Matches in SemOpenAlex for { <https://semopenalex.org/work/W4245873437> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4245873437 abstract "Predicting molecular properties remains a challenging task with numerous potential applications, notably in drug discovery. Recently, the development of deep learning, combined with rising amounts of data, has provided powerful tools to build predictive models. Since molecules can be encoded as graphs, Graph Neural Networks (GNNs) have emerged as a popular choice of architecture to tackle this task. Training GNNs to predict molecular properties however faces the challenge of collecting annotated data which is a costly and time consuming process. On the other hand, it is easy to access large databases of molecules without annotations. In this setting, self-supervised learning can efficiently leverage large amounts of non-annotated data to compensate for the lack of annotated ones. In this work, we introduce a self-supervised framework for GNNs tailored specifically for molecular property prediction. Our framework uses multiple pretext tasks focusing on different scales of molecules (atoms, fragments and entire molecules). We evaluate our method on a representative set of GNN architectures and datasets and also consider the impact of the choice of input features. Our results show that our framework can successfully improve performance compared to training from scratch, especially in low data regimes. The improvement varies depending on the dataset, model architecture and, importantly, on the choice of input feature representation." @default.
- W4245873437 created "2022-05-12" @default.
- W4245873437 creator A5007938243 @default.
- W4245873437 date "2021-10-15" @default.
- W4245873437 modified "2023-10-17" @default.
- W4245873437 title "Self-Supervised Learning for Molecular Property Prediction" @default.
- W4245873437 doi "https://doi.org/10.26434/chemrxiv-2021-vr43g" @default.
- W4245873437 hasPublicationYear "2021" @default.
- W4245873437 type Work @default.
- W4245873437 citedByCount "1" @default.
- W4245873437 countsByYear W42458734372022 @default.
- W4245873437 crossrefType "posted-content" @default.
- W4245873437 hasAuthorship W4245873437A5007938243 @default.
- W4245873437 hasBestOaLocation W42458734371 @default.
- W4245873437 hasConcept C111472728 @default.
- W4245873437 hasConcept C111919701 @default.
- W4245873437 hasConcept C119857082 @default.
- W4245873437 hasConcept C132525143 @default.
- W4245873437 hasConcept C138885662 @default.
- W4245873437 hasConcept C153083717 @default.
- W4245873437 hasConcept C154945302 @default.
- W4245873437 hasConcept C162324750 @default.
- W4245873437 hasConcept C177264268 @default.
- W4245873437 hasConcept C187736073 @default.
- W4245873437 hasConcept C189950617 @default.
- W4245873437 hasConcept C199360897 @default.
- W4245873437 hasConcept C2776145971 @default.
- W4245873437 hasConcept C2776401178 @default.
- W4245873437 hasConcept C2780451532 @default.
- W4245873437 hasConcept C41008148 @default.
- W4245873437 hasConcept C41895202 @default.
- W4245873437 hasConcept C51632099 @default.
- W4245873437 hasConcept C59404180 @default.
- W4245873437 hasConcept C80444323 @default.
- W4245873437 hasConcept C98045186 @default.
- W4245873437 hasConceptScore W4245873437C111472728 @default.
- W4245873437 hasConceptScore W4245873437C111919701 @default.
- W4245873437 hasConceptScore W4245873437C119857082 @default.
- W4245873437 hasConceptScore W4245873437C132525143 @default.
- W4245873437 hasConceptScore W4245873437C138885662 @default.
- W4245873437 hasConceptScore W4245873437C153083717 @default.
- W4245873437 hasConceptScore W4245873437C154945302 @default.
- W4245873437 hasConceptScore W4245873437C162324750 @default.
- W4245873437 hasConceptScore W4245873437C177264268 @default.
- W4245873437 hasConceptScore W4245873437C187736073 @default.
- W4245873437 hasConceptScore W4245873437C189950617 @default.
- W4245873437 hasConceptScore W4245873437C199360897 @default.
- W4245873437 hasConceptScore W4245873437C2776145971 @default.
- W4245873437 hasConceptScore W4245873437C2776401178 @default.
- W4245873437 hasConceptScore W4245873437C2780451532 @default.
- W4245873437 hasConceptScore W4245873437C41008148 @default.
- W4245873437 hasConceptScore W4245873437C41895202 @default.
- W4245873437 hasConceptScore W4245873437C51632099 @default.
- W4245873437 hasConceptScore W4245873437C59404180 @default.
- W4245873437 hasConceptScore W4245873437C80444323 @default.
- W4245873437 hasConceptScore W4245873437C98045186 @default.
- W4245873437 hasLocation W42458734371 @default.
- W4245873437 hasOpenAccess W4245873437 @default.
- W4245873437 hasPrimaryLocation W42458734371 @default.
- W4245873437 hasRelatedWork W2082624265 @default.
- W4245873437 hasRelatedWork W2905233337 @default.
- W4245873437 hasRelatedWork W3160195908 @default.
- W4245873437 hasRelatedWork W3174891612 @default.
- W4245873437 hasRelatedWork W3200371321 @default.
- W4245873437 hasRelatedWork W3204277253 @default.
- W4245873437 hasRelatedWork W3214301740 @default.
- W4245873437 hasRelatedWork W3214552351 @default.
- W4245873437 hasRelatedWork W4287116584 @default.
- W4245873437 hasRelatedWork W4366399932 @default.
- W4245873437 isParatext "false" @default.
- W4245873437 isRetracted "false" @default.
- W4245873437 workType "article" @default.