Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034293229> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W3034293229 abstract "Graph embeddings are a ubiquitous tool for machine learning tasks, such as node classification and link prediction, on graph-structured data. However, computing the embeddings for large-scale graphs is prohibitively inefficient even if we are interested only in a small subset of relevant vertices. To address this, we present an efficient graph coarsening approach, based on Schur complements, for computing the embedding of the relevant vertices. We prove that these embeddings are preserved exactly by the Schur complement graph that is obtained via Gaussian elimination on the non-relevant vertices. As computing Schur complements is expensive, we give a nearly-linear time algorithm that generates a coarsened graph on the relevant vertices that provably matches the Schur complement in expectation in each iteration. Our experiments involving prediction tasks on graphs demonstrate that computing embeddings on the coarsened graph, rather than the entire graph, leads to significant time savings without sacrificing accuracy." @default.
- W3034293229 created "2020-06-19" @default.
- W3034293229 creator A5015009174 @default.
- W3034293229 creator A5015978857 @default.
- W3034293229 creator A5019846729 @default.
- W3034293229 creator A5067464936 @default.
- W3034293229 creator A5078315645 @default.
- W3034293229 date "2020-07-06" @default.
- W3034293229 modified "2023-10-03" @default.
- W3034293229 title "Faster Graph Embeddings via Coarsening" @default.
- W3034293229 hasPublicationYear "2020" @default.
- W3034293229 type Work @default.
- W3034293229 sameAs 3034293229 @default.
- W3034293229 citedByCount "2" @default.
- W3034293229 countsByYear W30342932292021 @default.
- W3034293229 crossrefType "posted-content" @default.
- W3034293229 hasAuthorship W3034293229A5015009174 @default.
- W3034293229 hasAuthorship W3034293229A5015978857 @default.
- W3034293229 hasAuthorship W3034293229A5019846729 @default.
- W3034293229 hasAuthorship W3034293229A5067464936 @default.
- W3034293229 hasAuthorship W3034293229A5078315645 @default.
- W3034293229 hasConcept C114614502 @default.
- W3034293229 hasConcept C132525143 @default.
- W3034293229 hasConcept C154945302 @default.
- W3034293229 hasConcept C168291704 @default.
- W3034293229 hasConcept C203776342 @default.
- W3034293229 hasConcept C22149727 @default.
- W3034293229 hasConcept C33923547 @default.
- W3034293229 hasConcept C41008148 @default.
- W3034293229 hasConcept C41608201 @default.
- W3034293229 hasConcept C80444323 @default.
- W3034293229 hasConceptScore W3034293229C114614502 @default.
- W3034293229 hasConceptScore W3034293229C132525143 @default.
- W3034293229 hasConceptScore W3034293229C154945302 @default.
- W3034293229 hasConceptScore W3034293229C168291704 @default.
- W3034293229 hasConceptScore W3034293229C203776342 @default.
- W3034293229 hasConceptScore W3034293229C22149727 @default.
- W3034293229 hasConceptScore W3034293229C33923547 @default.
- W3034293229 hasConceptScore W3034293229C41008148 @default.
- W3034293229 hasConceptScore W3034293229C41608201 @default.
- W3034293229 hasConceptScore W3034293229C80444323 @default.
- W3034293229 hasOpenAccess W3034293229 @default.
- W3034293229 hasRelatedWork W10324078 @default.
- W3034293229 hasRelatedWork W11694923 @default.
- W3034293229 hasRelatedWork W12912828 @default.
- W3034293229 hasRelatedWork W370772 @default.
- W3034293229 hasRelatedWork W4696356 @default.
- W3034293229 hasRelatedWork W5374421 @default.
- W3034293229 hasRelatedWork W7585623 @default.
- W3034293229 hasRelatedWork W8711176 @default.
- W3034293229 hasRelatedWork W8885230 @default.
- W3034293229 hasRelatedWork W9290964 @default.
- W3034293229 isParatext "false" @default.
- W3034293229 isRetracted "false" @default.
- W3034293229 magId "3034293229" @default.
- W3034293229 workType "article" @default.