Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386336928> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386336928 endingPage "467" @default.
- W4386336928 startingPage "458" @default.
- W4386336928 abstract "Recently, material search utilizing the material informatics (MI) technique is considered to be an efficient approach to discovering new materials. Energy or environment-related materials are deeply related to chemical reactions, and the reactivity of materials is determined by the electronic energy (or internal energy) of materials and reactant systems. The electronic energy is often calculated by first-principles calculation which is based on the Schrödinger equation. Among them, a method called density functional theory (DFT) is widely used nowadays. Since the computational cost of the DFT calculation is relatively high, many graph neural networks (GNNs) for energy prediction have been proposed to obtain the energy values quickly. However, it is difficult to obtain a large amount of labeled data for GNNs training, because a large amount of the DFT data is necessary for training. Although self-supervised learning (SSL) methods using unlabeled data, i.e., no DFT energy information is needed, have been proposed to improve the GNNs’ energy prediction accuracy, existing SSL methods use a non-existent atom of “mask”; this may lead to the inefficient GNNs training. In this work, we propose a mask-less SSL method by replacing some atoms in the target material systems, aiming to improve the energy prediction accuracy of GNNs. Our target systems are catalysts, and here the atoms in unlabeled catalysts are replaced with other actual existing atoms. Then, GNNs predict whether the atoms have been replaced or not for all atoms composing the material. After that, GNNs pre-trained by the proposed SSL are fine-tuned by downstream tasks. We demonstrate the superiority of our proposed method on the Open Catalyst dataset and Poisoned Catalyst dataset using the energy prediction GNNs, CGCNN and PaiNN. The GNNs pre-trained by the proposed SSL achieve the best mean absolute error of predicted energy rather than that of the existing mask-based SSL in all experimental conditions." @default.
- W4386336928 created "2023-09-01" @default.
- W4386336928 creator A5008412118 @default.
- W4386336928 creator A5017399758 @default.
- W4386336928 creator A5024460223 @default.
- W4386336928 creator A5030122736 @default.
- W4386336928 creator A5039299164 @default.
- W4386336928 creator A5052940529 @default.
- W4386336928 creator A5054366146 @default.
- W4386336928 creator A5067326063 @default.
- W4386336928 creator A5081629487 @default.
- W4386336928 date "2023-01-01" @default.
- W4386336928 modified "2023-09-29" @default.
- W4386336928 title "Self-Supervised Learning with Atom Replacement for Catalyst Energy Prediction by Graph Neural Networks" @default.
- W4386336928 cites W1974324776 @default.
- W4386336928 cites W2758449232 @default.
- W4386336928 cites W2766856748 @default.
- W4386336928 cites W2997811423 @default.
- W4386336928 cites W3093999435 @default.
- W4386336928 cites W3101252710 @default.
- W4386336928 cites W3130241399 @default.
- W4386336928 cites W3169889433 @default.
- W4386336928 cites W3188440052 @default.
- W4386336928 doi "https://doi.org/10.1016/j.procs.2023.08.184" @default.
- W4386336928 hasPublicationYear "2023" @default.
- W4386336928 type Work @default.
- W4386336928 citedByCount "0" @default.
- W4386336928 crossrefType "journal-article" @default.
- W4386336928 hasAuthorship W4386336928A5008412118 @default.
- W4386336928 hasAuthorship W4386336928A5017399758 @default.
- W4386336928 hasAuthorship W4386336928A5024460223 @default.
- W4386336928 hasAuthorship W4386336928A5030122736 @default.
- W4386336928 hasAuthorship W4386336928A5039299164 @default.
- W4386336928 hasAuthorship W4386336928A5052940529 @default.
- W4386336928 hasAuthorship W4386336928A5054366146 @default.
- W4386336928 hasAuthorship W4386336928A5067326063 @default.
- W4386336928 hasAuthorship W4386336928A5081629487 @default.
- W4386336928 hasBestOaLocation W43863369281 @default.
- W4386336928 hasConcept C114614502 @default.
- W4386336928 hasConcept C119857082 @default.
- W4386336928 hasConcept C121332964 @default.
- W4386336928 hasConcept C132525143 @default.
- W4386336928 hasConcept C147597530 @default.
- W4386336928 hasConcept C149635348 @default.
- W4386336928 hasConcept C152365726 @default.
- W4386336928 hasConcept C154945302 @default.
- W4386336928 hasConcept C185592680 @default.
- W4386336928 hasConcept C186370098 @default.
- W4386336928 hasConcept C33923547 @default.
- W4386336928 hasConcept C41008148 @default.
- W4386336928 hasConcept C50644808 @default.
- W4386336928 hasConcept C58312451 @default.
- W4386336928 hasConcept C62520636 @default.
- W4386336928 hasConcept C80444323 @default.
- W4386336928 hasConcept C88230418 @default.
- W4386336928 hasConceptScore W4386336928C114614502 @default.
- W4386336928 hasConceptScore W4386336928C119857082 @default.
- W4386336928 hasConceptScore W4386336928C121332964 @default.
- W4386336928 hasConceptScore W4386336928C132525143 @default.
- W4386336928 hasConceptScore W4386336928C147597530 @default.
- W4386336928 hasConceptScore W4386336928C149635348 @default.
- W4386336928 hasConceptScore W4386336928C152365726 @default.
- W4386336928 hasConceptScore W4386336928C154945302 @default.
- W4386336928 hasConceptScore W4386336928C185592680 @default.
- W4386336928 hasConceptScore W4386336928C186370098 @default.
- W4386336928 hasConceptScore W4386336928C33923547 @default.
- W4386336928 hasConceptScore W4386336928C41008148 @default.
- W4386336928 hasConceptScore W4386336928C50644808 @default.
- W4386336928 hasConceptScore W4386336928C58312451 @default.
- W4386336928 hasConceptScore W4386336928C62520636 @default.
- W4386336928 hasConceptScore W4386336928C80444323 @default.
- W4386336928 hasConceptScore W4386336928C88230418 @default.
- W4386336928 hasLocation W43863369281 @default.
- W4386336928 hasOpenAccess W4386336928 @default.
- W4386336928 hasPrimaryLocation W43863369281 @default.
- W4386336928 hasRelatedWork W2386387936 @default.
- W4386336928 hasRelatedWork W2961085424 @default.
- W4386336928 hasRelatedWork W3046775127 @default.
- W4386336928 hasRelatedWork W3170094116 @default.
- W4386336928 hasRelatedWork W4205958290 @default.
- W4386336928 hasRelatedWork W4285260836 @default.
- W4386336928 hasRelatedWork W4286629047 @default.
- W4386336928 hasRelatedWork W4306321456 @default.
- W4386336928 hasRelatedWork W4306674287 @default.
- W4386336928 hasRelatedWork W4224009465 @default.
- W4386336928 hasVolume "222" @default.
- W4386336928 isParatext "false" @default.
- W4386336928 isRetracted "false" @default.
- W4386336928 workType "article" @default.