FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890850650> ?p ?o ?g. }

• W2890850650 endingPage "1701" @default.
• W2890850650 startingPage "1690" @default.
• W2890850650 abstract "We propose a data-efficient Gaussian process-based Bayesian approach to the semi-supervised learning problem on graphs. The proposed model shows extremely competitive performance when compared to the state-of-the-art graph neural networks on semi-supervised learning benchmark experiments, and outperforms the neural networks in active learning experiments where labels are scarce. Furthermore, the model does not require a validation data set for early stopping to control over-fitting. Our model can be viewed as an instance of empirical distribution regression weighted locally by network connectivity. We further motivate the intuitive construction of the model with a Bayesian linear model interpretation where the node features are filtered by an operator related to the graph Laplacian. The method can be easily implemented by adapting off-the-shelf scalable variational inference algorithms for Gaussian processes." @default.
• W2890850650 created "2018-09-27" @default.
• W2890850650 creator A5013018598 @default.
• W2890850650 creator A5033941123 @default.
• W2890850650 creator A5079590996 @default.
• W2890850650 date "2018-12-03" @default.
• W2890850650 modified "2023-10-08" @default.
• W2890850650 title "Bayesian semi-supervised learning with graph gaussian processes" @default.
• W2890850650 cites W1501856433 @default.
• W2890850650 cites W1578099820 @default.
• W2890850650 cites W1653444175 @default.
• W2890850650 cites W1746819321 @default.
• W2890850650 cites W1774304772 @default.
• W2890850650 cites W1908728294 @default.
• W2890850650 cites W1990488619 @default.
• W2890850650 cites W2029604420 @default.
• W2890850650 cites W2032005951 @default.
• W2890850650 cites W2034747098 @default.
• W2890850650 cites W2073020428 @default.
• W2890850650 cites W2098961198 @default.
• W2890850650 cites W2101491865 @default.
• W2890850650 cites W2104290444 @default.
• W2890850650 cites W2116341502 @default.
• W2890850650 cites W2118159011 @default.
• W2890850650 cites W2128973832 @default.
• W2890850650 cites W2130283669 @default.
• W2890850650 cites W2136504847 @default.
• W2890850650 cites W2139823104 @default.
• W2890850650 cites W2144211451 @default.
• W2890850650 cites W2148319469 @default.
• W2890850650 cites W2169410692 @default.
• W2890850650 cites W2210832646 @default.
• W2890850650 cites W2244807774 @default.
• W2890850650 cites W2315403234 @default.
• W2890850650 cites W2407712691 @default.
• W2890850650 cites W2465015709 @default.
• W2890850650 cites W2468907370 @default.
• W2890850650 cites W2514059336 @default.
• W2890850650 cites W2558460151 @default.
• W2890850650 cites W2558748708 @default.
• W2890850650 cites W2884453666 @default.
• W2890850650 cites W2911738047 @default.
• W2890850650 cites W2962756421 @default.
• W2890850650 cites W2963614384 @default.
• W2890850650 cites W2963711523 @default.
• W2890850650 cites W3101183984 @default.
• W2890850650 cites W824892955 @default.
• W2890850650 hasPublicationYear "2018" @default.
• W2890850650 type Work @default.
• W2890850650 sameAs 2890850650 @default.
• W2890850650 citedByCount "9" @default.
• W2890850650 countsByYear W28908506502018 @default.
• W2890850650 countsByYear W28908506502019 @default.
• W2890850650 countsByYear W28908506502020 @default.
• W2890850650 countsByYear W28908506502021 @default.
• W2890850650 countsByYear W28908506502023 @default.
• W2890850650 crossrefType "proceedings-article" @default.
• W2890850650 hasAuthorship W2890850650A5013018598 @default.
• W2890850650 hasAuthorship W2890850650A5033941123 @default.
• W2890850650 hasAuthorship W2890850650A5079590996 @default.
• W2890850650 hasConcept C115178988 @default.
• W2890850650 hasConcept C119857082 @default.
• W2890850650 hasConcept C121332964 @default.
• W2890850650 hasConcept C132525143 @default.
• W2890850650 hasConcept C154945302 @default.
• W2890850650 hasConcept C155846161 @default.
• W2890850650 hasConcept C163716315 @default.
• W2890850650 hasConcept C2776214188 @default.
• W2890850650 hasConcept C41008148 @default.
• W2890850650 hasConcept C58973888 @default.
• W2890850650 hasConcept C61326573 @default.
• W2890850650 hasConcept C62520636 @default.
• W2890850650 hasConcept C80444323 @default.
• W2890850650 hasConceptScore W2890850650C115178988 @default.
• W2890850650 hasConceptScore W2890850650C119857082 @default.
• W2890850650 hasConceptScore W2890850650C121332964 @default.
• W2890850650 hasConceptScore W2890850650C132525143 @default.
• W2890850650 hasConceptScore W2890850650C154945302 @default.
• W2890850650 hasConceptScore W2890850650C155846161 @default.
• W2890850650 hasConceptScore W2890850650C163716315 @default.
• W2890850650 hasConceptScore W2890850650C2776214188 @default.
• W2890850650 hasConceptScore W2890850650C41008148 @default.
• W2890850650 hasConceptScore W2890850650C58973888 @default.
• W2890850650 hasConceptScore W2890850650C61326573 @default.
• W2890850650 hasConceptScore W2890850650C62520636 @default.
• W2890850650 hasConceptScore W2890850650C80444323 @default.
• W2890850650 hasLocation W28908506501 @default.
• W2890850650 hasOpenAccess W2890850650 @default.
• W2890850650 hasPrimaryLocation W28908506501 @default.
• W2890850650 hasRelatedWork W1574138145 @default.
• W2890850650 hasRelatedWork W1583505058 @default.
• W2890850650 hasRelatedWork W2096989558 @default.
• W2890850650 hasRelatedWork W2106668826 @default.
• W2890850650 hasRelatedWork W2121953881 @default.
• W2890850650 hasRelatedWork W2247622001 @default.
• W2890850650 hasRelatedWork W2280751535 @default.
• W2890850650 hasRelatedWork W2512044834 @default.
• W2890850650 hasRelatedWork W2595360690 @default.

• next