Matches in SemOpenAlex for { <https://semopenalex.org/work/W3046609541> ?p ?o ?g. }
- W3046609541 abstract "In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods do not learn representations that can be interpreted in a straightforward way and that are robust to perturbations to the graph structure. In this work, we address these two limitations by proposing node2coords, a representation learning algorithm for graphs, which learns simultaneously a low-dimensional space and coordinates for the nodes in that space. The patterns that span the low dimensional space reveal the graph's most important structural information. The coordinates of the nodes reveal the proximity of their local structure to the graph structural patterns. In order to measure this proximity by taking into account the underlying graph, we propose to use Wasserstein distances. We introduce an autoencoder that employs a linear layer in the encoder and a novel Wasserstein barycentric layer at the decoder. Node connectivity descriptors, that capture the local structure of the nodes, are passed through the encoder to learn the small set of graph structural patterns. In the decoder, the node connectivity descriptors are reconstructed as Wasserstein barycenters of the graph structural patterns. The optimal weights for the barycenter representation of a node's connectivity descriptor correspond to the coordinates of that node in the low-dimensional space. Experimental results demonstrate that the representations learned with node2coords are interpretable, lead to node embeddings that are stable to perturbations of the graph structure and achieve competitive or superior results compared to state-of-the-art methods in node classification." @default.
- W3046609541 created "2020-08-07" @default.
- W3046609541 creator A5000947076 @default.
- W3046609541 creator A5014901433 @default.
- W3046609541 creator A5072466998 @default.
- W3046609541 date "2020-07-31" @default.
- W3046609541 modified "2023-10-01" @default.
- W3046609541 title "node2coords: Graph Representation Learning with Wasserstein Barycenters" @default.
- W3046609541 cites W1509562192 @default.
- W3046609541 cites W1574901103 @default.
- W3046609541 cites W1578099820 @default.
- W3046609541 cites W1965555277 @default.
- W3046609541 cites W1968333723 @default.
- W3046609541 cites W2001141328 @default.
- W3046609541 cites W2011959190 @default.
- W3046609541 cites W2036996178 @default.
- W3046609541 cites W2053186076 @default.
- W3046609541 cites W2079639858 @default.
- W3046609541 cites W2090891622 @default.
- W3046609541 cites W2102907934 @default.
- W3046609541 cites W2142535891 @default.
- W3046609541 cites W2156718197 @default.
- W3046609541 cites W2158131535 @default.
- W3046609541 cites W2162833336 @default.
- W3046609541 cites W2294347342 @default.
- W3046609541 cites W2387462954 @default.
- W3046609541 cites W2393319904 @default.
- W3046609541 cites W2415243320 @default.
- W3046609541 cites W2464628725 @default.
- W3046609541 cites W2724892359 @default.
- W3046609541 cites W2759336060 @default.
- W3046609541 cites W2798638367 @default.
- W3046609541 cites W2808856341 @default.
- W3046609541 cites W2808923352 @default.
- W3046609541 cites W2899771611 @default.
- W3046609541 cites W2905189217 @default.
- W3046609541 cites W2912987868 @default.
- W3046609541 cites W2914484425 @default.
- W3046609541 cites W2962756421 @default.
- W3046609541 cites W2963224980 @default.
- W3046609541 cites W2964272353 @default.
- W3046609541 cites W2964321699 @default.
- W3046609541 cites W2970406896 @default.
- W3046609541 cites W2970552844 @default.
- W3046609541 cites W2970782832 @default.
- W3046609541 cites W3022208364 @default.
- W3046609541 cites W3034220197 @default.
- W3046609541 cites W3035671087 @default.
- W3046609541 cites W3101413764 @default.
- W3046609541 cites W3102246635 @default.
- W3046609541 cites W3104097132 @default.
- W3046609541 cites W385466589 @default.
- W3046609541 hasPublicationYear "2020" @default.
- W3046609541 type Work @default.
- W3046609541 sameAs 3046609541 @default.
- W3046609541 citedByCount "2" @default.
- W3046609541 countsByYear W30466095412020 @default.
- W3046609541 countsByYear W30466095412021 @default.
- W3046609541 crossrefType "posted-content" @default.
- W3046609541 hasAuthorship W3046609541A5000947076 @default.
- W3046609541 hasAuthorship W3046609541A5014901433 @default.
- W3046609541 hasAuthorship W3046609541A5072466998 @default.
- W3046609541 hasConcept C101738243 @default.
- W3046609541 hasConcept C111919701 @default.
- W3046609541 hasConcept C11413529 @default.
- W3046609541 hasConcept C114614502 @default.
- W3046609541 hasConcept C118505674 @default.
- W3046609541 hasConcept C127413603 @default.
- W3046609541 hasConcept C132525143 @default.
- W3046609541 hasConcept C154945302 @default.
- W3046609541 hasConcept C184720557 @default.
- W3046609541 hasConcept C33923547 @default.
- W3046609541 hasConcept C41008148 @default.
- W3046609541 hasConcept C50644808 @default.
- W3046609541 hasConcept C59404180 @default.
- W3046609541 hasConcept C62611344 @default.
- W3046609541 hasConcept C66938386 @default.
- W3046609541 hasConcept C80444323 @default.
- W3046609541 hasConceptScore W3046609541C101738243 @default.
- W3046609541 hasConceptScore W3046609541C111919701 @default.
- W3046609541 hasConceptScore W3046609541C11413529 @default.
- W3046609541 hasConceptScore W3046609541C114614502 @default.
- W3046609541 hasConceptScore W3046609541C118505674 @default.
- W3046609541 hasConceptScore W3046609541C127413603 @default.
- W3046609541 hasConceptScore W3046609541C132525143 @default.
- W3046609541 hasConceptScore W3046609541C154945302 @default.
- W3046609541 hasConceptScore W3046609541C184720557 @default.
- W3046609541 hasConceptScore W3046609541C33923547 @default.
- W3046609541 hasConceptScore W3046609541C41008148 @default.
- W3046609541 hasConceptScore W3046609541C50644808 @default.
- W3046609541 hasConceptScore W3046609541C59404180 @default.
- W3046609541 hasConceptScore W3046609541C62611344 @default.
- W3046609541 hasConceptScore W3046609541C66938386 @default.
- W3046609541 hasConceptScore W3046609541C80444323 @default.
- W3046609541 hasLocation W30466095411 @default.
- W3046609541 hasOpenAccess W3046609541 @default.
- W3046609541 hasPrimaryLocation W30466095411 @default.
- W3046609541 hasRelatedWork W2805251015 @default.
- W3046609541 hasRelatedWork W2949659727 @default.
- W3046609541 hasRelatedWork W2952832237 @default.