FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3153029438> ?p ?o ?g. }

• W3153029438 abstract "Recently, the study of graph neural network (GNN) has attracted much attention and achieved promising performance in molecular property prediction. Most GNNs for molecular property prediction are proposed based on the idea of learning the representations for the nodes by aggregating the information of their neighbor nodes (e.g. atoms). Then, the representations can be passed to subsequent layers to deal with individual downstream tasks. Therefore, the architectures of GNNs can be considered as being composed of two core parts: graph-related layers and task-specific layers. Facing real-world molecular problems, the hyperparameter optimization for those layers are vital. Hyperparameter optimization (HPO) becomes expensive in this situation because evaluating candidate solutions requires massive computational resources to train and validate models. Furthermore, a larger search space often makes the HPO problems more challenging. In this research, we focus on the impact of selecting two types of GNN hyperparameters, those belonging to graph-related layers and those of task-specific layers, on the performance of GNN for molecular property prediction. In our experiments. we employed a state-of-the-art evolutionary algorithm (i.e., CMA-ES) for HPO. The results reveal that optimizing the two types of hyperparameters separately can gain the improvements on GNNs' performance, but optimising both types of hyperparameters simultaneously will lead to predominant improvements. Meanwhile, our study also further confirms the importance of HPO for GNNs in molecular property prediction problems." @default.
• W3153029438 created "2021-04-26" @default.
• W3153029438 creator A5046978138 @default.
• W3153029438 creator A5061397843 @default.
• W3153029438 creator A5091219117 @default.
• W3153029438 date "2021-04-13" @default.
• W3153029438 modified "2023-09-27" @default.
• W3153029438 title "Which Hyperparameters to Optimise? An Investigation of Evolutionary Hyperparameter Optimisation in Graph Neural Network For Molecular Property Prediction" @default.
• W3153029438 cites W1501856433 @default.
• W3153029438 cites W1579744901 @default.
• W3153029438 cites W1975147762 @default.
• W3153029438 cites W2008505552 @default.
• W3153029438 cites W2106411961 @default.
• W3153029438 cites W2126559945 @default.
• W3153029438 cites W2173027866 @default.
• W3153029438 cites W2244807774 @default.
• W3153029438 cites W2269544137 @default.
• W3153029438 cites W2336687883 @default.
• W3153029438 cites W2519887557 @default.
• W3153029438 cites W2594183968 @default.
• W3153029438 cites W2606780347 @default.
• W3153029438 cites W2735246657 @default.
• W3153029438 cites W2811124557 @default.
• W3153029438 cites W2894175828 @default.
• W3153029438 cites W2907079035 @default.
• W3153029438 cites W2908974255 @default.
• W3153029438 cites W2909882940 @default.
• W3153029438 cites W2914721378 @default.
• W3153029438 cites W2949676527 @default.
• W3153029438 cites W2951659295 @default.
• W3153029438 cites W2963017945 @default.
• W3153029438 cites W2963066159 @default.
• W3153029438 cites W2963334428 @default.
• W3153029438 cites W2963984147 @default.
• W3153029438 cites W2966357564 @default.
• W3153029438 cites W2969457089 @default.
• W3153029438 cites W3000478925 @default.
• W3153029438 cites W3013868095 @default.
• W3153029438 cites W3015494591 @default.
• W3153029438 cites W3110901318 @default.
• W3153029438 cites W3110902746 @default.
• W3153029438 cites W3116202926 @default.
• W3153029438 cites W3122999666 @default.
• W3153029438 cites W3131147239 @default.
• W3153029438 cites W3135127269 @default.
• W3153029438 cites W637153065 @default.
• W3153029438 hasPublicationYear "2021" @default.
• W3153029438 type Work @default.
• W3153029438 sameAs 3153029438 @default.
• W3153029438 citedByCount "0" @default.
• W3153029438 crossrefType "posted-content" @default.
• W3153029438 hasAuthorship W3153029438A5046978138 @default.
• W3153029438 hasAuthorship W3153029438A5061397843 @default.
• W3153029438 hasAuthorship W3153029438A5091219117 @default.
• W3153029438 hasConcept C111472728 @default.
• W3153029438 hasConcept C119857082 @default.
• W3153029438 hasConcept C127413603 @default.
• W3153029438 hasConcept C132525143 @default.
• W3153029438 hasConcept C138885662 @default.
• W3153029438 hasConcept C154945302 @default.
• W3153029438 hasConcept C189950617 @default.
• W3153029438 hasConcept C201995342 @default.
• W3153029438 hasConcept C2780451532 @default.
• W3153029438 hasConcept C41008148 @default.
• W3153029438 hasConcept C50644808 @default.
• W3153029438 hasConcept C80444323 @default.
• W3153029438 hasConcept C8642999 @default.
• W3153029438 hasConceptScore W3153029438C111472728 @default.
• W3153029438 hasConceptScore W3153029438C119857082 @default.
• W3153029438 hasConceptScore W3153029438C127413603 @default.
• W3153029438 hasConceptScore W3153029438C132525143 @default.
• W3153029438 hasConceptScore W3153029438C138885662 @default.
• W3153029438 hasConceptScore W3153029438C154945302 @default.
• W3153029438 hasConceptScore W3153029438C189950617 @default.
• W3153029438 hasConceptScore W3153029438C201995342 @default.
• W3153029438 hasConceptScore W3153029438C2780451532 @default.
• W3153029438 hasConceptScore W3153029438C41008148 @default.
• W3153029438 hasConceptScore W3153029438C50644808 @default.
• W3153029438 hasConceptScore W3153029438C80444323 @default.
• W3153029438 hasConceptScore W3153029438C8642999 @default.
• W3153029438 hasLocation W31530294381 @default.
• W3153029438 hasOpenAccess W3153029438 @default.
• W3153029438 hasPrimaryLocation W31530294381 @default.
• W3153029438 hasRelatedWork W1595115976 @default.
• W3153029438 hasRelatedWork W2011189936 @default.
• W3153029438 hasRelatedWork W2125121527 @default.
• W3153029438 hasRelatedWork W2411476716 @default.
• W3153029438 hasRelatedWork W2548077621 @default.
• W3153029438 hasRelatedWork W2554990182 @default.
• W3153029438 hasRelatedWork W2792191421 @default.
• W3153029438 hasRelatedWork W2804546959 @default.
• W3153029438 hasRelatedWork W2943154646 @default.
• W3153029438 hasRelatedWork W2982608503 @default.
• W3153029438 hasRelatedWork W2987488749 @default.
• W3153029438 hasRelatedWork W3006514345 @default.
• W3153029438 hasRelatedWork W3013732669 @default.
• W3153029438 hasRelatedWork W3031618159 @default.
• W3153029438 hasRelatedWork W3083000529 @default.
• W3153029438 hasRelatedWork W3132038172 @default.
• W3153029438 hasRelatedWork W3175465936 @default.

• next