; 2) controlling individual property enforces an implicit partially control of its correlated properties, which is difficult to model; 3) controlling multiple properties under various manners simultaneously is hard and under-explored. We address these challenges by proposing a novel deep generative framework, CorrVAE, that recovers semantics and the correlation of properties through disentangled latent vectors. The correlation is handled via an explainable mask pooling layer, and properties are precisely retained by generated objects via the mutual dependence between latent vectors and properties. Our generative model preserves properties of interest while handling correlation and conflicts of properties under a multi-objective optimization framework. The experiments demonstrate our model's superior performance in generating data with desired properties. The code of CorrVAE is available at https://github.com/shi-yu-wang/CorrVAE.

show abstract

Deep Generative Model for Periodic Graphs

Cited by 6 publications

References 44 publications

Graph neural networks for materials science and chemistry

Graph neural networks for materials science and chemistry

Controllable Data Generation by Deep Learning: A Review

Multi-objective Deep Data Generation with Correlated Property Control

Contact Info

Product

Resources

About