Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963270822> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2963270822 abstract "In this work we propose LASAGNE, a methodology to learn locality and structure aware graph node embeddings in an unsupervised way. In particular, we show that the performance of existing random-walk based approaches depends strongly on the structural properties of the graph, e.g., the size of the graph, whether the graph has a flat or upward-sloping Network Community Profile (NCP), whether the graph is expander-like, whether the classes of interest are more k-core-like or more peripheral, etc. For larger graphs with flat NCPs that are strongly expander-like, existing methods lead to random walks that expand rapidly, touching many dissimilar nodes, thereby leading to lower-quality vector representations that are less useful for downstream tasks. Rather than relying on global random walks or neighbors within fixed hop distances, LASAGNE exploits strongly local Approximate Personalized PageRank stationary distributions to more precisely engineer local information into node embeddings. This leads, in particular, to more meaningful and more useful vector representations of nodes in poorly-structured graphs. We show that LASAGNE leads to significant improvement in downstream multi-label classification for larger graphs with flat NCPs and that it is comparable for smaller graphs with upward-sloping NCPs." @default.
- W2963270822 created "2019-07-30" @default.
- W2963270822 creator A5007830019 @default.
- W2963270822 creator A5033006662 @default.
- W2963270822 creator A5050838896 @default.
- W2963270822 creator A5073934226 @default.
- W2963270822 date "2018-12-01" @default.
- W2963270822 modified "2023-10-18" @default.
- W2963270822 title "LASAGNE: Locality and Structure Aware Graph Node Embedding" @default.
- W2963270822 cites W2000041758 @default.
- W2963270822 cites W2033456101 @default.
- W2963270822 cites W2039191721 @default.
- W2963270822 cites W2046253692 @default.
- W2963270822 cites W2058600246 @default.
- W2963270822 cites W2069153192 @default.
- W2963270822 cites W2086254934 @default.
- W2963270822 cites W2090891622 @default.
- W2963270822 cites W2111002549 @default.
- W2963270822 cites W2131717044 @default.
- W2963270822 cites W2146591355 @default.
- W2963270822 cites W2393319904 @default.
- W2963270822 cites W2607500032 @default.
- W2963270822 cites W2741613777 @default.
- W2963270822 cites W2917431650 @default.
- W2963270822 cites W2962756421 @default.
- W2963270822 cites W2963079722 @default.
- W2963270822 cites W2963806858 @default.
- W2963270822 cites W3104097132 @default.
- W2963270822 cites W3105705953 @default.
- W2963270822 doi "https://doi.org/10.1109/wi.2018.00-83" @default.
- W2963270822 hasPublicationYear "2018" @default.
- W2963270822 type Work @default.
- W2963270822 sameAs 2963270822 @default.
- W2963270822 citedByCount "8" @default.
- W2963270822 countsByYear W29632708222018 @default.
- W2963270822 countsByYear W29632708222019 @default.
- W2963270822 countsByYear W29632708222020 @default.
- W2963270822 countsByYear W29632708222021 @default.
- W2963270822 countsByYear W29632708222022 @default.
- W2963270822 crossrefType "proceedings-article" @default.
- W2963270822 hasAuthorship W2963270822A5007830019 @default.
- W2963270822 hasAuthorship W2963270822A5033006662 @default.
- W2963270822 hasAuthorship W2963270822A5050838896 @default.
- W2963270822 hasAuthorship W2963270822A5073934226 @default.
- W2963270822 hasBestOaLocation W29632708222 @default.
- W2963270822 hasConcept C121332964 @default.
- W2963270822 hasConcept C132525143 @default.
- W2963270822 hasConcept C138885662 @default.
- W2963270822 hasConcept C154945302 @default.
- W2963270822 hasConcept C2779808786 @default.
- W2963270822 hasConcept C41008148 @default.
- W2963270822 hasConcept C41608201 @default.
- W2963270822 hasConcept C41895202 @default.
- W2963270822 hasConcept C62520636 @default.
- W2963270822 hasConcept C62611344 @default.
- W2963270822 hasConcept C80444323 @default.
- W2963270822 hasConceptScore W2963270822C121332964 @default.
- W2963270822 hasConceptScore W2963270822C132525143 @default.
- W2963270822 hasConceptScore W2963270822C138885662 @default.
- W2963270822 hasConceptScore W2963270822C154945302 @default.
- W2963270822 hasConceptScore W2963270822C2779808786 @default.
- W2963270822 hasConceptScore W2963270822C41008148 @default.
- W2963270822 hasConceptScore W2963270822C41608201 @default.
- W2963270822 hasConceptScore W2963270822C41895202 @default.
- W2963270822 hasConceptScore W2963270822C62520636 @default.
- W2963270822 hasConceptScore W2963270822C62611344 @default.
- W2963270822 hasConceptScore W2963270822C80444323 @default.
- W2963270822 hasLocation W29632708221 @default.
- W2963270822 hasLocation W29632708222 @default.
- W2963270822 hasOpenAccess W2963270822 @default.
- W2963270822 hasPrimaryLocation W29632708221 @default.
- W2963270822 hasRelatedWork W2808868472 @default.
- W2963270822 hasRelatedWork W2923818335 @default.
- W2963270822 hasRelatedWork W2951545510 @default.
- W2963270822 hasRelatedWork W2962797944 @default.
- W2963270822 hasRelatedWork W3035116611 @default.
- W2963270822 hasRelatedWork W3044354590 @default.
- W2963270822 hasRelatedWork W4226361842 @default.
- W2963270822 hasRelatedWork W4287763734 @default.
- W2963270822 hasRelatedWork W4310879833 @default.
- W2963270822 hasRelatedWork W4323323198 @default.
- W2963270822 isParatext "false" @default.
- W2963270822 isRetracted "false" @default.
- W2963270822 magId "2963270822" @default.
- W2963270822 workType "article" @default.