Matches in SemOpenAlex for { <https://semopenalex.org/work/W2970298096> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2970298096 endingPage "1980" @default.
- W2970298096 startingPage "1953" @default.
- W2970298096 abstract "Network embedding aims to learn a latent, low-dimensional vector representations of network nodes, effective in supporting various network analytic tasks. While prior arts on network embedding focus primarily on preserving network topology structure to learn node representations, recently proposed attributed network embedding algorithms attempt to integrate rich node content information with network topological structure for enhancing the quality of network embedding. In reality, networks often have sparse content, incomplete node attributes, as well as the discrepancy between node attribute feature space and network structure space, which severely deteriorates the performance of existing methods. In this paper, we propose a unified framework for attributed network embedding–attri2vec—that learns node embeddings by discovering a latent node attribute subspace via a network structure guided transformation performed on the original attribute space. The resultant latent subspace can respect network structure in a more consistent way towards learning high-quality node representations. We formulate an optimization problem which is solved by an efficient stochastic gradient descent algorithm, with linear time complexity to the number of nodes. We investigate a series of linear and non-linear transformations performed on node attributes and empirically validate their effectiveness on various types of networks. Another advantage of attri2vec is its ability to solve out-of-sample problems, where embeddings of new coming nodes can be inferred from their node attributes through the learned mapping function. Experiments on various types of networks confirm that attri2vec is superior to state-of-the-art baselines for node classification, node clustering, as well as out-of-sample link prediction tasks. The source code of this paper is available at https://github.com/daokunzhang/attri2vec ." @default.
- W2970298096 created "2019-09-05" @default.
- W2970298096 creator A5014017635 @default.
- W2970298096 creator A5074852078 @default.
- W2970298096 creator A5084641325 @default.
- W2970298096 date "2019-08-26" @default.
- W2970298096 modified "2023-10-14" @default.
- W2970298096 title "Attributed network embedding via subspace discovery" @default.
- W2970298096 cites W1504886279 @default.
- W2970298096 cites W2015953751 @default.
- W2970298096 cites W2090891622 @default.
- W2970298096 cites W2111114024 @default.
- W2970298096 cites W2123688186 @default.
- W2970298096 cites W2166395447 @default.
- W2970298096 cites W2393319904 @default.
- W2970298096 cites W2415243320 @default.
- W2970298096 cites W2511871973 @default.
- W2970298096 cites W2533635416 @default.
- W2970298096 cites W2583803680 @default.
- W2970298096 cites W2585247128 @default.
- W2970298096 cites W2604942799 @default.
- W2970298096 cites W2622489478 @default.
- W2970298096 cites W2739946816 @default.
- W2970298096 cites W2767460050 @default.
- W2970298096 cites W2808528665 @default.
- W2970298096 cites W2950723285 @default.
- W2970298096 cites W2962756421 @default.
- W2970298096 cites W3104097132 @default.
- W2970298096 cites W3105705953 @default.
- W2970298096 cites W4237723258 @default.
- W2970298096 doi "https://doi.org/10.1007/s10618-019-00650-2" @default.
- W2970298096 hasPublicationYear "2019" @default.
- W2970298096 type Work @default.
- W2970298096 sameAs 2970298096 @default.
- W2970298096 citedByCount "26" @default.
- W2970298096 countsByYear W29702980962019 @default.
- W2970298096 countsByYear W29702980962020 @default.
- W2970298096 countsByYear W29702980962021 @default.
- W2970298096 countsByYear W29702980962022 @default.
- W2970298096 countsByYear W29702980962023 @default.
- W2970298096 crossrefType "journal-article" @default.
- W2970298096 hasAuthorship W2970298096A5014017635 @default.
- W2970298096 hasAuthorship W2970298096A5074852078 @default.
- W2970298096 hasAuthorship W2970298096A5084641325 @default.
- W2970298096 hasBestOaLocation W29702980962 @default.
- W2970298096 hasConcept C104317684 @default.
- W2970298096 hasConcept C124101348 @default.
- W2970298096 hasConcept C127413603 @default.
- W2970298096 hasConcept C154945302 @default.
- W2970298096 hasConcept C185592680 @default.
- W2970298096 hasConcept C204241405 @default.
- W2970298096 hasConcept C32834561 @default.
- W2970298096 hasConcept C41008148 @default.
- W2970298096 hasConcept C41608201 @default.
- W2970298096 hasConcept C55493867 @default.
- W2970298096 hasConcept C62611344 @default.
- W2970298096 hasConcept C66938386 @default.
- W2970298096 hasConcept C80444323 @default.
- W2970298096 hasConceptScore W2970298096C104317684 @default.
- W2970298096 hasConceptScore W2970298096C124101348 @default.
- W2970298096 hasConceptScore W2970298096C127413603 @default.
- W2970298096 hasConceptScore W2970298096C154945302 @default.
- W2970298096 hasConceptScore W2970298096C185592680 @default.
- W2970298096 hasConceptScore W2970298096C204241405 @default.
- W2970298096 hasConceptScore W2970298096C32834561 @default.
- W2970298096 hasConceptScore W2970298096C41008148 @default.
- W2970298096 hasConceptScore W2970298096C41608201 @default.
- W2970298096 hasConceptScore W2970298096C55493867 @default.
- W2970298096 hasConceptScore W2970298096C62611344 @default.
- W2970298096 hasConceptScore W2970298096C66938386 @default.
- W2970298096 hasConceptScore W2970298096C80444323 @default.
- W2970298096 hasIssue "6" @default.
- W2970298096 hasLocation W29702980961 @default.
- W2970298096 hasLocation W29702980962 @default.
- W2970298096 hasOpenAccess W2970298096 @default.
- W2970298096 hasPrimaryLocation W29702980961 @default.
- W2970298096 hasRelatedWork W1503053695 @default.
- W2970298096 hasRelatedWork W2055709700 @default.
- W2970298096 hasRelatedWork W2078643146 @default.
- W2970298096 hasRelatedWork W2365767001 @default.
- W2970298096 hasRelatedWork W2379147087 @default.
- W2970298096 hasRelatedWork W2383650581 @default.
- W2970298096 hasRelatedWork W2951545510 @default.
- W2970298096 hasRelatedWork W3115310459 @default.
- W2970298096 hasRelatedWork W3161596960 @default.
- W2970298096 hasRelatedWork W4288093320 @default.
- W2970298096 hasVolume "33" @default.
- W2970298096 isParatext "false" @default.
- W2970298096 isRetracted "false" @default.
- W2970298096 magId "2970298096" @default.
- W2970298096 workType "article" @default.