Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361192781> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4361192781 abstract "Graph machine learning (GML) has made great progress in node classification, link prediction, graph classification and so on. However, graphs in reality are often structurally imbalanced, that is, only a few hub nodes have a denser local structure and higher influence. The imbalance may compromise the robustness of existing GML models, especially in learning tail nodes. This paper proposes a selective graph augmentation method (SAug) to solve this problem. Firstly, a Pagerank-based sampling strategy is designed to identify hub nodes and tail nodes in the graph. Secondly, a selective augmentation strategy is proposed, which drops the noisy neighbors of hub nodes on one side, and discovers the latent neighbors and generates pseudo neighbors for tail nodes on the other side. It can also alleviate the structural imbalance between two types of nodes. Finally, a GNN model will be retrained on the augmented graph. Extensive experiments demonstrate that SAug can significantly improve the backbone GNNs and achieve superior performance to its competitors of graph augmentation methods and hub/tail aware methods." @default.
- W4361192781 created "2023-03-31" @default.
- W4361192781 creator A5011220083 @default.
- W4361192781 creator A5065771969 @default.
- W4361192781 creator A5076139885 @default.
- W4361192781 date "2023-03-23" @default.
- W4361192781 modified "2023-10-16" @default.
- W4361192781 title "Structural Imbalance Aware Graph Augmentation Learning" @default.
- W4361192781 doi "https://doi.org/10.48550/arxiv.2303.13757" @default.
- W4361192781 hasPublicationYear "2023" @default.
- W4361192781 type Work @default.
- W4361192781 citedByCount "0" @default.
- W4361192781 crossrefType "posted-content" @default.
- W4361192781 hasAuthorship W4361192781A5011220083 @default.
- W4361192781 hasAuthorship W4361192781A5065771969 @default.
- W4361192781 hasAuthorship W4361192781A5076139885 @default.
- W4361192781 hasBestOaLocation W43611927811 @default.
- W4361192781 hasConcept C104317684 @default.
- W4361192781 hasConcept C119857082 @default.
- W4361192781 hasConcept C132525143 @default.
- W4361192781 hasConcept C154945302 @default.
- W4361192781 hasConcept C185592680 @default.
- W4361192781 hasConcept C2779172887 @default.
- W4361192781 hasConcept C41008148 @default.
- W4361192781 hasConcept C55493867 @default.
- W4361192781 hasConcept C63479239 @default.
- W4361192781 hasConcept C80444323 @default.
- W4361192781 hasConceptScore W4361192781C104317684 @default.
- W4361192781 hasConceptScore W4361192781C119857082 @default.
- W4361192781 hasConceptScore W4361192781C132525143 @default.
- W4361192781 hasConceptScore W4361192781C154945302 @default.
- W4361192781 hasConceptScore W4361192781C185592680 @default.
- W4361192781 hasConceptScore W4361192781C2779172887 @default.
- W4361192781 hasConceptScore W4361192781C41008148 @default.
- W4361192781 hasConceptScore W4361192781C55493867 @default.
- W4361192781 hasConceptScore W4361192781C63479239 @default.
- W4361192781 hasConceptScore W4361192781C80444323 @default.
- W4361192781 hasLocation W43611927811 @default.
- W4361192781 hasOpenAccess W4361192781 @default.
- W4361192781 hasPrimaryLocation W43611927811 @default.
- W4361192781 hasRelatedWork W2002053721 @default.
- W4361192781 hasRelatedWork W2054781765 @default.
- W4361192781 hasRelatedWork W2234753775 @default.
- W4361192781 hasRelatedWork W2407929059 @default.
- W4361192781 hasRelatedWork W3039500550 @default.
- W4361192781 hasRelatedWork W3124234489 @default.
- W4361192781 hasRelatedWork W4210836535 @default.
- W4361192781 hasRelatedWork W4304730863 @default.
- W4361192781 hasRelatedWork W4320502856 @default.
- W4361192781 hasRelatedWork W2624039590 @default.
- W4361192781 isParatext "false" @default.
- W4361192781 isRetracted "false" @default.
- W4361192781 workType "article" @default.