Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128017146> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3128017146 abstract "Network embedding (NE), aiming to embed a network into a low dimensional latent representation while preserving the inherent structural properties of the network, has attracted considerable attention recently. Variational Autoencoder (VAE) has been widely studied for NE. Existing VAE based methods let the network follow a unimodal distribution, that is, they typically use some fixed distribution as the prior, e.g. Gaussian distribution. However, in reality networks often contain many complicated structural properties [5], [6] (such as the first/second order proximity, the motif or community structures, power-law, etc). The latent representation from unimodal and fixed distribution is not capable of describing such multi-modal characteristic of networks. To address this issue, we develop a new VAE method for NE, named Normalizing Flow Variational Graph Autoencoder (NF-VGA). We design a prior-generative module based on normalizing flows to generate flexible, multi-modal distribution as the prior of the latent representation. To make the generated prior better describe the coupling relationship between nodes, we further utilize network local structures to guide the prior generation. Extensive experiments on some real-world networks show a superior performance of the new approach over some state-of-the-art methods on some popular network embedding tasks." @default.
- W3128017146 created "2021-02-15" @default.
- W3128017146 creator A5005761664 @default.
- W3128017146 creator A5012455357 @default.
- W3128017146 creator A5027782089 @default.
- W3128017146 creator A5056415908 @default.
- W3128017146 creator A5067998200 @default.
- W3128017146 creator A5077596057 @default.
- W3128017146 date "2020-11-01" @default.
- W3128017146 modified "2023-09-26" @default.
- W3128017146 title "NF-VGA: Incorporating Normalizing Flows into Graph Variational Autoencoder for Embedding Attribute Networks" @default.
- W3128017146 cites W1785502294 @default.
- W3128017146 cites W1997358273 @default.
- W3128017146 cites W2130354913 @default.
- W3128017146 cites W2393319904 @default.
- W3128017146 cites W2808409763 @default.
- W3128017146 cites W2962756421 @default.
- W3128017146 cites W2965819445 @default.
- W3128017146 cites W2971452831 @default.
- W3128017146 cites W2972607219 @default.
- W3128017146 cites W2996259521 @default.
- W3128017146 cites W3104097132 @default.
- W3128017146 doi "https://doi.org/10.1109/icdm50108.2020.00157" @default.
- W3128017146 hasPublicationYear "2020" @default.
- W3128017146 type Work @default.
- W3128017146 sameAs 3128017146 @default.
- W3128017146 citedByCount "1" @default.
- W3128017146 countsByYear W31280171462023 @default.
- W3128017146 crossrefType "proceedings-article" @default.
- W3128017146 hasAuthorship W3128017146A5005761664 @default.
- W3128017146 hasAuthorship W3128017146A5012455357 @default.
- W3128017146 hasAuthorship W3128017146A5027782089 @default.
- W3128017146 hasAuthorship W3128017146A5056415908 @default.
- W3128017146 hasAuthorship W3128017146A5067998200 @default.
- W3128017146 hasAuthorship W3128017146A5077596057 @default.
- W3128017146 hasConcept C101738243 @default.
- W3128017146 hasConcept C11413529 @default.
- W3128017146 hasConcept C121332964 @default.
- W3128017146 hasConcept C132525143 @default.
- W3128017146 hasConcept C153180895 @default.
- W3128017146 hasConcept C154945302 @default.
- W3128017146 hasConcept C163716315 @default.
- W3128017146 hasConcept C167966045 @default.
- W3128017146 hasConcept C17744445 @default.
- W3128017146 hasConcept C185592680 @default.
- W3128017146 hasConcept C188027245 @default.
- W3128017146 hasConcept C199539241 @default.
- W3128017146 hasConcept C2776359362 @default.
- W3128017146 hasConcept C39890363 @default.
- W3128017146 hasConcept C41008148 @default.
- W3128017146 hasConcept C41608201 @default.
- W3128017146 hasConcept C50644808 @default.
- W3128017146 hasConcept C62520636 @default.
- W3128017146 hasConcept C71139939 @default.
- W3128017146 hasConcept C80444323 @default.
- W3128017146 hasConcept C94625758 @default.
- W3128017146 hasConceptScore W3128017146C101738243 @default.
- W3128017146 hasConceptScore W3128017146C11413529 @default.
- W3128017146 hasConceptScore W3128017146C121332964 @default.
- W3128017146 hasConceptScore W3128017146C132525143 @default.
- W3128017146 hasConceptScore W3128017146C153180895 @default.
- W3128017146 hasConceptScore W3128017146C154945302 @default.
- W3128017146 hasConceptScore W3128017146C163716315 @default.
- W3128017146 hasConceptScore W3128017146C167966045 @default.
- W3128017146 hasConceptScore W3128017146C17744445 @default.
- W3128017146 hasConceptScore W3128017146C185592680 @default.
- W3128017146 hasConceptScore W3128017146C188027245 @default.
- W3128017146 hasConceptScore W3128017146C199539241 @default.
- W3128017146 hasConceptScore W3128017146C2776359362 @default.
- W3128017146 hasConceptScore W3128017146C39890363 @default.
- W3128017146 hasConceptScore W3128017146C41008148 @default.
- W3128017146 hasConceptScore W3128017146C41608201 @default.
- W3128017146 hasConceptScore W3128017146C50644808 @default.
- W3128017146 hasConceptScore W3128017146C62520636 @default.
- W3128017146 hasConceptScore W3128017146C71139939 @default.
- W3128017146 hasConceptScore W3128017146C80444323 @default.
- W3128017146 hasConceptScore W3128017146C94625758 @default.
- W3128017146 hasFunder F4320321001 @default.
- W3128017146 hasLocation W31280171461 @default.
- W3128017146 hasOpenAccess W3128017146 @default.
- W3128017146 hasPrimaryLocation W31280171461 @default.
- W3128017146 hasRelatedWork W2335364074 @default.
- W3128017146 hasRelatedWork W2572600474 @default.
- W3128017146 hasRelatedWork W2592385986 @default.
- W3128017146 hasRelatedWork W2776466379 @default.
- W3128017146 hasRelatedWork W2897995864 @default.
- W3128017146 hasRelatedWork W2998168123 @default.
- W3128017146 hasRelatedWork W3126201013 @default.
- W3128017146 hasRelatedWork W4220775285 @default.
- W3128017146 hasRelatedWork W4287995534 @default.
- W3128017146 hasRelatedWork W4300480195 @default.
- W3128017146 isParatext "false" @default.
- W3128017146 isRetracted "false" @default.
- W3128017146 magId "3128017146" @default.
- W3128017146 workType "article" @default.