Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014294114> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W3014294114 endingPage "2421" @default.
- W3014294114 startingPage "2421" @default.
- W3014294114 abstract "Recently, graph neural networks (GNNs) have achieved great success in dealing with graph-based data. The basic idea of GNNs is iteratively aggregating the information from neighbors, which is a special form of Laplacian smoothing. However, most of GNNs fall into the over-smoothing problem, i.e., when the model goes deeper, the learned representations become indistinguishable. This reflects the inability of the current GNNs to explore the global graph structure. In this paper, we propose a novel graph neural network to address this problem. A rejection mechanism is designed to address the over-smoothing problem, and a dilated graph convolution kernel is presented to capture the high-level graph structure. A number of experimental results demonstrate that the proposed model outperforms the state-of-the-art GNNs, and can effectively overcome the over-smoothing problem." @default.
- W3014294114 created "2020-04-10" @default.
- W3014294114 creator A5015654718 @default.
- W3014294114 creator A5028779371 @default.
- W3014294114 creator A5075068126 @default.
- W3014294114 date "2020-04-02" @default.
- W3014294114 modified "2023-09-26" @default.
- W3014294114 title "Graph Dilated Network with Rejection Mechanism" @default.
- W3014294114 cites W2296746822 @default.
- W3014294114 cites W2612872092 @default.
- W3014294114 cites W2898455119 @default.
- W3014294114 cites W2910166679 @default.
- W3014294114 cites W2955290266 @default.
- W3014294114 cites W2963512530 @default.
- W3014294114 cites W3106400857 @default.
- W3014294114 doi "https://doi.org/10.3390/app10072421" @default.
- W3014294114 hasPublicationYear "2020" @default.
- W3014294114 type Work @default.
- W3014294114 sameAs 3014294114 @default.
- W3014294114 citedByCount "1" @default.
- W3014294114 countsByYear W30142941142022 @default.
- W3014294114 crossrefType "journal-article" @default.
- W3014294114 hasAuthorship W3014294114A5015654718 @default.
- W3014294114 hasAuthorship W3014294114A5028779371 @default.
- W3014294114 hasAuthorship W3014294114A5075068126 @default.
- W3014294114 hasBestOaLocation W30142941141 @default.
- W3014294114 hasConcept C11413529 @default.
- W3014294114 hasConcept C115178988 @default.
- W3014294114 hasConcept C132525143 @default.
- W3014294114 hasConcept C154945302 @default.
- W3014294114 hasConcept C31972630 @default.
- W3014294114 hasConcept C3770464 @default.
- W3014294114 hasConcept C41008148 @default.
- W3014294114 hasConcept C80444323 @default.
- W3014294114 hasConceptScore W3014294114C11413529 @default.
- W3014294114 hasConceptScore W3014294114C115178988 @default.
- W3014294114 hasConceptScore W3014294114C132525143 @default.
- W3014294114 hasConceptScore W3014294114C154945302 @default.
- W3014294114 hasConceptScore W3014294114C31972630 @default.
- W3014294114 hasConceptScore W3014294114C3770464 @default.
- W3014294114 hasConceptScore W3014294114C41008148 @default.
- W3014294114 hasConceptScore W3014294114C80444323 @default.
- W3014294114 hasIssue "7" @default.
- W3014294114 hasLocation W30142941141 @default.
- W3014294114 hasOpenAccess W3014294114 @default.
- W3014294114 hasPrimaryLocation W30142941141 @default.
- W3014294114 hasRelatedWork W1500647279 @default.
- W3014294114 hasRelatedWork W2982149258 @default.
- W3014294114 hasRelatedWork W2982368516 @default.
- W3014294114 hasRelatedWork W3014294114 @default.
- W3014294114 hasRelatedWork W3083272131 @default.
- W3014294114 hasRelatedWork W3168493052 @default.
- W3014294114 hasRelatedWork W3198231249 @default.
- W3014294114 hasRelatedWork W4288089511 @default.
- W3014294114 hasRelatedWork W4295910392 @default.
- W3014294114 hasRelatedWork W4309795810 @default.
- W3014294114 hasVolume "10" @default.
- W3014294114 isParatext "false" @default.
- W3014294114 isRetracted "false" @default.
- W3014294114 magId "3014294114" @default.
- W3014294114 workType "article" @default.