Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313000383> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4313000383 endingPage "14" @default.
- W4313000383 startingPage "1" @default.
- W4313000383 abstract "Many recent studies of Entity Alignment (EA) use Graph Neural Networks (GNNs) to aggregate the neighborhood features of entities and achieve better performance. However, aligned entities in real Knowledge Graphs (KGs) usually have non-isomorphic neighborhood structures due to the different data sources of KGs. Therefore, it is insufficient to simply compare the global direct neighborhood of aligned entities, which may also become a variable for the EA judgment. In this paper, we propose a Relation-based Adaptive Neighborhood Matching method ( <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RANM</i> ), which matches larger range and higher confidence neighborhoods for aligned entities based on relation matching instead of alignment seeds. <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RANM</i> first uses alignment seeds to construct the best relation matching set, and then performs local direct neighborhood matching and feature aggregation on the candidate alignments. To obtain high-quality entity embeddings, we design a variant attention mechanism based on heterogeneous graphs, which considers the heterogeneity of relations in KGs. We also adopt a bi-directional iterative co-training to further improve the performance. Extensive experiments on three well-known datasets show our method significantly outperforms 14 state-of-the-art methods, and is 3.01-11.5% higher than the best-performing baselines in Hits@1. <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>RANM</i> also shows high performance on the long-tailed entities and the dataset with less alignment seeds." @default.
- W4313000383 created "2023-01-05" @default.
- W4313000383 creator A5015727828 @default.
- W4313000383 creator A5024159334 @default.
- W4313000383 creator A5029010934 @default.
- W4313000383 creator A5047803849 @default.
- W4313000383 date "2022-01-01" @default.
- W4313000383 modified "2023-10-16" @default.
- W4313000383 title "Semi-supervised Entity Alignment via Relation-based Adaptive Neighborhood Matching" @default.
- W4313000383 doi "https://doi.org/10.1109/tkde.2022.3222811" @default.
- W4313000383 hasPublicationYear "2022" @default.
- W4313000383 type Work @default.
- W4313000383 citedByCount "1" @default.
- W4313000383 countsByYear W43130003832023 @default.
- W4313000383 crossrefType "journal-article" @default.
- W4313000383 hasAuthorship W4313000383A5015727828 @default.
- W4313000383 hasAuthorship W4313000383A5024159334 @default.
- W4313000383 hasAuthorship W4313000383A5029010934 @default.
- W4313000383 hasAuthorship W4313000383A5047803849 @default.
- W4313000383 hasConcept C105795698 @default.
- W4313000383 hasConcept C119857082 @default.
- W4313000383 hasConcept C124101348 @default.
- W4313000383 hasConcept C132525143 @default.
- W4313000383 hasConcept C154945302 @default.
- W4313000383 hasConcept C159985019 @default.
- W4313000383 hasConcept C165064840 @default.
- W4313000383 hasConcept C177264268 @default.
- W4313000383 hasConcept C192562407 @default.
- W4313000383 hasConcept C199360897 @default.
- W4313000383 hasConcept C23123220 @default.
- W4313000383 hasConcept C25343380 @default.
- W4313000383 hasConcept C33923547 @default.
- W4313000383 hasConcept C41008148 @default.
- W4313000383 hasConcept C4679612 @default.
- W4313000383 hasConcept C80444323 @default.
- W4313000383 hasConceptScore W4313000383C105795698 @default.
- W4313000383 hasConceptScore W4313000383C119857082 @default.
- W4313000383 hasConceptScore W4313000383C124101348 @default.
- W4313000383 hasConceptScore W4313000383C132525143 @default.
- W4313000383 hasConceptScore W4313000383C154945302 @default.
- W4313000383 hasConceptScore W4313000383C159985019 @default.
- W4313000383 hasConceptScore W4313000383C165064840 @default.
- W4313000383 hasConceptScore W4313000383C177264268 @default.
- W4313000383 hasConceptScore W4313000383C192562407 @default.
- W4313000383 hasConceptScore W4313000383C199360897 @default.
- W4313000383 hasConceptScore W4313000383C23123220 @default.
- W4313000383 hasConceptScore W4313000383C25343380 @default.
- W4313000383 hasConceptScore W4313000383C33923547 @default.
- W4313000383 hasConceptScore W4313000383C41008148 @default.
- W4313000383 hasConceptScore W4313000383C4679612 @default.
- W4313000383 hasConceptScore W4313000383C80444323 @default.
- W4313000383 hasLocation W43130003831 @default.
- W4313000383 hasOpenAccess W4313000383 @default.
- W4313000383 hasPrimaryLocation W43130003831 @default.
- W4313000383 hasRelatedWork W2131787594 @default.
- W4313000383 hasRelatedWork W2384888906 @default.
- W4313000383 hasRelatedWork W2894024364 @default.
- W4313000383 hasRelatedWork W2961085424 @default.
- W4313000383 hasRelatedWork W3124973903 @default.
- W4313000383 hasRelatedWork W3201783519 @default.
- W4313000383 hasRelatedWork W3203785702 @default.
- W4313000383 hasRelatedWork W4226436121 @default.
- W4313000383 hasRelatedWork W4286909549 @default.
- W4313000383 hasRelatedWork W4306674287 @default.
- W4313000383 isParatext "false" @default.
- W4313000383 isRetracted "false" @default.
- W4313000383 workType "article" @default.