FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204651332> ?p ?o ?g. }

• W3204651332 endingPage "4549" @default.
• W3204651332 startingPage "4541" @default.
• W3204651332 abstract "Recently many efforts have been devoted to applying graph neural networks (GNNs) to molecular property prediction which is a fundamental task for computational drug and material discovery. One of major obstacles to hinder the successful prediction of molecular property by GNNs is the scarcity of labeled data. Though graph contrastive learning (GCL) methods have achieved extraordinary performance with insufficient labeled data, most focused on designing data augmentation schemes for general graphs. However, the fundamental property of a molecule could be altered with the augmentation method (like random perturbation) on molecular graphs. Whereas, the critical geometric information of molecules remains rarely explored under the current GNN and GCL architectures. To this end, we propose a novel graph contrastive learning method utilizing the geometry of the molecule across 2D and 3D views, which is named GeomGCL. Specifically, we first devise a dual-view geometric message passing network (GeomMPNN) to adaptively leverage the rich information of both 2D and 3D graphs of a molecule. The incorporation of geometric properties at different levels can greatly facilitate the molecular representation learning. Then a novel geometric graph contrastive scheme is designed to make both geometric views collaboratively supervise each other to improve the generalization ability of GeomMPNN. We evaluate GeomGCL on various downstream property prediction tasks via a finetune process. Experimental results on seven real-life molecular datasets demonstrate the effectiveness of our proposed GeomGCL against state-of-the-art baselines." @default.
• W3204651332 created "2021-10-11" @default.
• W3204651332 creator A5012266822 @default.
• W3204651332 creator A5025292786 @default.
• W3204651332 creator A5031546626 @default.
• W3204651332 creator A5066063885 @default.
• W3204651332 creator A5067731925 @default.
• W3204651332 date "2022-06-28" @default.
• W3204651332 modified "2023-10-05" @default.
• W3204651332 title "GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction" @default.
• W3204651332 cites W1988037271 @default.
• W3204651332 cites W2158219301 @default.
• W3204651332 cites W2558748708 @default.
• W3204651332 cites W2582187633 @default.
• W3204651332 cites W2594183968 @default.
• W3204651332 cites W2606780347 @default.
• W3204651332 cites W2726184500 @default.
• W3204651332 cites W2790808809 @default.
• W3204651332 cites W2964113829 @default.
• W3204651332 cites W2965556524 @default.
• W3204651332 cites W2966357564 @default.
• W3204651332 cites W2968734407 @default.
• W3204651332 cites W2994710732 @default.
• W3204651332 cites W2996443485 @default.
• W3204651332 cites W3007488165 @default.
• W3204651332 cites W3034516664 @default.
• W3204651332 cites W3099152386 @default.
• W3204651332 cites W3102419180 @default.
• W3204651332 cites W3109493217 @default.
• W3204651332 cites W3127113723 @default.
• W3204651332 cites W3167575787 @default.
• W3204651332 cites W3185087522 @default.
• W3204651332 cites W3190020173 @default.
• W3204651332 cites W3204453541 @default.
• W3204651332 cites W4210257598 @default.
• W3204651332 doi "https://doi.org/10.1609/aaai.v36i4.20377" @default.
• W3204651332 hasPublicationYear "2022" @default.
• W3204651332 type Work @default.
• W3204651332 sameAs 3204651332 @default.
• W3204651332 citedByCount "16" @default.
• W3204651332 countsByYear W32046513322022 @default.
• W3204651332 countsByYear W32046513322023 @default.
• W3204651332 crossrefType "journal-article" @default.
• W3204651332 hasAuthorship W3204651332A5012266822 @default.
• W3204651332 hasAuthorship W3204651332A5025292786 @default.
• W3204651332 hasAuthorship W3204651332A5031546626 @default.
• W3204651332 hasAuthorship W3204651332A5066063885 @default.
• W3204651332 hasAuthorship W3204651332A5067731925 @default.
• W3204651332 hasBestOaLocation W32046513321 @default.
• W3204651332 hasConcept C111472728 @default.
• W3204651332 hasConcept C11413529 @default.
• W3204651332 hasConcept C119857082 @default.
• W3204651332 hasConcept C132525143 @default.
• W3204651332 hasConcept C134306372 @default.
• W3204651332 hasConcept C138885662 @default.
• W3204651332 hasConcept C153083717 @default.
• W3204651332 hasConcept C154945302 @default.
• W3204651332 hasConcept C177148314 @default.
• W3204651332 hasConcept C17744445 @default.
• W3204651332 hasConcept C189950617 @default.
• W3204651332 hasConcept C199539241 @default.
• W3204651332 hasConcept C2776359362 @default.
• W3204651332 hasConcept C2780022179 @default.
• W3204651332 hasConcept C33923547 @default.
• W3204651332 hasConcept C41008148 @default.
• W3204651332 hasConcept C59404180 @default.
• W3204651332 hasConcept C80444323 @default.
• W3204651332 hasConcept C94625758 @default.
• W3204651332 hasConceptScore W3204651332C111472728 @default.
• W3204651332 hasConceptScore W3204651332C11413529 @default.
• W3204651332 hasConceptScore W3204651332C119857082 @default.
• W3204651332 hasConceptScore W3204651332C132525143 @default.
• W3204651332 hasConceptScore W3204651332C134306372 @default.
• W3204651332 hasConceptScore W3204651332C138885662 @default.
• W3204651332 hasConceptScore W3204651332C153083717 @default.
• W3204651332 hasConceptScore W3204651332C154945302 @default.
• W3204651332 hasConceptScore W3204651332C177148314 @default.
• W3204651332 hasConceptScore W3204651332C17744445 @default.
• W3204651332 hasConceptScore W3204651332C189950617 @default.
• W3204651332 hasConceptScore W3204651332C199539241 @default.
• W3204651332 hasConceptScore W3204651332C2776359362 @default.
• W3204651332 hasConceptScore W3204651332C2780022179 @default.
• W3204651332 hasConceptScore W3204651332C33923547 @default.
• W3204651332 hasConceptScore W3204651332C41008148 @default.
• W3204651332 hasConceptScore W3204651332C59404180 @default.
• W3204651332 hasConceptScore W3204651332C80444323 @default.
• W3204651332 hasConceptScore W3204651332C94625758 @default.
• W3204651332 hasIssue "4" @default.
• W3204651332 hasLocation W32046513321 @default.
• W3204651332 hasLocation W32046513322 @default.
• W3204651332 hasOpenAccess W3204651332 @default.
• W3204651332 hasPrimaryLocation W32046513321 @default.
• W3204651332 hasRelatedWork W2101355568 @default.
• W3204651332 hasRelatedWork W2492384539 @default.
• W3204651332 hasRelatedWork W2801603084 @default.
• W3204651332 hasRelatedWork W2908982266 @default.
• W3204651332 hasRelatedWork W3087493185 @default.
• W3204651332 hasRelatedWork W3206736029 @default.

• next