Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977693348> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2977693348 abstract "Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering. Graph AE, VAE and most of their extensions rely on graph convolutional networks (GCN) to learn vector space representations of nodes. In this paper, we propose to replace the GCN encoder by a simple linear model w.r.t. the adjacency matrix of the graph. For the two aforementioned tasks, we empirically show that this approach consistently reaches competitive performances w.r.t. GCN-based models for numerous real-world graphs, including the widely used Cora, Citeseer and Pubmed citation networks that became the de facto benchmark datasets for evaluating graph AE and VAE. This result questions the relevance of repeatedly using these three datasets to compare complex graph AE and VAE models. It also emphasizes the effectiveness of simple node encoding schemes for many real-world applications." @default.
- W2977693348 created "2019-10-10" @default.
- W2977693348 creator A5004879177 @default.
- W2977693348 creator A5057695979 @default.
- W2977693348 creator A5078969242 @default.
- W2977693348 date "2019-10-02" @default.
- W2977693348 modified "2023-09-27" @default.
- W2977693348 title "Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks." @default.
- W2977693348 cites W1662382123 @default.
- W2977693348 cites W1959608418 @default.
- W2977693348 cites W2090891622 @default.
- W2977693348 cites W2387462954 @default.
- W2977693348 cites W2393319904 @default.
- W2977693348 cites W2405933695 @default.
- W2977693348 cites W2554952599 @default.
- W2977693348 cites W2557283755 @default.
- W2977693348 cites W2624407581 @default.
- W2977693348 cites W2624431344 @default.
- W2977693348 cites W2767404761 @default.
- W2977693348 cites W2803526748 @default.
- W2977693348 cites W2808409763 @default.
- W2977693348 cites W2891814056 @default.
- W2977693348 cites W2899680271 @default.
- W2977693348 cites W2916106175 @default.
- W2977693348 cites W2946038989 @default.
- W2977693348 cites W2962756421 @default.
- W2977693348 cites W2962767366 @default.
- W2977693348 cites W2962937159 @default.
- W2977693348 cites W2963460103 @default.
- W2977693348 cites W2963539769 @default.
- W2977693348 cites W2963819570 @default.
- W2977693348 cites W2964015378 @default.
- W2977693348 cites W2964108670 @default.
- W2977693348 cites W2964124573 @default.
- W2977693348 cites W2964321699 @default.
- W2977693348 cites W2964394077 @default.
- W2977693348 cites W2968764971 @default.
- W2977693348 cites W2981450816 @default.
- W2977693348 cites W2984343629 @default.
- W2977693348 cites W3104097132 @default.
- W2977693348 hasPublicationYear "2019" @default.
- W2977693348 type Work @default.
- W2977693348 sameAs 2977693348 @default.
- W2977693348 citedByCount "13" @default.
- W2977693348 countsByYear W29776933482020 @default.
- W2977693348 countsByYear W29776933482021 @default.
- W2977693348 crossrefType "posted-content" @default.
- W2977693348 hasAuthorship W2977693348A5004879177 @default.
- W2977693348 hasAuthorship W2977693348A5057695979 @default.
- W2977693348 hasAuthorship W2977693348A5078969242 @default.
- W2977693348 hasConcept C132525143 @default.
- W2977693348 hasConcept C154945302 @default.
- W2977693348 hasConcept C180356752 @default.
- W2977693348 hasConcept C2779172887 @default.
- W2977693348 hasConcept C41008148 @default.
- W2977693348 hasConcept C41608201 @default.
- W2977693348 hasConcept C80444323 @default.
- W2977693348 hasConceptScore W2977693348C132525143 @default.
- W2977693348 hasConceptScore W2977693348C154945302 @default.
- W2977693348 hasConceptScore W2977693348C180356752 @default.
- W2977693348 hasConceptScore W2977693348C2779172887 @default.
- W2977693348 hasConceptScore W2977693348C41008148 @default.
- W2977693348 hasConceptScore W2977693348C41608201 @default.
- W2977693348 hasConceptScore W2977693348C80444323 @default.
- W2977693348 hasLocation W29776933481 @default.
- W2977693348 hasOpenAccess W2977693348 @default.
- W2977693348 hasPrimaryLocation W29776933481 @default.
- W2977693348 hasRelatedWork W2393319904 @default.
- W2977693348 hasRelatedWork W2519887557 @default.
- W2977693348 hasRelatedWork W2554952599 @default.
- W2977693348 hasRelatedWork W2624431344 @default.
- W2977693348 hasRelatedWork W2942223620 @default.
- W2977693348 hasRelatedWork W2962756421 @default.
- W2977693348 hasRelatedWork W2963017945 @default.
- W2977693348 hasRelatedWork W2972209102 @default.
- W2977693348 hasRelatedWork W2977737675 @default.
- W2977693348 hasRelatedWork W2984343629 @default.
- W2977693348 hasRelatedWork W3013085930 @default.
- W2977693348 hasRelatedWork W3093002101 @default.
- W2977693348 hasRelatedWork W3095213891 @default.
- W2977693348 hasRelatedWork W3104097132 @default.
- W2977693348 hasRelatedWork W3159332271 @default.
- W2977693348 hasRelatedWork W3190021640 @default.
- W2977693348 hasRelatedWork W3193389962 @default.
- W2977693348 hasRelatedWork W3201508510 @default.
- W2977693348 hasRelatedWork W3211716863 @default.
- W2977693348 hasRelatedWork W4210257598 @default.
- W2977693348 isParatext "false" @default.
- W2977693348 isRetracted "false" @default.
- W2977693348 magId "2977693348" @default.
- W2977693348 workType "article" @default.