Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382406608> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4382406608 endingPage "405" @default.
- W4382406608 startingPage "393" @default.
- W4382406608 abstract "Graph machine learning models have been successfully deployed in various application areas. One of the most prominent types of models – Graph Neural Networks (GNNs) – provides an elegant way of extracting expressive node-level representation vectors, which can be used to solve node-related problems, such as classifying users in a social network. However, many tasks require representations at the level of the whole graph, e.g., molecular applications. In order to convert node-level representations into a graph-level vector, a so-called readout function must be applied. In this work, we study existing readout methods, including simple non-trainable ones, as well as complex, parametrized models. We introduce a concept of ensemble-based readout functions that combine either representations or predictions. Our experiments show that such ensembles allow for better performance than simple single readouts or similar performance as the complex, parametrized ones, but at a fraction of the model complexity." @default.
- W4382406608 created "2023-06-29" @default.
- W4382406608 creator A5026855190 @default.
- W4382406608 creator A5039269881 @default.
- W4382406608 creator A5040042253 @default.
- W4382406608 creator A5050914099 @default.
- W4382406608 creator A5081185051 @default.
- W4382406608 date "2023-01-01" @default.
- W4382406608 modified "2023-10-14" @default.
- W4382406608 title "Graph-Level Representations Using Ensemble-Based Readout Functions" @default.
- W4382406608 cites W2008857988 @default.
- W4382406608 cites W2099438806 @default.
- W4382406608 cites W2170973067 @default.
- W4382406608 cites W2964199361 @default.
- W4382406608 cites W4295312788 @default.
- W4382406608 cites W4297445994 @default.
- W4382406608 cites W4299457904 @default.
- W4382406608 doi "https://doi.org/10.1007/978-3-031-35995-8_28" @default.
- W4382406608 hasPublicationYear "2023" @default.
- W4382406608 type Work @default.
- W4382406608 citedByCount "0" @default.
- W4382406608 crossrefType "book-chapter" @default.
- W4382406608 hasAuthorship W4382406608A5026855190 @default.
- W4382406608 hasAuthorship W4382406608A5039269881 @default.
- W4382406608 hasAuthorship W4382406608A5040042253 @default.
- W4382406608 hasAuthorship W4382406608A5050914099 @default.
- W4382406608 hasAuthorship W4382406608A5081185051 @default.
- W4382406608 hasBestOaLocation W43824066082 @default.
- W4382406608 hasConcept C111472728 @default.
- W4382406608 hasConcept C127413603 @default.
- W4382406608 hasConcept C132525143 @default.
- W4382406608 hasConcept C138885662 @default.
- W4382406608 hasConcept C154945302 @default.
- W4382406608 hasConcept C17744445 @default.
- W4382406608 hasConcept C199539241 @default.
- W4382406608 hasConcept C2776359362 @default.
- W4382406608 hasConcept C2780586882 @default.
- W4382406608 hasConcept C41008148 @default.
- W4382406608 hasConcept C62611344 @default.
- W4382406608 hasConcept C66938386 @default.
- W4382406608 hasConcept C80444323 @default.
- W4382406608 hasConcept C94625758 @default.
- W4382406608 hasConceptScore W4382406608C111472728 @default.
- W4382406608 hasConceptScore W4382406608C127413603 @default.
- W4382406608 hasConceptScore W4382406608C132525143 @default.
- W4382406608 hasConceptScore W4382406608C138885662 @default.
- W4382406608 hasConceptScore W4382406608C154945302 @default.
- W4382406608 hasConceptScore W4382406608C17744445 @default.
- W4382406608 hasConceptScore W4382406608C199539241 @default.
- W4382406608 hasConceptScore W4382406608C2776359362 @default.
- W4382406608 hasConceptScore W4382406608C2780586882 @default.
- W4382406608 hasConceptScore W4382406608C41008148 @default.
- W4382406608 hasConceptScore W4382406608C62611344 @default.
- W4382406608 hasConceptScore W4382406608C66938386 @default.
- W4382406608 hasConceptScore W4382406608C80444323 @default.
- W4382406608 hasConceptScore W4382406608C94625758 @default.
- W4382406608 hasLocation W43824066081 @default.
- W4382406608 hasLocation W43824066082 @default.
- W4382406608 hasOpenAccess W4382406608 @default.
- W4382406608 hasPrimaryLocation W43824066081 @default.
- W4382406608 hasRelatedWork W1549289070 @default.
- W4382406608 hasRelatedWork W1826416243 @default.
- W4382406608 hasRelatedWork W2038803387 @default.
- W4382406608 hasRelatedWork W2368259199 @default.
- W4382406608 hasRelatedWork W2728391469 @default.
- W4382406608 hasRelatedWork W3196755225 @default.
- W4382406608 hasRelatedWork W4238075012 @default.
- W4382406608 hasRelatedWork W4248389398 @default.
- W4382406608 hasRelatedWork W4323323198 @default.
- W4382406608 hasRelatedWork W2247596074 @default.
- W4382406608 isParatext "false" @default.
- W4382406608 isRetracted "false" @default.
- W4382406608 workType "book-chapter" @default.