Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948652371> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2948652371 abstract "In this paper, we propose to embed edges instead of nodes using state-of-the-art neural/factorization methods (DeepWalk, node2vec). These methods produce latent representations based on co-ocurrence statistics by simulating fixed-length random walks and then taking bags-of-vectors as the input to the Skip Gram Learning with Negative Sampling (SGNS). We commence by expressing commute times embedding as matrix factorization, and thus relating this embedding to those of DeepWalk and node2vec. Recent results showing formal links between all these methods via the spectrum of graph Laplacian, are then extended to understand the results obtained by SGNS when we embed edges instead of nodes. Since embedding edges is equivalent to embedding nodes in the line graph, we proceed to combine both existing formal characterizations of the line graphs and empirical evidence in order to explain why this embedding dramatically outperforms its nodal counterpart in multi-label classification tasks." @default.
- W2948652371 created "2019-06-14" @default.
- W2948652371 creator A5018766726 @default.
- W2948652371 creator A5019943145 @default.
- W2948652371 creator A5038387675 @default.
- W2948652371 creator A5074364400 @default.
- W2948652371 date "2019-01-01" @default.
- W2948652371 modified "2023-09-25" @default.
- W2948652371 title "Network Embedding by Walking on the Line Graph" @default.
- W2948652371 cites W173521036 @default.
- W2948652371 cites W2042276255 @default.
- W2948652371 cites W2130470622 @default.
- W2948652371 cites W2153959628 @default.
- W2948652371 cites W2541302947 @default.
- W2948652371 cites W2885316693 @default.
- W2948652371 cites W2917431650 @default.
- W2948652371 cites W2962756421 @default.
- W2948652371 cites W3102056589 @default.
- W2948652371 cites W3104097132 @default.
- W2948652371 cites W3105705953 @default.
- W2948652371 doi "https://doi.org/10.1007/978-3-030-20081-7_21" @default.
- W2948652371 hasPublicationYear "2019" @default.
- W2948652371 type Work @default.
- W2948652371 sameAs 2948652371 @default.
- W2948652371 citedByCount "0" @default.
- W2948652371 crossrefType "book-chapter" @default.
- W2948652371 hasAuthorship W2948652371A5018766726 @default.
- W2948652371 hasAuthorship W2948652371A5019943145 @default.
- W2948652371 hasAuthorship W2948652371A5038387675 @default.
- W2948652371 hasAuthorship W2948652371A5074364400 @default.
- W2948652371 hasConcept C105795698 @default.
- W2948652371 hasConcept C11413529 @default.
- W2948652371 hasConcept C121194460 @default.
- W2948652371 hasConcept C132525143 @default.
- W2948652371 hasConcept C154945302 @default.
- W2948652371 hasConcept C187834632 @default.
- W2948652371 hasConcept C198352243 @default.
- W2948652371 hasConcept C203776342 @default.
- W2948652371 hasConcept C2524010 @default.
- W2948652371 hasConcept C33923547 @default.
- W2948652371 hasConcept C41008148 @default.
- W2948652371 hasConcept C41608201 @default.
- W2948652371 hasConcept C75564084 @default.
- W2948652371 hasConcept C80444323 @default.
- W2948652371 hasConceptScore W2948652371C105795698 @default.
- W2948652371 hasConceptScore W2948652371C11413529 @default.
- W2948652371 hasConceptScore W2948652371C121194460 @default.
- W2948652371 hasConceptScore W2948652371C132525143 @default.
- W2948652371 hasConceptScore W2948652371C154945302 @default.
- W2948652371 hasConceptScore W2948652371C187834632 @default.
- W2948652371 hasConceptScore W2948652371C198352243 @default.
- W2948652371 hasConceptScore W2948652371C203776342 @default.
- W2948652371 hasConceptScore W2948652371C2524010 @default.
- W2948652371 hasConceptScore W2948652371C33923547 @default.
- W2948652371 hasConceptScore W2948652371C41008148 @default.
- W2948652371 hasConceptScore W2948652371C41608201 @default.
- W2948652371 hasConceptScore W2948652371C75564084 @default.
- W2948652371 hasConceptScore W2948652371C80444323 @default.
- W2948652371 hasLocation W29486523711 @default.
- W2948652371 hasOpenAccess W2948652371 @default.
- W2948652371 hasPrimaryLocation W29486523711 @default.
- W2948652371 hasRelatedWork W2544165879 @default.
- W2948652371 hasRelatedWork W2765425003 @default.
- W2948652371 hasRelatedWork W2785456199 @default.
- W2948652371 hasRelatedWork W2892310698 @default.
- W2948652371 hasRelatedWork W2948652371 @default.
- W2948652371 hasRelatedWork W2965608837 @default.
- W2948652371 hasRelatedWork W3044354590 @default.
- W2948652371 hasRelatedWork W3103545790 @default.
- W2948652371 hasRelatedWork W3106263792 @default.
- W2948652371 hasRelatedWork W3128479678 @default.
- W2948652371 isParatext "false" @default.
- W2948652371 isRetracted "false" @default.
- W2948652371 magId "2948652371" @default.
- W2948652371 workType "book-chapter" @default.