FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216490117> ?p ?o ?g. }

• W3216490117 abstract "Transformers have achieved great success in several domains, including Natural Language Processing and Computer Vision. However, its application to real-world graphs is less explored, mainly due to its high computation cost and its poor generalizability caused by the lack of enough training data in the graph domain. To fill in this gap, we propose a scalable Transformer-like dynamic graph learning method named Dynamic Graph Transformer (DyFormer) with spatial-temporal encoding to effectively learn graph topology and capture implicit links. To achieve efficient and scalable training, we propose temporal-union graph structure and its associated subgraph-based node sampling strategy. To improve the generalization ability, we introduce two complementary self-supervised pre-training tasks and show that jointly optimizing the two pre-training tasks results in a smaller Bayesian error rate via an information-theoretic analysis. Extensive experiments on the real-world datasets illustrate that DyFormer achieves a consistent 1%-3% AUC gain (averaged over all time steps) compared with baselines on all benchmarks." @default.
• W3216490117 created "2021-12-06" @default.
• W3216490117 creator A5021924764 @default.
• W3216490117 creator A5052933431 @default.
• W3216490117 creator A5061989398 @default.
• W3216490117 creator A5063658433 @default.
• W3216490117 creator A5076083402 @default.
• W3216490117 creator A5084821923 @default.
• W3216490117 creator A5087035301 @default.
• W3216490117 date "2021-11-19" @default.
• W3216490117 modified "2023-10-18" @default.
• W3216490117 title "DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability" @default.
• W3216490117 cites W2086254934 @default.
• W3216490117 cites W2099294566 @default.
• W3216490117 cites W2565330852 @default.
• W3216490117 cites W2624407581 @default.
• W3216490117 cites W2806983170 @default.
• W3216490117 cites W2945623882 @default.
• W3216490117 cites W2954691982 @default.
• W3216490117 cites W2962756421 @default.
• W3216490117 cites W2962767366 @default.
• W3216490117 cites W2963341956 @default.
• W3216490117 cites W2963396480 @default.
• W3216490117 cites W2963403868 @default.
• W3216490117 cites W2963791934 @default.
• W3216490117 cites W2963911286 @default.
• W3216490117 cites W2964015378 @default.
• W3216490117 cites W2964113829 @default.
• W3216490117 cites W2964321699 @default.
• W3216490117 cites W2970066309 @default.
• W3216490117 cites W2995533131 @default.
• W3216490117 cites W2996028985 @default.
• W3216490117 cites W2996451395 @default.
• W3216490117 cites W2998313947 @default.
• W3216490117 cites W3000577518 @default.
• W3216490117 cites W3012871709 @default.
• W3216490117 cites W3033529678 @default.
• W3216490117 cites W3036685317 @default.
• W3216490117 cites W3080902222 @default.
• W3216490117 cites W3094502228 @default.
• W3216490117 cites W3098903812 @default.
• W3216490117 cites W3100848837 @default.
• W3216490117 cites W3104613728 @default.
• W3216490117 cites W3107668149 @default.
• W3216490117 cites W3113177135 @default.
• W3216490117 cites W3126816608 @default.
• W3216490117 cites W3131573008 @default.
• W3216490117 cites W3133222630 @default.
• W3216490117 cites W3138516171 @default.
• W3216490117 cites W3169622372 @default.
• W3216490117 cites W2906407596 @default.
• W3216490117 doi "https://doi.org/10.48550/arxiv.2111.10447" @default.
• W3216490117 hasPublicationYear "2021" @default.
• W3216490117 type Work @default.
• W3216490117 sameAs 3216490117 @default.
• W3216490117 citedByCount "0" @default.
• W3216490117 crossrefType "posted-content" @default.
• W3216490117 hasAuthorship W3216490117A5021924764 @default.
• W3216490117 hasAuthorship W3216490117A5052933431 @default.
• W3216490117 hasAuthorship W3216490117A5061989398 @default.
• W3216490117 hasAuthorship W3216490117A5063658433 @default.
• W3216490117 hasAuthorship W3216490117A5076083402 @default.
• W3216490117 hasAuthorship W3216490117A5084821923 @default.
• W3216490117 hasAuthorship W3216490117A5087035301 @default.
• W3216490117 hasBestOaLocation W32164901171 @default.
• W3216490117 hasConcept C105795698 @default.
• W3216490117 hasConcept C11413529 @default.
• W3216490117 hasConcept C119857082 @default.
• W3216490117 hasConcept C121332964 @default.
• W3216490117 hasConcept C124101348 @default.
• W3216490117 hasConcept C132525143 @default.
• W3216490117 hasConcept C154945302 @default.
• W3216490117 hasConcept C165801399 @default.
• W3216490117 hasConcept C27158222 @default.
• W3216490117 hasConcept C33923547 @default.
• W3216490117 hasConcept C41008148 @default.
• W3216490117 hasConcept C45374587 @default.
• W3216490117 hasConcept C48044578 @default.
• W3216490117 hasConcept C62520636 @default.
• W3216490117 hasConcept C66322947 @default.
• W3216490117 hasConcept C77088390 @default.
• W3216490117 hasConcept C80444323 @default.
• W3216490117 hasConceptScore W3216490117C105795698 @default.
• W3216490117 hasConceptScore W3216490117C11413529 @default.
• W3216490117 hasConceptScore W3216490117C119857082 @default.
• W3216490117 hasConceptScore W3216490117C121332964 @default.
• W3216490117 hasConceptScore W3216490117C124101348 @default.
• W3216490117 hasConceptScore W3216490117C132525143 @default.
• W3216490117 hasConceptScore W3216490117C154945302 @default.
• W3216490117 hasConceptScore W3216490117C165801399 @default.
• W3216490117 hasConceptScore W3216490117C27158222 @default.
• W3216490117 hasConceptScore W3216490117C33923547 @default.
• W3216490117 hasConceptScore W3216490117C41008148 @default.
• W3216490117 hasConceptScore W3216490117C45374587 @default.
• W3216490117 hasConceptScore W3216490117C48044578 @default.
• W3216490117 hasConceptScore W3216490117C62520636 @default.
• W3216490117 hasConceptScore W3216490117C66322947 @default.
• W3216490117 hasConceptScore W3216490117C77088390 @default.
• W3216490117 hasConceptScore W3216490117C80444323 @default.
• W3216490117 hasLocation W32164901171 @default.

• next