Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089094711> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3089094711 endingPage "1" @default.
- W3089094711 startingPage "1" @default.
- W3089094711 abstract "Heterogeneous information networks(HINs) become popular in recent years for its strong capability of modelling objects with abundant information using explicit network structure. Network embedding has been proved as an effective method to convert information networks into lower-dimensional space, whereas the core information can be well preserved. However, traditional network embedding algorithms are sub-optimal in capturing rich while potentially incompatible semantics provided by HINs. To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is designed to simultaneously learn multiple node representations for different meta-paths. More specifically, one representation learning module inspired by the RNN structure is developed and multiple node representations can be learned simultaneously, where each representation is associated with one respective meta-path. By measuring the relevance between nodes with the designed objective function, the learned module can be applied in downstream link prediction tasks. A set of criteria for selecting initial meta-paths is proposed as the other module in mSHINE which is important to reduce the optimal meta-path selection cost when no prior knowledge of suitable meta-paths is available. To corroborate the effectiveness of mSHINE, extensive experimental studies including node classification and link prediction are conducted on five real-world datasets. The results demonstrate that mSHINE outperforms other state-of-the-art HIN embedding methods." @default.
- W3089094711 created "2020-10-01" @default.
- W3089094711 creator A5003043493 @default.
- W3089094711 creator A5039545694 @default.
- W3089094711 date "2020-01-01" @default.
- W3089094711 modified "2023-10-16" @default.
- W3089094711 title "mSHINE: A Multiple-meta-paths Simultaneous Learning Framework for Heterogeneous Information Network Embedding" @default.
- W3089094711 cites W103340358 @default.
- W3089094711 cites W1975563293 @default.
- W3089094711 cites W2149288670 @default.
- W3089094711 cites W2157331557 @default.
- W3089094711 cites W2219888463 @default.
- W3089094711 cites W2393319904 @default.
- W3089094711 cites W2470673105 @default.
- W3089094711 cites W2577283662 @default.
- W3089094711 cites W2743104969 @default.
- W3089094711 cites W2767774008 @default.
- W3089094711 cites W2808466528 @default.
- W3089094711 cites W2809435521 @default.
- W3089094711 cites W2884134047 @default.
- W3089094711 cites W2911286998 @default.
- W3089094711 cites W2943373497 @default.
- W3089094711 cites W2951626319 @default.
- W3089094711 cites W2952343887 @default.
- W3089094711 cites W2962756421 @default.
- W3089094711 cites W2962975498 @default.
- W3089094711 cites W2963224980 @default.
- W3089094711 cites W2963512530 @default.
- W3089094711 cites W2963707260 @default.
- W3089094711 cites W2963844113 @default.
- W3089094711 cites W2963919031 @default.
- W3089094711 cites W3104097132 @default.
- W3089094711 cites W3104717349 @default.
- W3089094711 cites W3105705953 @default.
- W3089094711 cites W4254816979 @default.
- W3089094711 cites W4288278932 @default.
- W3089094711 doi "https://doi.org/10.1109/tkde.2020.3025464" @default.
- W3089094711 hasPublicationYear "2020" @default.
- W3089094711 type Work @default.
- W3089094711 sameAs 3089094711 @default.
- W3089094711 citedByCount "3" @default.
- W3089094711 countsByYear W30890947112022 @default.
- W3089094711 countsByYear W30890947112023 @default.
- W3089094711 crossrefType "journal-article" @default.
- W3089094711 hasAuthorship W3089094711A5003043493 @default.
- W3089094711 hasAuthorship W3089094711A5039545694 @default.
- W3089094711 hasBestOaLocation W30890947112 @default.
- W3089094711 hasConcept C108037233 @default.
- W3089094711 hasConcept C124101348 @default.
- W3089094711 hasConcept C154945302 @default.
- W3089094711 hasConcept C158207573 @default.
- W3089094711 hasConcept C41008148 @default.
- W3089094711 hasConcept C41608201 @default.
- W3089094711 hasConcept C555944384 @default.
- W3089094711 hasConcept C76155785 @default.
- W3089094711 hasConcept C80444323 @default.
- W3089094711 hasConceptScore W3089094711C108037233 @default.
- W3089094711 hasConceptScore W3089094711C124101348 @default.
- W3089094711 hasConceptScore W3089094711C154945302 @default.
- W3089094711 hasConceptScore W3089094711C158207573 @default.
- W3089094711 hasConceptScore W3089094711C41008148 @default.
- W3089094711 hasConceptScore W3089094711C41608201 @default.
- W3089094711 hasConceptScore W3089094711C555944384 @default.
- W3089094711 hasConceptScore W3089094711C76155785 @default.
- W3089094711 hasConceptScore W3089094711C80444323 @default.
- W3089094711 hasLocation W30890947111 @default.
- W3089094711 hasLocation W30890947112 @default.
- W3089094711 hasLocation W30890947113 @default.
- W3089094711 hasOpenAccess W3089094711 @default.
- W3089094711 hasPrimaryLocation W30890947111 @default.
- W3089094711 hasRelatedWork W2765425003 @default.
- W3089094711 hasRelatedWork W2903634148 @default.
- W3089094711 hasRelatedWork W2950307844 @default.
- W3089094711 hasRelatedWork W2972179598 @default.
- W3089094711 hasRelatedWork W3009612160 @default.
- W3089094711 hasRelatedWork W3014537556 @default.
- W3089094711 hasRelatedWork W3089200643 @default.
- W3089094711 hasRelatedWork W3191449014 @default.
- W3089094711 hasRelatedWork W4285544886 @default.
- W3089094711 hasRelatedWork W4308872799 @default.
- W3089094711 isParatext "false" @default.
- W3089094711 isRetracted "false" @default.
- W3089094711 magId "3089094711" @default.
- W3089094711 workType "article" @default.