Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100848837> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3100848837 abstract "Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge. Here we describe a large-scale deep recommendation engine that we developed and deployed at Pinterest. We develop a data-efficient Graph Convolutional Network (GCN) algorithm PinSage, which combines efficient random walks and graph convolutions to generate embeddings of nodes (i.e., items) that incorporate both graph structure as well as node feature information. Compared to prior GCN approaches, we develop a novel method based on highly efficient random walks to structure the convolutions and design a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model. We also develop an efficient MapReduce model inference algorithm to generate embeddings using a trained model. We deploy PinSage at Pinterest and train it on 7.5 billion examples on a graph with 3 billion nodes representing pins and boards, and 18 billion edges. According to offline metrics, user studies and A/B tests, PinSage generates higher-quality recommendations than comparable deep learning and graph-based alternatives. To our knowledge, this is the largest application of deep graph embeddings to date and paves the way for a new generation of web-scale recommender systems based on graph convolutional architectures." @default.
- W3100848837 created "2020-11-23" @default.
- W3100848837 creator A5004542284 @default.
- W3100848837 creator A5017763101 @default.
- W3100848837 creator A5046766246 @default.
- W3100848837 creator A5046787262 @default.
- W3100848837 creator A5078337825 @default.
- W3100848837 creator A5091272738 @default.
- W3100848837 date "2018-07-19" @default.
- W3100848837 modified "2023-10-18" @default.
- W3100848837 title "Graph Convolutional Neural Networks for Web-Scale Recommender Systems" @default.
- W3100848837 cites W2116341502 @default.
- W3100848837 cites W2145065594 @default.
- W3100848837 cites W2154610494 @default.
- W3100848837 cites W2296073425 @default.
- W3100848837 cites W2510317721 @default.
- W3100848837 cites W2512971201 @default.
- W3100848837 cites W2558748708 @default.
- W3100848837 cites W2950277699 @default.
- W3100848837 cites W2962756421 @default.
- W3100848837 cites W2963921057 @default.
- W3100848837 cites W3104097132 @default.
- W3100848837 doi "https://doi.org/10.1145/3219819.3219890" @default.
- W3100848837 hasPublicationYear "2018" @default.
- W3100848837 type Work @default.
- W3100848837 sameAs 3100848837 @default.
- W3100848837 citedByCount "1971" @default.
- W3100848837 countsByYear W31008488372017 @default.
- W3100848837 countsByYear W31008488372018 @default.
- W3100848837 countsByYear W31008488372019 @default.
- W3100848837 countsByYear W31008488372020 @default.
- W3100848837 countsByYear W31008488372021 @default.
- W3100848837 countsByYear W31008488372022 @default.
- W3100848837 countsByYear W31008488372023 @default.
- W3100848837 crossrefType "proceedings-article" @default.
- W3100848837 hasAuthorship W3100848837A5004542284 @default.
- W3100848837 hasAuthorship W3100848837A5017763101 @default.
- W3100848837 hasAuthorship W3100848837A5046766246 @default.
- W3100848837 hasAuthorship W3100848837A5046787262 @default.
- W3100848837 hasAuthorship W3100848837A5078337825 @default.
- W3100848837 hasAuthorship W3100848837A5091272738 @default.
- W3100848837 hasBestOaLocation W31008488372 @default.
- W3100848837 hasConcept C104317684 @default.
- W3100848837 hasConcept C108583219 @default.
- W3100848837 hasConcept C119857082 @default.
- W3100848837 hasConcept C132525143 @default.
- W3100848837 hasConcept C154945302 @default.
- W3100848837 hasConcept C176225458 @default.
- W3100848837 hasConcept C185592680 @default.
- W3100848837 hasConcept C2776214188 @default.
- W3100848837 hasConcept C41008148 @default.
- W3100848837 hasConcept C48044578 @default.
- W3100848837 hasConcept C55493867 @default.
- W3100848837 hasConcept C557471498 @default.
- W3100848837 hasConcept C63479239 @default.
- W3100848837 hasConcept C77088390 @default.
- W3100848837 hasConcept C80444323 @default.
- W3100848837 hasConcept C81363708 @default.
- W3100848837 hasConceptScore W3100848837C104317684 @default.
- W3100848837 hasConceptScore W3100848837C108583219 @default.
- W3100848837 hasConceptScore W3100848837C119857082 @default.
- W3100848837 hasConceptScore W3100848837C132525143 @default.
- W3100848837 hasConceptScore W3100848837C154945302 @default.
- W3100848837 hasConceptScore W3100848837C176225458 @default.
- W3100848837 hasConceptScore W3100848837C185592680 @default.
- W3100848837 hasConceptScore W3100848837C2776214188 @default.
- W3100848837 hasConceptScore W3100848837C41008148 @default.
- W3100848837 hasConceptScore W3100848837C48044578 @default.
- W3100848837 hasConceptScore W3100848837C55493867 @default.
- W3100848837 hasConceptScore W3100848837C557471498 @default.
- W3100848837 hasConceptScore W3100848837C63479239 @default.
- W3100848837 hasConceptScore W3100848837C77088390 @default.
- W3100848837 hasConceptScore W3100848837C80444323 @default.
- W3100848837 hasConceptScore W3100848837C81363708 @default.
- W3100848837 hasLocation W31008488371 @default.
- W3100848837 hasLocation W31008488372 @default.
- W3100848837 hasLocation W31008488373 @default.
- W3100848837 hasOpenAccess W3100848837 @default.
- W3100848837 hasPrimaryLocation W31008488371 @default.
- W3100848837 hasRelatedWork W2731899572 @default.
- W3100848837 hasRelatedWork W2999805992 @default.
- W3100848837 hasRelatedWork W3116150086 @default.
- W3100848837 hasRelatedWork W3133861977 @default.
- W3100848837 hasRelatedWork W4200173597 @default.
- W3100848837 hasRelatedWork W4223943233 @default.
- W3100848837 hasRelatedWork W4291897433 @default.
- W3100848837 hasRelatedWork W4312417841 @default.
- W3100848837 hasRelatedWork W4321369474 @default.
- W3100848837 hasRelatedWork W4380075502 @default.
- W3100848837 isParatext "false" @default.
- W3100848837 isRetracted "false" @default.
- W3100848837 magId "3100848837" @default.
- W3100848837 workType "article" @default.