Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385376560> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4385376560 endingPage "715" @default.
- W4385376560 startingPage "700" @default.
- W4385376560 abstract "In AI drug discovery, molecular property prediction is critical. Two main molecular representation methods in molecular property prediction models, descriptor-based and molecular graph-based, offer complementary information, but face challenges like representation conflicts and training imbalances when combined. To counter these issues, we propose a two-stage training process. The first stage employs a self-supervised contrastive learning scheme based on descriptors and graph representations, which pre-trains the encoders for the two modal representations, reducing bimodal feature conflicts and promoting representational consistency. In the second stage, supervised learning using target attribute labels is applied. Here, we design a multi-branch predictor architecture to address training imbalances and facilitate decision fusion. Our method, compatible with various graph neural network modules, has shown superior performance on most of the six tested datasets." @default.
- W4385376560 created "2023-07-30" @default.
- W4385376560 creator A5007318273 @default.
- W4385376560 creator A5009308792 @default.
- W4385376560 creator A5019756461 @default.
- W4385376560 creator A5024349225 @default.
- W4385376560 creator A5062179244 @default.
- W4385376560 creator A5074250521 @default.
- W4385376560 creator A5089707622 @default.
- W4385376560 creator A5091835117 @default.
- W4385376560 date "2023-01-01" @default.
- W4385376560 modified "2023-09-23" @default.
- W4385376560 title "A Novel Descriptor and Molecular Graph-Based Bimodal Contrastive Learning Framework for Drug Molecular Property Prediction" @default.
- W4385376560 cites W2159887157 @default.
- W4385376560 cites W2920795827 @default.
- W4385376560 cites W2966357564 @default.
- W4385376560 cites W2968734407 @default.
- W4385376560 cites W3035524453 @default.
- W4385376560 cites W3093844547 @default.
- W4385376560 cites W3094681328 @default.
- W4385376560 cites W3110901318 @default.
- W4385376560 cites W3121084266 @default.
- W4385376560 cites W3163933735 @default.
- W4385376560 cites W3168997536 @default.
- W4385376560 cites W4205164650 @default.
- W4385376560 cites W4213077304 @default.
- W4385376560 cites W4214868967 @default.
- W4385376560 cites W4220982113 @default.
- W4385376560 cites W4281722003 @default.
- W4385376560 cites W4312397049 @default.
- W4385376560 cites W4318981550 @default.
- W4385376560 doi "https://doi.org/10.1007/978-981-99-4749-2_60" @default.
- W4385376560 hasPublicationYear "2023" @default.
- W4385376560 type Work @default.
- W4385376560 citedByCount "0" @default.
- W4385376560 crossrefType "book-chapter" @default.
- W4385376560 hasAuthorship W4385376560A5007318273 @default.
- W4385376560 hasAuthorship W4385376560A5009308792 @default.
- W4385376560 hasAuthorship W4385376560A5019756461 @default.
- W4385376560 hasAuthorship W4385376560A5024349225 @default.
- W4385376560 hasAuthorship W4385376560A5062179244 @default.
- W4385376560 hasAuthorship W4385376560A5074250521 @default.
- W4385376560 hasAuthorship W4385376560A5089707622 @default.
- W4385376560 hasAuthorship W4385376560A5091835117 @default.
- W4385376560 hasConcept C111472728 @default.
- W4385376560 hasConcept C119857082 @default.
- W4385376560 hasConcept C132525143 @default.
- W4385376560 hasConcept C138885662 @default.
- W4385376560 hasConcept C153180895 @default.
- W4385376560 hasConcept C154945302 @default.
- W4385376560 hasConcept C17744445 @default.
- W4385376560 hasConcept C189950617 @default.
- W4385376560 hasConcept C199539241 @default.
- W4385376560 hasConcept C2776359362 @default.
- W4385376560 hasConcept C2776401178 @default.
- W4385376560 hasConcept C2776436953 @default.
- W4385376560 hasConcept C2780022179 @default.
- W4385376560 hasConcept C41008148 @default.
- W4385376560 hasConcept C41895202 @default.
- W4385376560 hasConcept C59404180 @default.
- W4385376560 hasConcept C80444323 @default.
- W4385376560 hasConcept C94625758 @default.
- W4385376560 hasConceptScore W4385376560C111472728 @default.
- W4385376560 hasConceptScore W4385376560C119857082 @default.
- W4385376560 hasConceptScore W4385376560C132525143 @default.
- W4385376560 hasConceptScore W4385376560C138885662 @default.
- W4385376560 hasConceptScore W4385376560C153180895 @default.
- W4385376560 hasConceptScore W4385376560C154945302 @default.
- W4385376560 hasConceptScore W4385376560C17744445 @default.
- W4385376560 hasConceptScore W4385376560C189950617 @default.
- W4385376560 hasConceptScore W4385376560C199539241 @default.
- W4385376560 hasConceptScore W4385376560C2776359362 @default.
- W4385376560 hasConceptScore W4385376560C2776401178 @default.
- W4385376560 hasConceptScore W4385376560C2776436953 @default.
- W4385376560 hasConceptScore W4385376560C2780022179 @default.
- W4385376560 hasConceptScore W4385376560C41008148 @default.
- W4385376560 hasConceptScore W4385376560C41895202 @default.
- W4385376560 hasConceptScore W4385376560C59404180 @default.
- W4385376560 hasConceptScore W4385376560C80444323 @default.
- W4385376560 hasConceptScore W4385376560C94625758 @default.
- W4385376560 hasLocation W43853765601 @default.
- W4385376560 hasOpenAccess W4385376560 @default.
- W4385376560 hasPrimaryLocation W43853765601 @default.
- W4385376560 hasRelatedWork W2382607599 @default.
- W4385376560 hasRelatedWork W2521850565 @default.
- W4385376560 hasRelatedWork W2546942002 @default.
- W4385376560 hasRelatedWork W2592385986 @default.
- W4385376560 hasRelatedWork W2944661354 @default.
- W4385376560 hasRelatedWork W2970216048 @default.
- W4385376560 hasRelatedWork W2998168123 @default.
- W4385376560 hasRelatedWork W3206736029 @default.
- W4385376560 hasRelatedWork W4281760909 @default.
- W4385376560 hasRelatedWork W4287995534 @default.
- W4385376560 isParatext "false" @default.
- W4385376560 isRetracted "false" @default.
- W4385376560 workType "book-chapter" @default.