Contrastive representation learning of inorganic materials to overcome lack of training datasets-Reference-Cited by-同舟云学术

Contrastive representation learning of inorganic materials to overcome lack of training datasets

Published:2022 Issue:47 Volume:58 Page:6729-6732
ISSN:1359-7345
Container-title:Chemical Communications
language:en
Short-container-title:Chem. Commun.

Author:

Na Gyoung S.¹^ORCID,Kim Hyun Woo²

Affiliation:

1. Korea Research Institute of Chemical Technology (KRICT), Republic of Korea

2. Department of Chemistry, Gwangju Institute of Science and Technology (GIST), Republic of Korea

Abstract

Target-correlated materials representation generated by explicitly materials representation learning (EMRL) for simplifying the regression problems.

Funder

Korea Research Institute of Chemical Technology

Publisher

Royal Society of Chemistry (RSC)

Subject

Materials Chemistry,Metals and Alloys,Surfaces, Coatings and Films,General Chemistry,Ceramics and Composites,Electronic, Optical and Magnetic Materials,Catalysis

Link

http://pubs.rsc.org/en/content/articlepdf/2022/CC/D2CC01764D

Reference32 articles.

1. Recent advances and applications of machine learning in solid-state materials science

2. Machine learning for molecular and materials science

3. Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces

4. On representing chemical environments

5. Crystal Structure Prediction via Deep Learning

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Leveraging language representation for materials exploration and discovery;npj Computational Materials;2024-03-21

2. Conditional Graph Regression for Complex Chemical Systems with Heterogeneous Substructures;2022 IEEE International Conference on Big Data (Big Data);2022-12-17