FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172300923> ?p ?o ?g. }

• W3172300923 abstract "Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its development, supervision has been considered necessary for accurate alignments. Inspired by the recent progress of self-supervised learning, we explore the extent to which we can get rid of supervision for entity alignment. Existing supervised methods for this task focus on pulling each pair of positive (labeled) entities close to each other. However, our analysis suggests that the learning of entity alignment can actually benefit more from pushing sampled (unlabeled) negatives far away than pulling positive aligned pairs close. We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs. Extensive experiments on benchmark datasets demonstrate that SelfKG without supervision can match or achieve comparable results with state-of-the-art supervised baselines. The performance of SelfKG demonstrates self-supervised learning offers great potential for entity alignment in KGs." @default.
• W3172300923 created "2021-06-22" @default.
• W3172300923 creator A5025295947 @default.
• W3172300923 creator A5030612674 @default.
• W3172300923 creator A5040266310 @default.
• W3172300923 creator A5049102441 @default.
• W3172300923 creator A5052284218 @default.
• W3172300923 creator A5067619750 @default.
• W3172300923 creator A5075936732 @default.
• W3172300923 date "2021-06-17" @default.
• W3172300923 modified "2023-10-14" @default.
• W3172300923 title "A Self-supervised Method for Entity Alignment" @default.
• W3172300923 cites W1990578345 @default.
• W3172300923 cites W2024523516 @default.
• W3172300923 cites W2058036501 @default.
• W3172300923 cites W2114538147 @default.
• W3172300923 cites W2127795553 @default.
• W3172300923 cites W2152790380 @default.
• W3172300923 cites W2300469216 @default.
• W3172300923 cites W2551361256 @default.
• W3172300923 cites W2551710909 @default.
• W3172300923 cites W2741750617 @default.
• W3172300923 cites W2746582923 @default.
• W3172300923 cites W2766453196 @default.
• W3172300923 cites W2808284704 @default.
• W3172300923 cites W2890187992 @default.
• W3172300923 cites W2896831016 @default.
• W3172300923 cites W2903963001 @default.
• W3172300923 cites W2913224127 @default.
• W3172300923 cites W2944671994 @default.
• W3172300923 cites W2952205826 @default.
• W3172300923 cites W2952557513 @default.
• W3172300923 cites W2952862139 @default.
• W3172300923 cites W2953054275 @default.
• W3172300923 cites W2964855489 @default.
• W3172300923 cites W2966055354 @default.
• W3172300923 cites W2970439619 @default.
• W3172300923 cites W2970503913 @default.
• W3172300923 cites W2970921796 @default.
• W3172300923 cites W2973488892 @default.
• W3172300923 cites W2980525481 @default.
• W3172300923 cites W2981198292 @default.
• W3172300923 cites W2990531836 @default.
• W3172300923 cites W2994639135 @default.
• W3172300923 cites W2996993961 @default.
• W3172300923 cites W3001510267 @default.
• W3172300923 cites W3027879771 @default.
• W3172300923 cites W3032567415 @default.
• W3172300923 cites W3034978746 @default.
• W3172300923 cites W3035524453 @default.
• W3172300923 cites W3039695075 @default.
• W3172300923 cites W3091993229 @default.
• W3172300923 cites W3095602948 @default.
• W3172300923 cites W3098583774 @default.
• W3172300923 cites W3099152386 @default.
• W3172300923 cites W3100825476 @default.
• W3172300923 cites W3111851097 @default.
• W3172300923 cites W3118062200 @default.
• W3172300923 cites W3141023492 @default.
• W3172300923 cites W3173151551 @default.
• W3172300923 doi "https://doi.org/10.48550/arxiv.2106.09395" @default.
• W3172300923 hasPublicationYear "2021" @default.
• W3172300923 type Work @default.
• W3172300923 sameAs 3172300923 @default.
• W3172300923 citedByCount "0" @default.
• W3172300923 crossrefType "posted-content" @default.
• W3172300923 hasAuthorship W3172300923A5025295947 @default.
• W3172300923 hasAuthorship W3172300923A5030612674 @default.
• W3172300923 hasAuthorship W3172300923A5040266310 @default.
• W3172300923 hasAuthorship W3172300923A5049102441 @default.
• W3172300923 hasAuthorship W3172300923A5052284218 @default.
• W3172300923 hasAuthorship W3172300923A5067619750 @default.
• W3172300923 hasAuthorship W3172300923A5075936732 @default.
• W3172300923 hasBestOaLocation W31723009231 @default.
• W3172300923 hasConcept C119857082 @default.
• W3172300923 hasConcept C120665830 @default.
• W3172300923 hasConcept C121332964 @default.
• W3172300923 hasConcept C127413603 @default.
• W3172300923 hasConcept C13280743 @default.
• W3172300923 hasConcept C136389625 @default.
• W3172300923 hasConcept C154945302 @default.
• W3172300923 hasConcept C185798385 @default.
• W3172300923 hasConcept C192209626 @default.
• W3172300923 hasConcept C201995342 @default.
• W3172300923 hasConcept C204321447 @default.
• W3172300923 hasConcept C205649164 @default.
• W3172300923 hasConcept C2778755073 @default.
• W3172300923 hasConcept C2780451532 @default.
• W3172300923 hasConcept C41008148 @default.
• W3172300923 hasConcept C50644808 @default.
• W3172300923 hasConcept C62520636 @default.
• W3172300923 hasConceptScore W3172300923C119857082 @default.
• W3172300923 hasConceptScore W3172300923C120665830 @default.
• W3172300923 hasConceptScore W3172300923C121332964 @default.
• W3172300923 hasConceptScore W3172300923C127413603 @default.
• W3172300923 hasConceptScore W3172300923C13280743 @default.
• W3172300923 hasConceptScore W3172300923C136389625 @default.
• W3172300923 hasConceptScore W3172300923C154945302 @default.
• W3172300923 hasConceptScore W3172300923C185798385 @default.
• W3172300923 hasConceptScore W3172300923C192209626 @default.

• next