Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324069622> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4324069622 endingPage "109518" @default.
- W4324069622 startingPage "109518" @default.
- W4324069622 abstract "Graph Neural Networks (GNNs) have shown great potential for graph data analysis. In this paper, we focus on multi-hop graph neural networks and aim to extend existing models to a high-order multi-hop form for graph-level representation learning. However, such a directly extending method suffers from two limitations, i.e., computational inefficiency and limited representation ability of the multi-hop neighbor. For the former limitation, we utilize an iteration approach to approximate the power of a complex adjacency matrix to achieve linear computational complexity. For the latter limitation, we introduce the Regularized Markov Clustering (R-MCL) to regularize the flow matrix, i.e., the adjacency matrix, in each iteration step. With these two strategies, we construct Markov Clustering Regularized Multi-hop Graph Neural Network (MCMGN) for graph-level representation learning tasks. Specifically, MCMGN consists of a multi-hop message passing phase and a readout phase, where the multi-hop message passing phase aims to learn multi-hop node embedding, and then the readout phase aggregates multi-hop node representations to generate graph embedding for graph-level representation learning tasks. Extensive experiments on eight graph benchmark datasets strongly demonstrate the effectiveness of Markov Clustering Regularized Multi-hop Graph Neural Network, leading to superior performance on graph classification." @default.
- W4324069622 created "2023-03-14" @default.
- W4324069622 creator A5017834338 @default.
- W4324069622 creator A5088010841 @default.
- W4324069622 creator A5091227928 @default.
- W4324069622 date "2023-07-01" @default.
- W4324069622 modified "2023-10-09" @default.
- W4324069622 title "Markov clustering regularized multi-hop graph neural network" @default.
- W4324069622 cites W1179283095 @default.
- W4324069622 cites W2985111225 @default.
- W4324069622 cites W3006893391 @default.
- W4324069622 cites W3014513496 @default.
- W4324069622 cites W3036727658 @default.
- W4324069622 cites W3192436896 @default.
- W4324069622 doi "https://doi.org/10.1016/j.patcog.2023.109518" @default.
- W4324069622 hasPublicationYear "2023" @default.
- W4324069622 type Work @default.
- W4324069622 citedByCount "0" @default.
- W4324069622 crossrefType "journal-article" @default.
- W4324069622 hasAuthorship W4324069622A5017834338 @default.
- W4324069622 hasAuthorship W4324069622A5088010841 @default.
- W4324069622 hasAuthorship W4324069622A5091227928 @default.
- W4324069622 hasConcept C11413529 @default.
- W4324069622 hasConcept C119857082 @default.
- W4324069622 hasConcept C132525143 @default.
- W4324069622 hasConcept C154945302 @default.
- W4324069622 hasConcept C180356752 @default.
- W4324069622 hasConcept C22047676 @default.
- W4324069622 hasConcept C41008148 @default.
- W4324069622 hasConcept C48903430 @default.
- W4324069622 hasConcept C73555534 @default.
- W4324069622 hasConcept C80444323 @default.
- W4324069622 hasConcept C98763669 @default.
- W4324069622 hasConceptScore W4324069622C11413529 @default.
- W4324069622 hasConceptScore W4324069622C119857082 @default.
- W4324069622 hasConceptScore W4324069622C132525143 @default.
- W4324069622 hasConceptScore W4324069622C154945302 @default.
- W4324069622 hasConceptScore W4324069622C180356752 @default.
- W4324069622 hasConceptScore W4324069622C22047676 @default.
- W4324069622 hasConceptScore W4324069622C41008148 @default.
- W4324069622 hasConceptScore W4324069622C48903430 @default.
- W4324069622 hasConceptScore W4324069622C73555534 @default.
- W4324069622 hasConceptScore W4324069622C80444323 @default.
- W4324069622 hasConceptScore W4324069622C98763669 @default.
- W4324069622 hasFunder F4320321001 @default.
- W4324069622 hasFunder F4320335787 @default.
- W4324069622 hasLocation W43240696221 @default.
- W4324069622 hasOpenAccess W4324069622 @default.
- W4324069622 hasPrimaryLocation W43240696221 @default.
- W4324069622 hasRelatedWork W2053209358 @default.
- W4324069622 hasRelatedWork W2155218858 @default.
- W4324069622 hasRelatedWork W2604585036 @default.
- W4324069622 hasRelatedWork W2791849501 @default.
- W4324069622 hasRelatedWork W3034334914 @default.
- W4324069622 hasRelatedWork W3185513611 @default.
- W4324069622 hasRelatedWork W4214710283 @default.
- W4324069622 hasRelatedWork W4297853639 @default.
- W4324069622 hasRelatedWork W4299519240 @default.
- W4324069622 hasRelatedWork W4323896988 @default.
- W4324069622 hasVolume "139" @default.
- W4324069622 isParatext "false" @default.
- W4324069622 isRetracted "false" @default.
- W4324069622 workType "article" @default.