Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197529899> ?p ?o ?g. }
- W3197529899 abstract "Graph neural networks (GNNs) have been successfully applied to learning representation on graphs in many relational tasks. Recently, researchers study neural architecture search (NAS) to reduce the dependence of human expertise and explore better GNN architectures, but they over-emphasize entity features and ignore latent relation information concealed in the edges. To solve this problem, we incorporate edge features into graph search space and propose Edge-featured Graph Neural Architecture Search to find the optimal GNN architecture. Specifically, we design rich entity and edge updating operations to learn high-order representations, which convey more generic message passing mechanisms. Moreover, the architecture topology in our search space allows to explore complex feature dependence of both entities and edges, which can be efficiently optimized by differentiable search strategy. Experiments at three graph tasks on six datasets show EGNAS can search better GNNs with higher performance than current state-of-the-art human-designed and searched-based GNNs." @default.
- W3197529899 created "2021-09-13" @default.
- W3197529899 creator A5003217535 @default.
- W3197529899 creator A5006870317 @default.
- W3197529899 creator A5049313711 @default.
- W3197529899 creator A5074233262 @default.
- W3197529899 creator A5076495171 @default.
- W3197529899 date "2021-09-03" @default.
- W3197529899 modified "2023-09-23" @default.
- W3197529899 title "Edge-featured Graph Neural Architecture Search" @default.
- W3197529899 cites W1522301498 @default.
- W3197529899 cites W1924770834 @default.
- W3197529899 cites W2027482274 @default.
- W3197529899 cites W2112796928 @default.
- W3197529899 cites W2118246710 @default.
- W3197529899 cites W2150134853 @default.
- W3197529899 cites W2244807774 @default.
- W3197529899 cites W2519887557 @default.
- W3197529899 cites W2553303224 @default.
- W3197529899 cites W2558460151 @default.
- W3197529899 cites W2558748708 @default.
- W3197529899 cites W2559839022 @default.
- W3197529899 cites W2594529350 @default.
- W3197529899 cites W2604314403 @default.
- W3197529899 cites W2624431344 @default.
- W3197529899 cites W2766453196 @default.
- W3197529899 cites W2767002384 @default.
- W3197529899 cites W2768242641 @default.
- W3197529899 cites W2905672847 @default.
- W3197529899 cites W2951104886 @default.
- W3197529899 cites W2951545716 @default.
- W3197529899 cites W2951886768 @default.
- W3197529899 cites W2952915411 @default.
- W3197529899 cites W2962711740 @default.
- W3197529899 cites W2962746461 @default.
- W3197529899 cites W2963921132 @default.
- W3197529899 cites W2964081807 @default.
- W3197529899 cites W2964259004 @default.
- W3197529899 cites W2964915865 @default.
- W3197529899 cites W2965658867 @default.
- W3197529899 cites W2966256598 @default.
- W3197529899 cites W2971564650 @default.
- W3197529899 cites W2972830778 @default.
- W3197529899 cites W2973943791 @default.
- W3197529899 cites W2996409713 @default.
- W3197529899 cites W3007332492 @default.
- W3197529899 cites W3016124664 @default.
- W3197529899 cites W3026937485 @default.
- W3197529899 cites W3034202788 @default.
- W3197529899 cites W3034452783 @default.
- W3197529899 cites W3034723893 @default.
- W3197529899 cites W3041877813 @default.
- W3197529899 cites W3080510905 @default.
- W3197529899 cites W3081209961 @default.
- W3197529899 cites W3082519296 @default.
- W3197529899 cites W3101753637 @default.
- W3197529899 cites W3104978323 @default.
- W3197529899 cites W3121945093 @default.
- W3197529899 cites W3135546355 @default.
- W3197529899 cites W3161172957 @default.
- W3197529899 cites W3097836457 @default.
- W3197529899 doi "https://doi.org/10.48550/arxiv.2109.01356" @default.
- W3197529899 hasPublicationYear "2021" @default.
- W3197529899 type Work @default.
- W3197529899 sameAs 3197529899 @default.
- W3197529899 citedByCount "0" @default.
- W3197529899 crossrefType "posted-content" @default.
- W3197529899 hasAuthorship W3197529899A5003217535 @default.
- W3197529899 hasAuthorship W3197529899A5006870317 @default.
- W3197529899 hasAuthorship W3197529899A5049313711 @default.
- W3197529899 hasAuthorship W3197529899A5074233262 @default.
- W3197529899 hasAuthorship W3197529899A5076495171 @default.
- W3197529899 hasBestOaLocation W31975298991 @default.
- W3197529899 hasConcept C119857082 @default.
- W3197529899 hasConcept C123657996 @default.
- W3197529899 hasConcept C132525143 @default.
- W3197529899 hasConcept C134306372 @default.
- W3197529899 hasConcept C142362112 @default.
- W3197529899 hasConcept C153349607 @default.
- W3197529899 hasConcept C154945302 @default.
- W3197529899 hasConcept C162307627 @default.
- W3197529899 hasConcept C202615002 @default.
- W3197529899 hasConcept C33923547 @default.
- W3197529899 hasConcept C41008148 @default.
- W3197529899 hasConcept C50644808 @default.
- W3197529899 hasConcept C80444323 @default.
- W3197529899 hasConceptScore W3197529899C119857082 @default.
- W3197529899 hasConceptScore W3197529899C123657996 @default.
- W3197529899 hasConceptScore W3197529899C132525143 @default.
- W3197529899 hasConceptScore W3197529899C134306372 @default.
- W3197529899 hasConceptScore W3197529899C142362112 @default.
- W3197529899 hasConceptScore W3197529899C153349607 @default.
- W3197529899 hasConceptScore W3197529899C154945302 @default.
- W3197529899 hasConceptScore W3197529899C162307627 @default.
- W3197529899 hasConceptScore W3197529899C202615002 @default.
- W3197529899 hasConceptScore W3197529899C33923547 @default.
- W3197529899 hasConceptScore W3197529899C41008148 @default.
- W3197529899 hasConceptScore W3197529899C50644808 @default.
- W3197529899 hasConceptScore W3197529899C80444323 @default.
- W3197529899 hasLocation W31975298991 @default.