Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213450741> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3213450741 abstract "Machine learning techniques are being applied in quantifying structure-property relationships for a wide variety of materials, where the properly representing materials plays key roles. Although algorithms for representation learning are extensively studied, their applications to domain-specific areas, such as polymer, are limited largely due to the lack of benchmark databases. In this work, we investigate different types of polymer representations, including Morgan Fingerprint (MF), molecular embedding (ME) and molecular graph (MG), based on a benchmark database from a subset of PolyInfo. We evaluate the quality of different polymer representations via quantifying the relationships between the representations and polymer properties, including density, melting temperature and glass transition temperature. Different representation learning schemes, such as supervised learning, semi-supervised learning and transfer learning, are investigated. It is found that ME outperforms the other representations for structure-property relationship quantification in all cases studied, and MG is shown to be much inferior than ME and MF, likely due to the relatively small volumes of training data available. For MEs, it is found that the similarities of substructure MEs under different learning schemes (e.g., SL, SSL and TL) are differently estimated, thus leading to different performance scores in structure-property relation quantification. Several ME mixtures have shown to outperform the single MEs in the corresponding regression tasks, and this is attributed to the information gain when mixing different ME." @default.
- W3213450741 created "2021-11-22" @default.
- W3213450741 creator A5022684050 @default.
- W3213450741 creator A5036145381 @default.
- W3213450741 creator A5048860788 @default.
- W3213450741 creator A5065387614 @default.
- W3213450741 creator A5084338979 @default.
- W3213450741 date "2019-05-02" @default.
- W3213450741 modified "2023-09-23" @default.
- W3213450741 title "Evaluating Polymer Representations via Quantifying Structure-Property Relationships" @default.
- W3213450741 doi "https://doi.org/10.26434/chemrxiv.8060000.v1" @default.
- W3213450741 hasPublicationYear "2019" @default.
- W3213450741 type Work @default.
- W3213450741 sameAs 3213450741 @default.
- W3213450741 citedByCount "0" @default.
- W3213450741 crossrefType "posted-content" @default.
- W3213450741 hasAuthorship W3213450741A5022684050 @default.
- W3213450741 hasAuthorship W3213450741A5036145381 @default.
- W3213450741 hasAuthorship W3213450741A5048860788 @default.
- W3213450741 hasAuthorship W3213450741A5065387614 @default.
- W3213450741 hasAuthorship W3213450741A5084338979 @default.
- W3213450741 hasConcept C111472728 @default.
- W3213450741 hasConcept C119857082 @default.
- W3213450741 hasConcept C124101348 @default.
- W3213450741 hasConcept C127413603 @default.
- W3213450741 hasConcept C13280743 @default.
- W3213450741 hasConcept C138885662 @default.
- W3213450741 hasConcept C150899416 @default.
- W3213450741 hasConcept C154945302 @default.
- W3213450741 hasConcept C17744445 @default.
- W3213450741 hasConcept C185798385 @default.
- W3213450741 hasConcept C189950617 @default.
- W3213450741 hasConcept C199539241 @default.
- W3213450741 hasConcept C205649164 @default.
- W3213450741 hasConcept C25343380 @default.
- W3213450741 hasConcept C2776359362 @default.
- W3213450741 hasConcept C41008148 @default.
- W3213450741 hasConcept C41608201 @default.
- W3213450741 hasConcept C59404180 @default.
- W3213450741 hasConcept C66938386 @default.
- W3213450741 hasConcept C80444323 @default.
- W3213450741 hasConcept C94625758 @default.
- W3213450741 hasConcept C99679407 @default.
- W3213450741 hasConceptScore W3213450741C111472728 @default.
- W3213450741 hasConceptScore W3213450741C119857082 @default.
- W3213450741 hasConceptScore W3213450741C124101348 @default.
- W3213450741 hasConceptScore W3213450741C127413603 @default.
- W3213450741 hasConceptScore W3213450741C13280743 @default.
- W3213450741 hasConceptScore W3213450741C138885662 @default.
- W3213450741 hasConceptScore W3213450741C150899416 @default.
- W3213450741 hasConceptScore W3213450741C154945302 @default.
- W3213450741 hasConceptScore W3213450741C17744445 @default.
- W3213450741 hasConceptScore W3213450741C185798385 @default.
- W3213450741 hasConceptScore W3213450741C189950617 @default.
- W3213450741 hasConceptScore W3213450741C199539241 @default.
- W3213450741 hasConceptScore W3213450741C205649164 @default.
- W3213450741 hasConceptScore W3213450741C25343380 @default.
- W3213450741 hasConceptScore W3213450741C2776359362 @default.
- W3213450741 hasConceptScore W3213450741C41008148 @default.
- W3213450741 hasConceptScore W3213450741C41608201 @default.
- W3213450741 hasConceptScore W3213450741C59404180 @default.
- W3213450741 hasConceptScore W3213450741C66938386 @default.
- W3213450741 hasConceptScore W3213450741C80444323 @default.
- W3213450741 hasConceptScore W3213450741C94625758 @default.
- W3213450741 hasConceptScore W3213450741C99679407 @default.
- W3213450741 hasLocation W32134507411 @default.
- W3213450741 hasOpenAccess W3213450741 @default.
- W3213450741 hasPrimaryLocation W32134507411 @default.
- W3213450741 hasRelatedWork W1165741764 @default.
- W3213450741 hasRelatedWork W1278276328 @default.
- W3213450741 hasRelatedWork W2783777501 @default.
- W3213450741 hasRelatedWork W2811024573 @default.
- W3213450741 hasRelatedWork W2892611525 @default.
- W3213450741 hasRelatedWork W2901287800 @default.
- W3213450741 hasRelatedWork W2997072756 @default.
- W3213450741 hasRelatedWork W3005343217 @default.
- W3213450741 hasRelatedWork W3010937527 @default.
- W3213450741 hasRelatedWork W3013188600 @default.
- W3213450741 hasRelatedWork W3020537215 @default.
- W3213450741 hasRelatedWork W3026239495 @default.
- W3213450741 hasRelatedWork W3034838799 @default.
- W3213450741 hasRelatedWork W3035664806 @default.
- W3213450741 hasRelatedWork W3090840841 @default.
- W3213450741 hasRelatedWork W3095190524 @default.
- W3213450741 hasRelatedWork W3154488273 @default.
- W3213450741 hasRelatedWork W3169646931 @default.
- W3213450741 hasRelatedWork W3175359828 @default.
- W3213450741 hasRelatedWork W3207749172 @default.
- W3213450741 isParatext "false" @default.
- W3213450741 isRetracted "false" @default.
- W3213450741 magId "3213450741" @default.
- W3213450741 workType "article" @default.