FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3122999666> ?p ?o ?g. }

• W3122999666 abstract "Graph representation of structured data can facilitate the extraction of stereoscopic features, and it has demonstrated excellent ability when working with deep learning systems, the so-called Graph Neural Networks (GNNs). Choosing a promising architecture for constructing GNNs can be transferred to a hyperparameter optimisation problem, a very challenging task due to the size of the underlying search space and high computational cost for evaluating candidate GNNs. To address this issue, this research presents a novel genetic algorithm with a hierarchical evaluation strategy (HESGA), which combines the full evaluation of GNNs with a fast evaluation approach. By using full evaluation, a GNN is represented by a set of hyperparameter values and trained on a specified dataset, and root mean square error (RMSE) will be used to measure the quality of the GNN represented by the set of hyperparameter values (for regression problems). While in the proposed fast evaluation process, the training will be interrupted at an early stage, the difference of RMSE values between the starting and interrupted epochs will be used as a fast score, which implies the potential of the GNN being considered. To coordinate both types of evaluations, the proposed hierarchical strategy uses the fast evaluation in a lower level for recommending candidates to a higher level, where the full evaluation will act as a final assessor to maintain a group of elite individuals. To validate the effectiveness of HESGA, we apply it to optimise two types of deep graph neural networks. The experimental results on three benchmark datasets demonstrate its advantages compared to Bayesian hyperparameter optimization." @default.
• W3122999666 created "2021-02-01" @default.
• W3122999666 creator A5046978138 @default.
• W3122999666 creator A5061397843 @default.
• W3122999666 creator A5082375941 @default.
• W3122999666 creator A5091219117 @default.
• W3122999666 date "2021-01-22" @default.
• W3122999666 modified "2023-10-17" @default.
• W3122999666 title "A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networks" @default.
• W3122999666 cites W1553373771 @default.
• W3122999666 cites W1595498733 @default.
• W3122999666 cites W1798702550 @default.
• W3122999666 cites W1975147762 @default.
• W3122999666 cites W2008505552 @default.
• W3122999666 cites W2024372894 @default.
• W3122999666 cites W2047094503 @default.
• W3122999666 cites W2076498053 @default.
• W3122999666 cites W2097571405 @default.
• W3122999666 cites W2097998348 @default.
• W3122999666 cites W2126105956 @default.
• W3122999666 cites W2131241448 @default.
• W3122999666 cites W2140404878 @default.
• W3122999666 cites W2173183968 @default.
• W3122999666 cites W2210287443 @default.
• W3122999666 cites W2250904038 @default.
• W3122999666 cites W225560312 @default.
• W3122999666 cites W2283268937 @default.
• W3122999666 cites W2288758989 @default.
• W3122999666 cites W2574787734 @default.
• W3122999666 cites W2594183968 @default.
• W3122999666 cites W2606006859 @default.
• W3122999666 cites W2625776493 @default.
• W3122999666 cites W2736793217 @default.
• W3122999666 cites W2755520760 @default.
• W3122999666 cites W2780562800 @default.
• W3122999666 cites W2782417188 @default.
• W3122999666 cites W2792338380 @default.
• W3122999666 cites W2883188678 @default.
• W3122999666 cites W2898741784 @default.
• W3122999666 cites W2905224888 @default.
• W3122999666 cites W2947998308 @default.
• W3122999666 cites W2963224980 @default.
• W3122999666 cites W2963423218 @default.
• W3122999666 cites W2963474950 @default.
• W3122999666 cites W2964081807 @default.
• W3122999666 cites W2964113829 @default.
• W3122999666 cites W2965658867 @default.
• W3122999666 cites W2980729512 @default.
• W3122999666 cites W2985451450 @default.
• W3122999666 cites W2989219762 @default.
• W3122999666 cites W3034723893 @default.
• W3122999666 cites W3036810572 @default.
• W3122999666 cites W3080834109 @default.
• W3122999666 cites W3097836457 @default.
• W3122999666 doi "https://doi.org/10.48550/arxiv.2101.09300" @default.
• W3122999666 hasPublicationYear "2021" @default.
• W3122999666 type Work @default.
• W3122999666 sameAs 3122999666 @default.
• W3122999666 citedByCount "3" @default.
• W3122999666 countsByYear W31229996662021 @default.
• W3122999666 crossrefType "posted-content" @default.
• W3122999666 hasAuthorship W3122999666A5046978138 @default.
• W3122999666 hasAuthorship W3122999666A5061397843 @default.
• W3122999666 hasAuthorship W3122999666A5082375941 @default.
• W3122999666 hasAuthorship W3122999666A5091219117 @default.
• W3122999666 hasBestOaLocation W31229996661 @default.
• W3122999666 hasConcept C105795698 @default.
• W3122999666 hasConcept C119857082 @default.
• W3122999666 hasConcept C124101348 @default.
• W3122999666 hasConcept C132525143 @default.
• W3122999666 hasConcept C13280743 @default.
• W3122999666 hasConcept C139945424 @default.
• W3122999666 hasConcept C154945302 @default.
• W3122999666 hasConcept C177264268 @default.
• W3122999666 hasConcept C185798385 @default.
• W3122999666 hasConcept C199360897 @default.
• W3122999666 hasConcept C205649164 @default.
• W3122999666 hasConcept C33923547 @default.
• W3122999666 hasConcept C41008148 @default.
• W3122999666 hasConcept C50644808 @default.
• W3122999666 hasConcept C80444323 @default.
• W3122999666 hasConcept C83546350 @default.
• W3122999666 hasConcept C8642999 @default.
• W3122999666 hasConceptScore W3122999666C105795698 @default.
• W3122999666 hasConceptScore W3122999666C119857082 @default.
• W3122999666 hasConceptScore W3122999666C124101348 @default.
• W3122999666 hasConceptScore W3122999666C132525143 @default.
• W3122999666 hasConceptScore W3122999666C13280743 @default.
• W3122999666 hasConceptScore W3122999666C139945424 @default.
• W3122999666 hasConceptScore W3122999666C154945302 @default.
• W3122999666 hasConceptScore W3122999666C177264268 @default.
• W3122999666 hasConceptScore W3122999666C185798385 @default.
• W3122999666 hasConceptScore W3122999666C199360897 @default.
• W3122999666 hasConceptScore W3122999666C205649164 @default.
• W3122999666 hasConceptScore W3122999666C33923547 @default.
• W3122999666 hasConceptScore W3122999666C41008148 @default.
• W3122999666 hasConceptScore W3122999666C50644808 @default.
• W3122999666 hasConceptScore W3122999666C80444323 @default.
• W3122999666 hasConceptScore W3122999666C83546350 @default.
• W3122999666 hasConceptScore W3122999666C8642999 @default.

• next