Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386102370> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386102370 endingPage "121280" @default.
- W4386102370 startingPage "121280" @default.
- W4386102370 abstract "Graph embedding learning is a fundamental task when dealing with diverse datasets. While encoder–decoder architectures, such as U-Nets, have shown great success in image pixel-wise prediction tasks, applying similar methods to graph data poses challenges due to the lack of natural pooling and up-sampling operations for graphs. Recent methods leverage learnable parameters to extract structural information from neural networks and extend pooling and unpooling to graphs using node features and graph structural information. This paper proposes a novel model called GIUNet (Graph Isomorphism U-Net) for the graph classification task. The proposed Graph U-Net structure is based on graph isomorphism convolution while using a comprehensive pqPooling layer. The pqPooling layer in our approach effectively combines node features and graph structure information during the graph down-sampling stage. To incorporate graph structure information, we utilize both the spectral representation and node centrality measurements. Node centrality measurements capture various structural aspects of nodes in the graph, while the spectral representation helps us focus on the informative low-frequency components of the graph structure. Through ablation studies, we have demonstrated that leveraging the GIUNet model leads to significant improvements compared to state-of-the-art methods across multiple benchmark datasets." @default.
- W4386102370 created "2023-08-24" @default.
- W4386102370 creator A5006999765 @default.
- W4386102370 creator A5023644552 @default.
- W4386102370 creator A5042862727 @default.
- W4386102370 creator A5052644126 @default.
- W4386102370 creator A5055218430 @default.
- W4386102370 date "2024-02-01" @default.
- W4386102370 modified "2023-09-26" @default.
- W4386102370 title "Graph isomorphism U-Net" @default.
- W4386102370 cites W2092750499 @default.
- W4386102370 cites W2099438806 @default.
- W4386102370 cites W2101491865 @default.
- W4386102370 cites W2116341502 @default.
- W4386102370 cites W2121406124 @default.
- W4386102370 cites W2134784378 @default.
- W4386102370 cites W2195972617 @default.
- W4386102370 cites W2927980542 @default.
- W4386102370 cites W2969996838 @default.
- W4386102370 cites W3080216795 @default.
- W4386102370 cites W3085084733 @default.
- W4386102370 cites W3096947210 @default.
- W4386102370 cites W3097300053 @default.
- W4386102370 cites W3110736101 @default.
- W4386102370 cites W3116202926 @default.
- W4386102370 cites W3123909522 @default.
- W4386102370 cites W3132455321 @default.
- W4386102370 cites W3133780103 @default.
- W4386102370 cites W3144386677 @default.
- W4386102370 cites W3152893301 @default.
- W4386102370 cites W3190734472 @default.
- W4386102370 cites W4210257598 @default.
- W4386102370 cites W4292267310 @default.
- W4386102370 cites W4309625848 @default.
- W4386102370 cites W4317931697 @default.
- W4386102370 cites W4376848346 @default.
- W4386102370 doi "https://doi.org/10.1016/j.eswa.2023.121280" @default.
- W4386102370 hasPublicationYear "2024" @default.
- W4386102370 type Work @default.
- W4386102370 citedByCount "0" @default.
- W4386102370 crossrefType "journal-article" @default.
- W4386102370 hasAuthorship W4386102370A5006999765 @default.
- W4386102370 hasAuthorship W4386102370A5023644552 @default.
- W4386102370 hasAuthorship W4386102370A5042862727 @default.
- W4386102370 hasAuthorship W4386102370A5052644126 @default.
- W4386102370 hasAuthorship W4386102370A5055218430 @default.
- W4386102370 hasConcept C110384440 @default.
- W4386102370 hasConcept C114614502 @default.
- W4386102370 hasConcept C115961682 @default.
- W4386102370 hasConcept C132525143 @default.
- W4386102370 hasConcept C154945302 @default.
- W4386102370 hasConcept C180356752 @default.
- W4386102370 hasConcept C203776342 @default.
- W4386102370 hasConcept C33923547 @default.
- W4386102370 hasConcept C41008148 @default.
- W4386102370 hasConcept C53811970 @default.
- W4386102370 hasConcept C61665672 @default.
- W4386102370 hasConcept C70437156 @default.
- W4386102370 hasConcept C80444323 @default.
- W4386102370 hasConceptScore W4386102370C110384440 @default.
- W4386102370 hasConceptScore W4386102370C114614502 @default.
- W4386102370 hasConceptScore W4386102370C115961682 @default.
- W4386102370 hasConceptScore W4386102370C132525143 @default.
- W4386102370 hasConceptScore W4386102370C154945302 @default.
- W4386102370 hasConceptScore W4386102370C180356752 @default.
- W4386102370 hasConceptScore W4386102370C203776342 @default.
- W4386102370 hasConceptScore W4386102370C33923547 @default.
- W4386102370 hasConceptScore W4386102370C41008148 @default.
- W4386102370 hasConceptScore W4386102370C53811970 @default.
- W4386102370 hasConceptScore W4386102370C61665672 @default.
- W4386102370 hasConceptScore W4386102370C70437156 @default.
- W4386102370 hasConceptScore W4386102370C80444323 @default.
- W4386102370 hasLocation W43861023701 @default.
- W4386102370 hasOpenAccess W4386102370 @default.
- W4386102370 hasPrimaryLocation W43861023701 @default.
- W4386102370 hasRelatedWork W2087148058 @default.
- W4386102370 hasRelatedWork W2195864695 @default.
- W4386102370 hasRelatedWork W3145941582 @default.
- W4386102370 hasRelatedWork W3170097993 @default.
- W4386102370 hasRelatedWork W4287121761 @default.
- W4386102370 hasRelatedWork W4296821948 @default.
- W4386102370 hasRelatedWork W4300868102 @default.
- W4386102370 hasRelatedWork W4312843054 @default.
- W4386102370 hasRelatedWork W4313200725 @default.
- W4386102370 hasRelatedWork W4382239150 @default.
- W4386102370 hasVolume "236" @default.
- W4386102370 isParatext "false" @default.
- W4386102370 isRetracted "false" @default.
- W4386102370 workType "article" @default.