Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386044487> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4386044487 abstract "Graph Active Learning (GAL), which aims to find the most informative nodes in graphs for annotation to maximize the Graph Neural Networks (GNNs) performance, has attracted many research efforts but remains non-trivial challenges. One major challenge is that existing GAL strategies may introduce semantic confusion to the selected training set, particularly when graphs are noisy. Specifically, most existing methods assume all aggregating features to be helpful, ignoring the semantically negative effect between inter-class edges under the message-passing mechanism. In this work, we present Semantic-aware Active learning framework for Graphs (SAG) to mitigate the semantic confusion problem. Pairwise similarities and dissimilarities of nodes with semantic features are introduced to jointly evaluate the node influence. A new prototype-based criterion and query policy are also designed to maintain diversity and class balance of the selected nodes, respectively. Extensive experiments on the public benchmark graphs and a real-world financial dataset demonstrate that SAG significantly improves node classification performances and consistently outperforms previous methods. Moreover, comprehensive analysis and ablation study also verify the effectiveness of the proposed framework." @default.
- W4386044487 created "2023-08-22" @default.
- W4386044487 creator A5009221204 @default.
- W4386044487 creator A5024097240 @default.
- W4386044487 creator A5042932080 @default.
- W4386044487 creator A5051901934 @default.
- W4386044487 creator A5062357883 @default.
- W4386044487 creator A5070162914 @default.
- W4386044487 creator A5086979603 @default.
- W4386044487 date "2023-08-17" @default.
- W4386044487 modified "2023-09-25" @default.
- W4386044487 title "Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning" @default.
- W4386044487 doi "https://doi.org/10.48550/arxiv.2308.08823" @default.
- W4386044487 hasPublicationYear "2023" @default.
- W4386044487 type Work @default.
- W4386044487 citedByCount "0" @default.
- W4386044487 crossrefType "posted-content" @default.
- W4386044487 hasAuthorship W4386044487A5009221204 @default.
- W4386044487 hasAuthorship W4386044487A5024097240 @default.
- W4386044487 hasAuthorship W4386044487A5042932080 @default.
- W4386044487 hasAuthorship W4386044487A5051901934 @default.
- W4386044487 hasAuthorship W4386044487A5062357883 @default.
- W4386044487 hasAuthorship W4386044487A5070162914 @default.
- W4386044487 hasAuthorship W4386044487A5086979603 @default.
- W4386044487 hasBestOaLocation W43860444871 @default.
- W4386044487 hasConcept C11171543 @default.
- W4386044487 hasConcept C119857082 @default.
- W4386044487 hasConcept C127413603 @default.
- W4386044487 hasConcept C132525143 @default.
- W4386044487 hasConcept C154945302 @default.
- W4386044487 hasConcept C15744967 @default.
- W4386044487 hasConcept C177264268 @default.
- W4386044487 hasConcept C184898388 @default.
- W4386044487 hasConcept C199360897 @default.
- W4386044487 hasConcept C2777212361 @default.
- W4386044487 hasConcept C2781140086 @default.
- W4386044487 hasConcept C41008148 @default.
- W4386044487 hasConcept C62611344 @default.
- W4386044487 hasConcept C66938386 @default.
- W4386044487 hasConcept C80444323 @default.
- W4386044487 hasConcept C94124525 @default.
- W4386044487 hasConceptScore W4386044487C11171543 @default.
- W4386044487 hasConceptScore W4386044487C119857082 @default.
- W4386044487 hasConceptScore W4386044487C127413603 @default.
- W4386044487 hasConceptScore W4386044487C132525143 @default.
- W4386044487 hasConceptScore W4386044487C154945302 @default.
- W4386044487 hasConceptScore W4386044487C15744967 @default.
- W4386044487 hasConceptScore W4386044487C177264268 @default.
- W4386044487 hasConceptScore W4386044487C184898388 @default.
- W4386044487 hasConceptScore W4386044487C199360897 @default.
- W4386044487 hasConceptScore W4386044487C2777212361 @default.
- W4386044487 hasConceptScore W4386044487C2781140086 @default.
- W4386044487 hasConceptScore W4386044487C41008148 @default.
- W4386044487 hasConceptScore W4386044487C62611344 @default.
- W4386044487 hasConceptScore W4386044487C66938386 @default.
- W4386044487 hasConceptScore W4386044487C80444323 @default.
- W4386044487 hasConceptScore W4386044487C94124525 @default.
- W4386044487 hasLocation W43860444871 @default.
- W4386044487 hasOpenAccess W4386044487 @default.
- W4386044487 hasPrimaryLocation W43860444871 @default.
- W4386044487 hasRelatedWork W2014358890 @default.
- W4386044487 hasRelatedWork W2125665461 @default.
- W4386044487 hasRelatedWork W2365213443 @default.
- W4386044487 hasRelatedWork W2945365184 @default.
- W4386044487 hasRelatedWork W2961085424 @default.
- W4386044487 hasRelatedWork W2971267355 @default.
- W4386044487 hasRelatedWork W4312266567 @default.
- W4386044487 hasRelatedWork W4312816440 @default.
- W4386044487 hasRelatedWork W4383860413 @default.
- W4386044487 hasRelatedWork W637059485 @default.
- W4386044487 isParatext "false" @default.
- W4386044487 isRetracted "false" @default.
- W4386044487 workType "article" @default.