Matches in SemOpenAlex for { <https://semopenalex.org/work/W2946108624> ?p ?o ?g. }
- W2946108624 abstract "Networks have been widely used as the data structure for abstracting real-world systems as well as organizing the relations among entities. Network embedding models are powerful tools in mapping nodes in a network into continuous vector-space representations in order to facilitate subsequent tasks such as classification and link prediction. Existing network embedding models comprehensively integrate all information of each node, such as links and attributes, towards a single embedding vector to represent the node's general role in the network. However, a real-world entity could be multifaceted, where it connects to different neighborhoods due to different motives or self-characteristics that are not necessarily correlated. For example, in a movie recommender system, a user may love comedies or horror movies simultaneously, but it is not likely that these two types of movies are mutually close in the embedding space, nor the user embedding vector could be sufficiently close to them at the same time. In this paper, we propose a polysemous embedding approach for modeling multiple facets of nodes, as motivated by the phenomenon of word polysemy in language modeling. Each facet of a node is mapped as an embedding vector, while we also maintain association degree between each pair of node and facet. The proposed method is adaptive to various existing embedding models, without significantly complicating the optimization process. We also discuss how to engage embedding vectors of different facets for inference tasks including classification and link prediction. Experiments on real-world datasets help comprehensively evaluate the performance of the proposed method." @default.
- W2946108624 created "2019-05-29" @default.
- W2946108624 creator A5007489034 @default.
- W2946108624 creator A5043697901 @default.
- W2946108624 creator A5057864403 @default.
- W2946108624 creator A5068477431 @default.
- W2946108624 creator A5070873121 @default.
- W2946108624 creator A5082599714 @default.
- W2946108624 date "2019-05-25" @default.
- W2946108624 modified "2023-09-27" @default.
- W2946108624 title "Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding" @default.
- W2946108624 cites W1504886279 @default.
- W2946108624 cites W1964311319 @default.
- W2946108624 cites W2013029404 @default.
- W2946108624 cites W2153579005 @default.
- W2946108624 cites W2162456950 @default.
- W2946108624 cites W2164019165 @default.
- W2946108624 cites W2164973920 @default.
- W2946108624 cites W2238728730 @default.
- W2946108624 cites W2340502990 @default.
- W2946108624 cites W2387462954 @default.
- W2946108624 cites W2393319904 @default.
- W2946108624 cites W2519887557 @default.
- W2946108624 cites W2583803680 @default.
- W2946108624 cites W2604942799 @default.
- W2946108624 cites W2624431344 @default.
- W2946108624 cites W2753738274 @default.
- W2946108624 cites W2768352146 @default.
- W2946108624 cites W2782914678 @default.
- W2946108624 cites W2787927827 @default.
- W2946108624 cites W2788451951 @default.
- W2946108624 cites W2808787330 @default.
- W2946108624 cites W2808923352 @default.
- W2946108624 cites W2809441541 @default.
- W2946108624 cites W2809660921 @default.
- W2946108624 cites W2883559670 @default.
- W2946108624 cites W2907379153 @default.
- W2946108624 cites W2950723285 @default.
- W2946108624 cites W2951004968 @default.
- W2946108624 cites W2962756421 @default.
- W2946108624 cites W2962767366 @default.
- W2946108624 cites W2963460103 @default.
- W2946108624 cites W2996061341 @default.
- W2946108624 cites W3100848837 @default.
- W2946108624 cites W3103995645 @default.
- W2946108624 cites W3104097132 @default.
- W2946108624 cites W3143596294 @default.
- W2946108624 hasPublicationYear "2019" @default.
- W2946108624 type Work @default.
- W2946108624 sameAs 2946108624 @default.
- W2946108624 citedByCount "1" @default.
- W2946108624 countsByYear W29461086242019 @default.
- W2946108624 crossrefType "proceedings-article" @default.
- W2946108624 hasAuthorship W2946108624A5007489034 @default.
- W2946108624 hasAuthorship W2946108624A5043697901 @default.
- W2946108624 hasAuthorship W2946108624A5057864403 @default.
- W2946108624 hasAuthorship W2946108624A5068477431 @default.
- W2946108624 hasAuthorship W2946108624A5070873121 @default.
- W2946108624 hasAuthorship W2946108624A5082599714 @default.
- W2946108624 hasBestOaLocation W29461086241 @default.
- W2946108624 hasConcept C124101348 @default.
- W2946108624 hasConcept C127413603 @default.
- W2946108624 hasConcept C13336665 @default.
- W2946108624 hasConcept C154945302 @default.
- W2946108624 hasConcept C2524010 @default.
- W2946108624 hasConcept C2776214188 @default.
- W2946108624 hasConcept C2777462759 @default.
- W2946108624 hasConcept C2780276568 @default.
- W2946108624 hasConcept C33923547 @default.
- W2946108624 hasConcept C41008148 @default.
- W2946108624 hasConcept C41608201 @default.
- W2946108624 hasConcept C62611344 @default.
- W2946108624 hasConcept C66938386 @default.
- W2946108624 hasConcept C80444323 @default.
- W2946108624 hasConceptScore W2946108624C124101348 @default.
- W2946108624 hasConceptScore W2946108624C127413603 @default.
- W2946108624 hasConceptScore W2946108624C13336665 @default.
- W2946108624 hasConceptScore W2946108624C154945302 @default.
- W2946108624 hasConceptScore W2946108624C2524010 @default.
- W2946108624 hasConceptScore W2946108624C2776214188 @default.
- W2946108624 hasConceptScore W2946108624C2777462759 @default.
- W2946108624 hasConceptScore W2946108624C2780276568 @default.
- W2946108624 hasConceptScore W2946108624C33923547 @default.
- W2946108624 hasConceptScore W2946108624C41008148 @default.
- W2946108624 hasConceptScore W2946108624C41608201 @default.
- W2946108624 hasConceptScore W2946108624C62611344 @default.
- W2946108624 hasConceptScore W2946108624C66938386 @default.
- W2946108624 hasConceptScore W2946108624C80444323 @default.
- W2946108624 hasLocation W29461086241 @default.
- W2946108624 hasOpenAccess W2946108624 @default.
- W2946108624 hasPrimaryLocation W29461086241 @default.
- W2946108624 hasRelatedWork W2796988304 @default.
- W2946108624 hasRelatedWork W2835252343 @default.
- W2946108624 hasRelatedWork W2895654512 @default.
- W2946108624 hasRelatedWork W2903036385 @default.
- W2946108624 hasRelatedWork W2905181608 @default.
- W2946108624 hasRelatedWork W2916059024 @default.
- W2946108624 hasRelatedWork W2940847211 @default.
- W2946108624 hasRelatedWork W2940882578 @default.
- W2946108624 hasRelatedWork W2946250457 @default.