FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226358743> ?p ?o ?g. }

• W4226358743 endingPage "41225" @default.
• W4226358743 startingPage "41215" @default.
• W4226358743 abstract "Graph Convolutional Network (GCN) has achieved significant success in many graph representation learning tasks. GCN usually learns graph representations by performing Neighbor Aggregation (NA) and Feature Transformation (FT) operations. Deep Adaptive Graph Neural Network (DAGNN) improves NA operation in the aggregation-transformation decoupled GCN, which enables the model to obtain a large receiver field. However, the problem with GCN is that when the model is trained to a deeper level, the performance decreases. In particular, the influence of NA and FT on model degradation has not been fully considered. In this work, we propose a new decoupled GCN architecture to enhance the performance of deep GCN. First, we conduct an experimental analysis of the impact of NA and FT operations on the degradation of the deep GCN model. Subsequently, we propose an Adaptive Aggregation-Transform Decoupled Graph Convolutional Network (AATD-GCN) which divides the model into two depths <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$D_{NA}$ </tex-math></inline-formula> and <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$D_{FT}$ </tex-math></inline-formula> , and proposes improved approaches in NA and FT, respectively. The AATD-GCN reduces the influence of NA and FT operations on performance degradation of deep GCN, and obtains a large receiver field while extracting complex feature information. We investigate the requirements of model depth <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$D_{NA}$ </tex-math></inline-formula> and <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$D_{FT}$ </tex-math></inline-formula> for graphs of different structures and sizes. Finally, the effectiveness of the proposed architecture is verified through extensive experiments on real-world datasets, the experimental results show that AATD-GCN is superior in terms of accuracy and robustness." @default.
• W4226358743 created "2022-05-05" @default.
• W4226358743 creator A5008795836 @default.
• W4226358743 creator A5047379899 @default.
• W4226358743 creator A5072543735 @default.
• W4226358743 date "2022-01-01" @default.
• W4226358743 modified "2023-09-26" @default.
• W4226358743 title "Adaptive Aggregation-Transformation Decoupled Graph Convolutional Network for Semi-Supervised Learning" @default.
• W4226358743 cites W2027731328 @default.
• W4226358743 cites W2064675550 @default.
• W4226358743 cites W2079017595 @default.
• W4226358743 cites W2153959628 @default.
• W4226358743 cites W2194775991 @default.
• W4226358743 cites W2788284887 @default.
• W4226358743 cites W2990045899 @default.
• W4226358743 cites W2998496395 @default.
• W4226358743 cites W3007364240 @default.
• W4226358743 cites W3035625743 @default.
• W4226358743 cites W3042770487 @default.
• W4226358743 cites W3209520664 @default.
• W4226358743 doi "https://doi.org/10.1109/access.2022.3166938" @default.
• W4226358743 hasPublicationYear "2022" @default.
• W4226358743 type Work @default.
• W4226358743 citedByCount "2" @default.
• W4226358743 countsByYear W42263587432022 @default.
• W4226358743 countsByYear W42263587432023 @default.
• W4226358743 crossrefType "journal-article" @default.
• W4226358743 hasAuthorship W4226358743A5008795836 @default.
• W4226358743 hasAuthorship W4226358743A5047379899 @default.
• W4226358743 hasAuthorship W4226358743A5072543735 @default.
• W4226358743 hasBestOaLocation W42263587431 @default.
• W4226358743 hasConcept C104317684 @default.
• W4226358743 hasConcept C108583219 @default.
• W4226358743 hasConcept C132525143 @default.
• W4226358743 hasConcept C154945302 @default.
• W4226358743 hasConcept C185592680 @default.
• W4226358743 hasConcept C204241405 @default.
• W4226358743 hasConcept C41008148 @default.
• W4226358743 hasConcept C55493867 @default.
• W4226358743 hasConcept C558772884 @default.
• W4226358743 hasConcept C80444323 @default.
• W4226358743 hasConcept C81363708 @default.
• W4226358743 hasConceptScore W4226358743C104317684 @default.
• W4226358743 hasConceptScore W4226358743C108583219 @default.
• W4226358743 hasConceptScore W4226358743C132525143 @default.
• W4226358743 hasConceptScore W4226358743C154945302 @default.
• W4226358743 hasConceptScore W4226358743C185592680 @default.
• W4226358743 hasConceptScore W4226358743C204241405 @default.
• W4226358743 hasConceptScore W4226358743C41008148 @default.
• W4226358743 hasConceptScore W4226358743C55493867 @default.
• W4226358743 hasConceptScore W4226358743C558772884 @default.
• W4226358743 hasConceptScore W4226358743C80444323 @default.
• W4226358743 hasConceptScore W4226358743C81363708 @default.
• W4226358743 hasFunder F4320327376 @default.
• W4226358743 hasLocation W42263587431 @default.
• W4226358743 hasLocation W42263587432 @default.
• W4226358743 hasOpenAccess W4226358743 @default.
• W4226358743 hasPrimaryLocation W42263587431 @default.
• W4226358743 hasRelatedWork W2731899572 @default.
• W4226358743 hasRelatedWork W2999805992 @default.
• W4226358743 hasRelatedWork W3011074480 @default.
• W4226358743 hasRelatedWork W3116150086 @default.
• W4226358743 hasRelatedWork W3133861977 @default.
• W4226358743 hasRelatedWork W3192840557 @default.
• W4226358743 hasRelatedWork W4200173597 @default.
• W4226358743 hasRelatedWork W4291897433 @default.
• W4226358743 hasRelatedWork W4312417841 @default.
• W4226358743 hasRelatedWork W4321369474 @default.
• W4226358743 hasVolume "10" @default.
• W4226358743 isParatext "false" @default.
• W4226358743 isRetracted "false" @default.
• W4226358743 workType "article" @default.