FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3021451168> ?p ?o ?g. }

• W3021451168 endingPage "85453" @default.
• W3021451168 startingPage "85441" @default.
• W3021451168 abstract "As an effective technique to learn low-dimensional node features in complicated network environment, network embedding has become a promising research direction in the field of network analysis. Due to the virtues of better interpretability and flexibility, matrix factorization based methods for network embedding have received increasing attentions. However, most of them are inadequate to learn more complicated hierarchical features hidden in complex networks because of their mechanisms of single-layer factorization structure. Besides, their original feature matrices used for factorization and their robustness against noises also need to be further improved. To solve these problems, we propose a novel network embedding method named DRNMF (deep robust nonnegative matrix factorization), which is formed by multi-layer NMF learning structure. Meanwhile, DRNMF employs the combination of high-order proximity matrices of the network as the original feature matrix for the factorization. To improve the robustness against noises, we use ℓ <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2,1</sub> norm to devise the objective function for the DRNMF network embedding model. Effective iterative update rules are derived to resolve the model, and the convergence of these rules are strictly proved. Moreover, we introduce a pre-training strategy to improve the efficiency of convergence. Extensive experiments on several benchmarks of complex networks demonstrate that our proposed method DRNMF is effective and has better performance than the state-of-the-art matrix factorization based methods for network embedding." @default.
• W3021451168 created "2020-05-13" @default.
• W3021451168 creator A5001989082 @default.
• W3021451168 creator A5013479932 @default.
• W3021451168 creator A5026139698 @default.
• W3021451168 creator A5031808267 @default.
• W3021451168 creator A5056002024 @default.
• W3021451168 creator A5081342676 @default.
• W3021451168 date "2020-01-01" @default.
• W3021451168 modified "2023-10-12" @default.
• W3021451168 title "Network Embedding Using Deep Robust Nonnegative Matrix Factorization" @default.
• W3021451168 cites W1902027874 @default.
• W3021451168 cites W1979104937 @default.
• W3021451168 cites W2016412486 @default.
• W3021451168 cites W2090891622 @default.
• W3021451168 cites W2104819583 @default.
• W3021451168 cites W2108433027 @default.
• W3021451168 cites W2142535891 @default.
• W3021451168 cites W2168103112 @default.
• W3021451168 cites W2168627253 @default.
• W3021451168 cites W2387462954 @default.
• W3021451168 cites W2393319904 @default.
• W3021451168 cites W2525068948 @default.
• W3021451168 cites W2586573945 @default.
• W3021451168 cites W2612872092 @default.
• W3021451168 cites W2620611182 @default.
• W3021451168 cites W2739747431 @default.
• W3021451168 cites W2762237834 @default.
• W3021451168 cites W2765386553 @default.
• W3021451168 cites W2897979119 @default.
• W3021451168 cites W2913855763 @default.
• W3021451168 cites W2916059024 @default.
• W3021451168 cites W2942962046 @default.
• W3021451168 cites W2956490308 @default.
• W3021451168 cites W2962756421 @default.
• W3021451168 cites W2963224980 @default.
• W3021451168 cites W2963512530 @default.
• W3021451168 cites W2964144157 @default.
• W3021451168 cites W3104097132 @default.
• W3021451168 cites W3105705953 @default.
• W3021451168 cites W3126033509 @default.
• W3021451168 cites W4250589301 @default.
• W3021451168 cites W4291474301 @default.
• W3021451168 doi "https://doi.org/10.1109/access.2020.2992269" @default.
• W3021451168 hasPublicationYear "2020" @default.
• W3021451168 type Work @default.
• W3021451168 sameAs 3021451168 @default.
• W3021451168 citedByCount "6" @default.
• W3021451168 countsByYear W30214511682020 @default.
• W3021451168 countsByYear W30214511682021 @default.
• W3021451168 countsByYear W30214511682022 @default.
• W3021451168 countsByYear W30214511682023 @default.
• W3021451168 crossrefType "journal-article" @default.
• W3021451168 hasAuthorship W3021451168A5001989082 @default.
• W3021451168 hasAuthorship W3021451168A5013479932 @default.
• W3021451168 hasAuthorship W3021451168A5026139698 @default.
• W3021451168 hasAuthorship W3021451168A5031808267 @default.
• W3021451168 hasAuthorship W3021451168A5056002024 @default.
• W3021451168 hasAuthorship W3021451168A5081342676 @default.
• W3021451168 hasBestOaLocation W30214511681 @default.
• W3021451168 hasConcept C104317684 @default.
• W3021451168 hasConcept C11413529 @default.
• W3021451168 hasConcept C121332964 @default.
• W3021451168 hasConcept C152671427 @default.
• W3021451168 hasConcept C154945302 @default.
• W3021451168 hasConcept C158693339 @default.
• W3021451168 hasConcept C185592680 @default.
• W3021451168 hasConcept C187834632 @default.
• W3021451168 hasConcept C2781067378 @default.
• W3021451168 hasConcept C41008148 @default.
• W3021451168 hasConcept C41608201 @default.
• W3021451168 hasConcept C42355184 @default.
• W3021451168 hasConcept C55493867 @default.
• W3021451168 hasConcept C62520636 @default.
• W3021451168 hasConcept C63479239 @default.
• W3021451168 hasConcept C80444323 @default.
• W3021451168 hasConceptScore W3021451168C104317684 @default.
• W3021451168 hasConceptScore W3021451168C11413529 @default.
• W3021451168 hasConceptScore W3021451168C121332964 @default.
• W3021451168 hasConceptScore W3021451168C152671427 @default.
• W3021451168 hasConceptScore W3021451168C154945302 @default.
• W3021451168 hasConceptScore W3021451168C158693339 @default.
• W3021451168 hasConceptScore W3021451168C185592680 @default.
• W3021451168 hasConceptScore W3021451168C187834632 @default.
• W3021451168 hasConceptScore W3021451168C2781067378 @default.
• W3021451168 hasConceptScore W3021451168C41008148 @default.
• W3021451168 hasConceptScore W3021451168C41608201 @default.
• W3021451168 hasConceptScore W3021451168C42355184 @default.
• W3021451168 hasConceptScore W3021451168C55493867 @default.
• W3021451168 hasConceptScore W3021451168C62520636 @default.
• W3021451168 hasConceptScore W3021451168C63479239 @default.
• W3021451168 hasConceptScore W3021451168C80444323 @default.
• W3021451168 hasFunder F4320321001 @default.
• W3021451168 hasFunder F4320321921 @default.
• W3021451168 hasLocation W30214511681 @default.
• W3021451168 hasLocation W30214511682 @default.
• W3021451168 hasOpenAccess W3021451168 @default.
• W3021451168 hasPrimaryLocation W30214511681 @default.

• next