Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285177410> ?p ?o ?g. }
- W4285177410 endingPage "2438" @default.
- W4285177410 startingPage "2421" @default.
- W4285177410 abstract "Network embedding that maps nodes in a graph to vectors in a Euclidean space is a very powerful method to address various tasks on a graph. However, most network embedding algorithms, in particular, graph neural networks (GNNs), are difficult to interpret and do not scale well to handle millions of nodes. In this article, we tackle the problem from a new perspective based on the equivalence of three constrained optimization problems: the network embedding problem, the trace maximization problem of the modularity matrix in a sampled graph, and the matrix factorization problem of the modularity matrix in a sampled graph. The optimal solutions to these three problems are the dominant eigenvectors of the modularity matrix. We propose two unsupervised learning algorithms that belong to a special class of graph convolutional networks (GCNs) for solving these problems: 1) Clustering As Feature Embedding (CAFE) and 2) Sphere. Both algorithms are stable trace maximization algorithms and yield good approximations of dominant eigenvectors. Moreover, there are linear-time implementations for sparse graphs. Various experiments are conducted to evaluate our algorithms and show that our proposed algorithms outperform several baseline methods." @default.
- W4285177410 created "2022-07-14" @default.
- W4285177410 creator A5016945609 @default.
- W4285177410 creator A5026209439 @default.
- W4285177410 creator A5081012062 @default.
- W4285177410 date "2023-10-01" @default.
- W4285177410 modified "2023-10-06" @default.
- W4285177410 title "Explainable, Stable, and Scalable Network Embedding Algorithms for Unsupervised Learning of Graph Representations" @default.
- W4285177410 cites W1856487264 @default.
- W4285177410 cites W1965580719 @default.
- W4285177410 cites W1977271127 @default.
- W4285177410 cites W1986007546 @default.
- W4285177410 cites W1988219946 @default.
- W4285177410 cites W2008209917 @default.
- W4285177410 cites W2008620264 @default.
- W4285177410 cites W2023655578 @default.
- W4285177410 cites W2026417691 @default.
- W4285177410 cites W2040870580 @default.
- W4285177410 cites W2045107949 @default.
- W4285177410 cites W2062684080 @default.
- W4285177410 cites W2066636486 @default.
- W4285177410 cites W2089458547 @default.
- W4285177410 cites W2090891622 @default.
- W4285177410 cites W2102907934 @default.
- W4285177410 cites W2108614537 @default.
- W4285177410 cites W2116341502 @default.
- W4285177410 cites W2130789338 @default.
- W4285177410 cites W2131681506 @default.
- W4285177410 cites W2132914434 @default.
- W4285177410 cites W2135512436 @default.
- W4285177410 cites W2139906443 @default.
- W4285177410 cites W2142535891 @default.
- W4285177410 cites W2152864241 @default.
- W4285177410 cites W2153959628 @default.
- W4285177410 cites W2158787690 @default.
- W4285177410 cites W2164998314 @default.
- W4285177410 cites W2387462954 @default.
- W4285177410 cites W2393319904 @default.
- W4285177410 cites W2405933695 @default.
- W4285177410 cites W2519796145 @default.
- W4285177410 cites W2571268788 @default.
- W4285177410 cites W2608422103 @default.
- W4285177410 cites W2765570567 @default.
- W4285177410 cites W2768308213 @default.
- W4285177410 cites W2791035291 @default.
- W4285177410 cites W2889672206 @default.
- W4285177410 cites W2903709398 @default.
- W4285177410 cites W2962756421 @default.
- W4285177410 cites W2978831816 @default.
- W4285177410 cites W2990049382 @default.
- W4285177410 cites W2997671625 @default.
- W4285177410 cites W3098726796 @default.
- W4285177410 cites W3101413764 @default.
- W4285177410 cites W3102476541 @default.
- W4285177410 cites W3104097132 @default.
- W4285177410 cites W3105705953 @default.
- W4285177410 cites W3128283229 @default.
- W4285177410 cites W4211042066 @default.
- W4285177410 cites W4235019172 @default.
- W4285177410 cites W4312258136 @default.
- W4285177410 doi "https://doi.org/10.1109/tcss.2022.3181739" @default.
- W4285177410 hasPublicationYear "2023" @default.
- W4285177410 type Work @default.
- W4285177410 citedByCount "0" @default.
- W4285177410 crossrefType "journal-article" @default.
- W4285177410 hasAuthorship W4285177410A5016945609 @default.
- W4285177410 hasAuthorship W4285177410A5026209439 @default.
- W4285177410 hasAuthorship W4285177410A5081012062 @default.
- W4285177410 hasConcept C11413529 @default.
- W4285177410 hasConcept C121332964 @default.
- W4285177410 hasConcept C132525143 @default.
- W4285177410 hasConcept C154945302 @default.
- W4285177410 hasConcept C158693339 @default.
- W4285177410 hasConcept C41008148 @default.
- W4285177410 hasConcept C41608201 @default.
- W4285177410 hasConcept C42355184 @default.
- W4285177410 hasConcept C48044578 @default.
- W4285177410 hasConcept C62520636 @default.
- W4285177410 hasConcept C75564084 @default.
- W4285177410 hasConcept C77088390 @default.
- W4285177410 hasConcept C80444323 @default.
- W4285177410 hasConceptScore W4285177410C11413529 @default.
- W4285177410 hasConceptScore W4285177410C121332964 @default.
- W4285177410 hasConceptScore W4285177410C132525143 @default.
- W4285177410 hasConceptScore W4285177410C154945302 @default.
- W4285177410 hasConceptScore W4285177410C158693339 @default.
- W4285177410 hasConceptScore W4285177410C41008148 @default.
- W4285177410 hasConceptScore W4285177410C41608201 @default.
- W4285177410 hasConceptScore W4285177410C42355184 @default.
- W4285177410 hasConceptScore W4285177410C48044578 @default.
- W4285177410 hasConceptScore W4285177410C62520636 @default.
- W4285177410 hasConceptScore W4285177410C75564084 @default.
- W4285177410 hasConceptScore W4285177410C77088390 @default.
- W4285177410 hasConceptScore W4285177410C80444323 @default.
- W4285177410 hasFunder F4320308258 @default.
- W4285177410 hasFunder F4320322795 @default.
- W4285177410 hasIssue "5" @default.
- W4285177410 hasLocation W42851774101 @default.