FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201653419> ?p ?o ?g. }

• W3201653419 endingPage "107498" @default.
• W3201653419 startingPage "107498" @default.
• W3201653419 abstract "Reasoning aiming at inferring implicit facts over knowledge graphs (KGs) is a critical and fundamental task for various intelligent knowledge-based services. With multiple distributed and complementary KGs, the effective and efficient capture and fusion of knowledge from different KGs is becoming an increasingly important topic, which has not been well studied. To fill this gap, we propose to explore cross-KG relation paths with the anchor links identified by entity alignment for the knowledge fusion and collaborative reasoning of multiple KGs. To address the heterogeneity of different KGs, this paper proposes a novel reasoning model named HackRL based on the reinforcement learning framework, which incorporates the long short-term memory and hierarchical graph attention in the policy network to infer indicative cross-KG relation paths from the history trajectory and the heterogeneous environment for predicting corresponding relations. Meanwhile, an entity alignment-oriented representation learning method is utilized to embed different KGs into a unified vector space based on the anchor links to reduce the impact of distinct vector spaces, and two training mechanisms, action mask and retrain with sampled paths, are proposed to optimize the training process to learn more successful indicative paths. The proposed HackRL is validated on three cross-lingual datasets built from DBpedia on the link prediction and fact prediction tasks. Experimental results demonstrate that HackRL achieves better performance on most tasks than existing methods. This work provides an industrially-applicable framework for fusing distributed KGs to make better decisions." @default.
• W3201653419 created "2021-09-27" @default.
• W3201653419 creator A5027985722 @default.
• W3201653419 creator A5044689658 @default.
• W3201653419 creator A5058010200 @default.
• W3201653419 creator A5068297028 @default.
• W3201653419 creator A5069969191 @default.
• W3201653419 creator A5071672663 @default.
• W3201653419 creator A5083438052 @default.
• W3201653419 creator A5088598615 @default.
• W3201653419 date "2021-12-01" @default.
• W3201653419 modified "2023-10-16" @default.
• W3201653419 title "HackRL: Reinforcement learning with hierarchical attention for cross-graph knowledge fusion and collaborative reasoning" @default.
• W3201653419 cites W1552847225 @default.
• W3201653419 cites W2020682070 @default.
• W3201653419 cites W2022166150 @default.
• W3201653419 cites W2029249040 @default.
• W3201653419 cites W2058036501 @default.
• W3201653419 cites W2064675550 @default.
• W3201653419 cites W2068245942 @default.
• W3201653419 cites W2094728533 @default.
• W3201653419 cites W2250193220 @default.
• W3201653419 cites W2283196293 @default.
• W3201653419 cites W2547239171 @default.
• W3201653419 cites W2551361256 @default.
• W3201653419 cites W2728059831 @default.
• W3201653419 cites W2738020474 @default.
• W3201653419 cites W2806832624 @default.
• W3201653419 cites W2808284704 @default.
• W3201653419 cites W2889583850 @default.
• W3201653419 cites W2890187992 @default.
• W3201653419 cites W2903963001 @default.
• W3201653419 cites W2914846572 @default.
• W3201653419 cites W2921873695 @default.
• W3201653419 cites W2947986443 @default.
• W3201653419 cites W2962886429 @default.
• W3201653419 cites W2970618565 @default.
• W3201653419 cites W2971311320 @default.
• W3201653419 cites W2972535098 @default.
• W3201653419 cites W2979814938 @default.
• W3201653419 cites W2997062749 @default.
• W3201653419 cites W3006982823 @default.
• W3201653419 cites W3012000912 @default.
• W3201653419 cites W3015158377 @default.
• W3201653419 cites W3017152929 @default.
• W3201653419 cites W3029587262 @default.
• W3201653419 cites W3030216914 @default.
• W3201653419 cites W3034616364 @default.
• W3201653419 cites W3035191547 @default.
• W3201653419 cites W3049335548 @default.
• W3201653419 cites W3082320588 @default.
• W3201653419 cites W3089164705 @default.
• W3201653419 cites W3095940986 @default.
• W3201653419 cites W3099384160 @default.
• W3201653419 cites W3113470404 @default.
• W3201653419 cites W3124962741 @default.
• W3201653419 cites W3167099550 @default.
• W3201653419 doi "https://doi.org/10.1016/j.knosys.2021.107498" @default.
• W3201653419 hasPublicationYear "2021" @default.
• W3201653419 type Work @default.
• W3201653419 sameAs 3201653419 @default.
• W3201653419 citedByCount "5" @default.
• W3201653419 countsByYear W32016534192021 @default.
• W3201653419 countsByYear W32016534192022 @default.
• W3201653419 countsByYear W32016534192023 @default.
• W3201653419 crossrefType "journal-article" @default.
• W3201653419 hasAuthorship W3201653419A5027985722 @default.
• W3201653419 hasAuthorship W3201653419A5044689658 @default.
• W3201653419 hasAuthorship W3201653419A5058010200 @default.
• W3201653419 hasAuthorship W3201653419A5068297028 @default.
• W3201653419 hasAuthorship W3201653419A5069969191 @default.
• W3201653419 hasAuthorship W3201653419A5071672663 @default.
• W3201653419 hasAuthorship W3201653419A5083438052 @default.
• W3201653419 hasAuthorship W3201653419A5088598615 @default.
• W3201653419 hasConcept C111919701 @default.
• W3201653419 hasConcept C119857082 @default.
• W3201653419 hasConcept C124101348 @default.
• W3201653419 hasConcept C132525143 @default.
• W3201653419 hasConcept C154945302 @default.
• W3201653419 hasConcept C162324750 @default.
• W3201653419 hasConcept C17744445 @default.
• W3201653419 hasConcept C187736073 @default.
• W3201653419 hasConcept C199539241 @default.
• W3201653419 hasConcept C25343380 @default.
• W3201653419 hasConcept C2776359362 @default.
• W3201653419 hasConcept C2780451532 @default.
• W3201653419 hasConcept C2987255567 @default.
• W3201653419 hasConcept C41008148 @default.
• W3201653419 hasConcept C80444323 @default.
• W3201653419 hasConcept C94625758 @default.
• W3201653419 hasConcept C97541855 @default.
• W3201653419 hasConcept C98045186 @default.
• W3201653419 hasConceptScore W3201653419C111919701 @default.
• W3201653419 hasConceptScore W3201653419C119857082 @default.
• W3201653419 hasConceptScore W3201653419C124101348 @default.
• W3201653419 hasConceptScore W3201653419C132525143 @default.
• W3201653419 hasConceptScore W3201653419C154945302 @default.
• W3201653419 hasConceptScore W3201653419C162324750 @default.

• next