FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300772200> ?p ?o ?g. }

• W4300772200 endingPage "118916" @default.
• W4300772200 startingPage "118916" @default.
• W4300772200 abstract "Graph Neural Networks (GNNs) have emerged recently as a powerful way of dealing with non-Euclidean data on graphs, such as social networks and citation networks. Despite their success, obtaining optimal graph neural networks requires immense manual work and domain knowledge. Inspired by the strong searching capability of neural architecture search in CNN, a few attempts automatically search optimal GNNs that rival the best human-invented architectures. However, existing Graph Neural Architecture Search (GNAS) approaches face two challenges: (1) Sampling GNNs across the entire search space results in low search efficiency, particularly in large search spaces. (2) It is pretty costly to evaluate GNNs by training architectures from scratch. To overcome these challenges, this paper proposes an Efficient Graph Neural Architecture Search (EGNAS) method based on Monte Carlo Tree Search (MCTS) and a prediction network. Specifically, EGNAS first uses MCTS to recursively partition the entire search space into good or bad search regions. Then, the reinforcement learning-based search strategy (also called the agent) is applied to sample GNNs in those good search regions, which prevents overly exploring complex architectures and bad-performance regions, thus improving sampling efficiency. To reduce the evaluation cost, we use a prediction network to estimate the performance of GNNs. We alternately use ground-truth accuracy (by training GNNs from scratch) and prediction accuracy (by the prediction network) to update the search strategy to avoid inaccuracies caused by long-term use of the prediction network. Furthermore, to improve the training efficiency and stability, the agent is trained by a variant of Proximal Policy Optimization. Experiments show that EGNAS can search for better GNNs in the promising search region in a shorter search time, with an accuracy of 83.5%, 73.3%, 79.6%, and 94.5% on Cora, Citeseer, Pubmed, and Photo datasets, respectively In particular, compared to the most popular GNAS algorithm, our EGNAS-NP without using the prediction network achieves an accuracy of 83.6% on Cora, 73.5% on Citeseer, 79.9% on Pubmed, and 94.6% on Photo, with a relative improvement of 0.6%, 0.2%, 0.7%, and 0.6%." @default.
• W4300772200 created "2022-10-04" @default.
• W4300772200 creator A5010197223 @default.
• W4300772200 creator A5088941117 @default.
• W4300772200 date "2023-03-01" @default.
• W4300772200 modified "2023-10-14" @default.
• W4300772200 title "Efficient graph neural architecture search using Monte Carlo Tree search and prediction network" @default.
• W4300772200 cites W2116341502 @default.
• W4300772200 cites W2119717200 @default.
• W4300772200 cites W2153959628 @default.
• W4300772200 cites W2168405694 @default.
• W4300772200 cites W2257979135 @default.
• W4300772200 cites W2902907165 @default.
• W4300772200 cites W2912636151 @default.
• W4300772200 cites W3007309629 @default.
• W4300772200 cites W3090369187 @default.
• W4300772200 cites W3107237154 @default.
• W4300772200 cites W3152893301 @default.
• W4300772200 cites W3166059025 @default.
• W4300772200 cites W3168130883 @default.
• W4300772200 cites W3170112077 @default.
• W4300772200 cites W3194071146 @default.
• W4300772200 cites W3202775986 @default.
• W4300772200 cites W3215748189 @default.
• W4300772200 cites W4210257598 @default.
• W4300772200 doi "https://doi.org/10.1016/j.eswa.2022.118916" @default.
• W4300772200 hasPublicationYear "2023" @default.
• W4300772200 type Work @default.
• W4300772200 citedByCount "3" @default.
• W4300772200 countsByYear W43007722002023 @default.
• W4300772200 crossrefType "journal-article" @default.
• W4300772200 hasAuthorship W4300772200A5010197223 @default.
• W4300772200 hasAuthorship W4300772200A5088941117 @default.
• W4300772200 hasConcept C105795698 @default.
• W4300772200 hasConcept C11413529 @default.
• W4300772200 hasConcept C119857082 @default.
• W4300772200 hasConcept C124101348 @default.
• W4300772200 hasConcept C125583679 @default.
• W4300772200 hasConcept C132525143 @default.
• W4300772200 hasConcept C139979381 @default.
• W4300772200 hasConcept C154945302 @default.
• W4300772200 hasConcept C19499675 @default.
• W4300772200 hasConcept C19889080 @default.
• W4300772200 hasConcept C33923547 @default.
• W4300772200 hasConcept C41008148 @default.
• W4300772200 hasConcept C46149586 @default.
• W4300772200 hasConcept C50644808 @default.
• W4300772200 hasConcept C80444323 @default.
• W4300772200 hasConceptScore W4300772200C105795698 @default.
• W4300772200 hasConceptScore W4300772200C11413529 @default.
• W4300772200 hasConceptScore W4300772200C119857082 @default.
• W4300772200 hasConceptScore W4300772200C124101348 @default.
• W4300772200 hasConceptScore W4300772200C125583679 @default.
• W4300772200 hasConceptScore W4300772200C132525143 @default.
• W4300772200 hasConceptScore W4300772200C139979381 @default.
• W4300772200 hasConceptScore W4300772200C154945302 @default.
• W4300772200 hasConceptScore W4300772200C19499675 @default.
• W4300772200 hasConceptScore W4300772200C19889080 @default.
• W4300772200 hasConceptScore W4300772200C33923547 @default.
• W4300772200 hasConceptScore W4300772200C41008148 @default.
• W4300772200 hasConceptScore W4300772200C46149586 @default.
• W4300772200 hasConceptScore W4300772200C50644808 @default.
• W4300772200 hasConceptScore W4300772200C80444323 @default.
• W4300772200 hasFunder F4320321001 @default.
• W4300772200 hasLocation W43007722001 @default.
• W4300772200 hasOpenAccess W4300772200 @default.
• W4300772200 hasPrimaryLocation W43007722001 @default.
• W4300772200 hasRelatedWork W128952136 @default.
• W4300772200 hasRelatedWork W1605835093 @default.
• W4300772200 hasRelatedWork W1994919150 @default.
• W4300772200 hasRelatedWork W2064794194 @default.
• W4300772200 hasRelatedWork W2081821176 @default.
• W4300772200 hasRelatedWork W2358427436 @default.
• W4300772200 hasRelatedWork W2510420671 @default.
• W4300772200 hasRelatedWork W2970365156 @default.
• W4300772200 hasRelatedWork W4206302813 @default.
• W4300772200 hasRelatedWork W4322703856 @default.
• W4300772200 hasVolume "213" @default.
• W4300772200 isParatext "false" @default.
• W4300772200 isRetracted "false" @default.
• W4300772200 workType "article" @default.