FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385709265> ?p ?o ?g. }

• W4385709265 endingPage "2516" @default.
• W4385709265 startingPage "2494" @default.
• W4385709265 abstract "Knowledge graphs (KGs) are becoming essential resources for many downstream applications. However, their incompleteness may limit their potential. Thus, continuous curation is needed to mitigate this problem. One of the strategies to address this problem is KG alignment, i.e., forming a more complete KG by merging two or more KGs. This paper proposes i-Align, an interpretable KG alignment model. Unlike the existing KG alignment models, i-Align provides an explanation for each alignment prediction while maintaining high alignment performance. Experts can use the explanation to check the correctness of the alignment prediction. Thus, the high quality of a KG can be maintained during the curation process (e.g., the merging process of two KGs). To this end, a novel Transformer-based Graph Encoder (Trans-GE) is proposed as a key component of i-Align for aggregating information from entities' neighbors (structures). Trans-GE uses Edge-gated Attention that combines the adjacency matrix and the self-attention matrix to learn a gating mechanism to control the information aggregation from the neighboring entities. It also uses historical embeddings, allowing Trans-GE to be trained over mini-batches, or smaller sub-graphs, to address the scalability issue when encoding a large KG. Another component of i-Align is a Transformer encoder for aggregating entities' attributes. This way, i-Align can generate explanations in the form of a set of the most influential attributes/neighbors based on attention weights. Extensive experiments are conducted to show the power of i-Align. The experiments include several aspects, such as the model's effectiveness for aligning KGs, the quality of the generated explanations, and its practicality for aligning large KGs. The results show the effectiveness of i-Align in these aspects." @default.
• W4385709265 created "2023-08-10" @default.
• W4385709265 creator A5004361143 @default.
• W4385709265 creator A5071422010 @default.
• W4385709265 creator A5072614956 @default.
• W4385709265 creator A5083881309 @default.
• W4385709265 creator A5085925326 @default.
• W4385709265 creator A5090893421 @default.
• W4385709265 date "2023-08-09" @default.
• W4385709265 modified "2023-10-15" @default.
• W4385709265 title "i-Align: an interpretable knowledge graph alignment model" @default.
• W4385709265 cites W1491110638 @default.
• W4385709265 cites W1491268609 @default.
• W4385709265 cites W1707562537 @default.
• W4385709265 cites W1787224781 @default.
• W4385709265 cites W2070232376 @default.
• W4385709265 cites W2090243146 @default.
• W4385709265 cites W2197151308 @default.
• W4385709265 cites W2282821441 @default.
• W4385709265 cites W2300469216 @default.
• W4385709265 cites W2509893387 @default.
• W4385709265 cites W2551361256 @default.
• W4385709265 cites W2583976214 @default.
• W4385709265 cites W2613094910 @default.
• W4385709265 cites W2741750617 @default.
• W4385709265 cites W2743159750 @default.
• W4385709265 cites W2759136286 @default.
• W4385709265 cites W2808284704 @default.
• W4385709265 cites W2890187992 @default.
• W4385709265 cites W2903963001 @default.
• W4385709265 cites W2919115771 @default.
• W4385709265 cites W2945827377 @default.
• W4385709265 cites W2945976633 @default.
• W4385709265 cites W2949700412 @default.
• W4385709265 cites W2953054275 @default.
• W4385709265 cites W2962858109 @default.
• W4385709265 cites W2962916648 @default.
• W4385709265 cites W2964199361 @default.
• W4385709265 cites W2964263523 @default.
• W4385709265 cites W2964855489 @default.
• W4385709265 cites W2970188762 @default.
• W4385709265 cites W2970726176 @default.
• W4385709265 cites W2970921796 @default.
• W4385709265 cites W2980525481 @default.
• W4385709265 cites W2986711944 @default.
• W4385709265 cites W2997062749 @default.
• W4385709265 cites W3001896264 @default.
• W4385709265 cites W3034521981 @default.
• W4385709265 cites W3034906292 @default.
• W4385709265 cites W3044410371 @default.
• W4385709265 cites W3098038527 @default.
• W4385709265 cites W3100711616 @default.
• W4385709265 cites W4230405732 @default.
• W4385709265 cites W4287252285 @default.
• W4385709265 doi "https://doi.org/10.1007/s10618-023-00963-3" @default.
• W4385709265 hasPublicationYear "2023" @default.
• W4385709265 type Work @default.
• W4385709265 citedByCount "0" @default.
• W4385709265 crossrefType "journal-article" @default.
• W4385709265 hasAuthorship W4385709265A5004361143 @default.
• W4385709265 hasAuthorship W4385709265A5071422010 @default.
• W4385709265 hasAuthorship W4385709265A5072614956 @default.
• W4385709265 hasAuthorship W4385709265A5083881309 @default.
• W4385709265 hasAuthorship W4385709265A5085925326 @default.
• W4385709265 hasAuthorship W4385709265A5090893421 @default.
• W4385709265 hasBestOaLocation W43857092651 @default.
• W4385709265 hasConcept C110484373 @default.
• W4385709265 hasConcept C111919701 @default.
• W4385709265 hasConcept C11413529 @default.
• W4385709265 hasConcept C118505674 @default.
• W4385709265 hasConcept C119599485 @default.
• W4385709265 hasConcept C124101348 @default.
• W4385709265 hasConcept C127413603 @default.
• W4385709265 hasConcept C132525143 @default.
• W4385709265 hasConcept C154945302 @default.
• W4385709265 hasConcept C165801399 @default.
• W4385709265 hasConcept C180356752 @default.
• W4385709265 hasConcept C41008148 @default.
• W4385709265 hasConcept C48044578 @default.
• W4385709265 hasConcept C55439883 @default.
• W4385709265 hasConcept C66322947 @default.
• W4385709265 hasConcept C77088390 @default.
• W4385709265 hasConcept C80444323 @default.
• W4385709265 hasConceptScore W4385709265C110484373 @default.
• W4385709265 hasConceptScore W4385709265C111919701 @default.
• W4385709265 hasConceptScore W4385709265C11413529 @default.
• W4385709265 hasConceptScore W4385709265C118505674 @default.
• W4385709265 hasConceptScore W4385709265C119599485 @default.
• W4385709265 hasConceptScore W4385709265C124101348 @default.
• W4385709265 hasConceptScore W4385709265C127413603 @default.
• W4385709265 hasConceptScore W4385709265C132525143 @default.
• W4385709265 hasConceptScore W4385709265C154945302 @default.
• W4385709265 hasConceptScore W4385709265C165801399 @default.
• W4385709265 hasConceptScore W4385709265C180356752 @default.
• W4385709265 hasConceptScore W4385709265C41008148 @default.
• W4385709265 hasConceptScore W4385709265C48044578 @default.
• W4385709265 hasConceptScore W4385709265C55439883 @default.
• W4385709265 hasConceptScore W4385709265C66322947 @default.

• next