FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999649805> ?p ?o ?g. }

• W2999649805 endingPage "28" @default.
• W2999649805 startingPage "1" @default.
• W2999649805 abstract "Recommendation systems play a vital role to keep users engaged with personalized contents in modern online platforms. Recently, deep learning has revolutionized many research fields and there is a surge of interest in applying it for recommendation. However, existing studies have largely focused on exploring complex deep-learning architectures for recommendation task, while typically applying the negative sampling strategy for model learning. Despite effectiveness, we argue that these methods suffer from two important limitations: (1) the methods with complex network structures have a substantial number of parameters, and require expensive computations even with a sampling-based learning strategy; (2) the negative sampling strategy is not robust, making sampling-based methods difficult to achieve the optimal performance in practical applications. In this work, we propose to learn neural recommendation models from the whole training data without sampling. However, such a non-sampling strategy poses strong challenges to learning efficiency. To address this, we derive three new optimization methods through rigorous mathematical reasoning, which can efficiently learn model parameters from the whole data (including all missing data) with a rather low time complexity. Moreover, based on a simple Neural Matrix Factorization architecture, we present a general framework named ENMF, short for Efficient Neural Matrix Factorization . Extensive experiments on three real-world public datasets indicate that the proposed ENMF framework consistently and significantly outperforms the state-of-the-art methods on the Top-K recommendation task. Remarkably, ENMF also shows significant advantages in training efficiency, which makes it more applicable to real-world large-scale systems." @default.
• W2999649805 created "2020-01-23" @default.
• W2999649805 creator A5008168090 @default.
• W2999649805 creator A5019574552 @default.
• W2999649805 creator A5033642702 @default.
• W2999649805 creator A5053204257 @default.
• W2999649805 creator A5079263497 @default.
• W2999649805 date "2020-03-18" @default.
• W2999649805 modified "2023-10-15" @default.
• W2999649805 title "Efficient Neural Matrix Factorization without Sampling for Recommendation" @default.
• W2999649805 cites W1720514416 @default.
• W2999649805 cites W1857884451 @default.
• W2999649805 cites W1976999215 @default.
• W2999649805 cites W1994389483 @default.
• W2999649805 cites W2027731328 @default.
• W2999649805 cites W2040367556 @default.
• W2999649805 cites W2042281163 @default.
• W2999649805 cites W2063468305 @default.
• W2999649805 cites W2077927809 @default.
• W2999649805 cites W2080320419 @default.
• W2999649805 cites W2099866409 @default.
• W2999649805 cites W2101409192 @default.
• W2999649805 cites W2124187902 @default.
• W2999649805 cites W2150886314 @default.
• W2999649805 cites W2253995343 @default.
• W2999649805 cites W2295739661 @default.
• W2999649805 cites W2340502990 @default.
• W2999649805 cites W2512971201 @default.
• W2999649805 cites W2593507512 @default.
• W2999649805 cites W2605350416 @default.
• W2999649805 cites W2614794251 @default.
• W2999649805 cites W2741249238 @default.
• W2999649805 cites W2742272831 @default.
• W2999649805 cites W2783944588 @default.
• W2999649805 cites W2788376297 @default.
• W2999649805 cites W2798868970 @default.
• W2999649805 cites W2798908418 @default.
• W2999649805 cites W2798972759 @default.
• W2999649805 cites W2802187397 @default.
• W2999649805 cites W2808446163 @default.
• W2999649805 cites W2900229157 @default.
• W2999649805 cites W2901054662 @default.
• W2999649805 cites W2907827821 @default.
• W2999649805 cites W2914721378 @default.
• W2999649805 cites W2951369132 @default.
• W2999649805 cites W2954123367 @default.
• W2999649805 cites W2962712142 @default.
• W2999649805 cites W2963323306 @default.
• W2999649805 cites W2963921057 @default.
• W2999649805 cites W2973172293 @default.
• W2999649805 cites W3100278010 @default.
• W2999649805 cites W3100591234 @default.
• W2999649805 cites W3101023724 @default.
• W2999649805 cites W3101830194 @default.
• W2999649805 cites W3102560000 @default.
• W2999649805 cites W3105114834 @default.
• W2999649805 cites W4301312111 @default.
• W2999649805 doi "https://doi.org/10.1145/3373807" @default.
• W2999649805 hasPublicationYear "2020" @default.
• W2999649805 type Work @default.
• W2999649805 sameAs 2999649805 @default.
• W2999649805 citedByCount "75" @default.
• W2999649805 countsByYear W29996498052020 @default.
• W2999649805 countsByYear W29996498052021 @default.
• W2999649805 countsByYear W29996498052022 @default.
• W2999649805 countsByYear W29996498052023 @default.
• W2999649805 crossrefType "journal-article" @default.
• W2999649805 hasAuthorship W2999649805A5008168090 @default.
• W2999649805 hasAuthorship W2999649805A5019574552 @default.
• W2999649805 hasAuthorship W2999649805A5033642702 @default.
• W2999649805 hasAuthorship W2999649805A5053204257 @default.
• W2999649805 hasAuthorship W2999649805A5079263497 @default.
• W2999649805 hasBestOaLocation W29996498051 @default.
• W2999649805 hasConcept C106131492 @default.
• W2999649805 hasConcept C108583219 @default.
• W2999649805 hasConcept C119857082 @default.
• W2999649805 hasConcept C121332964 @default.
• W2999649805 hasConcept C124101348 @default.
• W2999649805 hasConcept C140779682 @default.
• W2999649805 hasConcept C154945302 @default.
• W2999649805 hasConcept C158693339 @default.
• W2999649805 hasConcept C162324750 @default.
• W2999649805 hasConcept C187736073 @default.
• W2999649805 hasConcept C2780451532 @default.
• W2999649805 hasConcept C31972630 @default.
• W2999649805 hasConcept C41008148 @default.
• W2999649805 hasConcept C42355184 @default.
• W2999649805 hasConcept C50644808 @default.
• W2999649805 hasConcept C557471498 @default.
• W2999649805 hasConcept C62520636 @default.
• W2999649805 hasConceptScore W2999649805C106131492 @default.
• W2999649805 hasConceptScore W2999649805C108583219 @default.
• W2999649805 hasConceptScore W2999649805C119857082 @default.
• W2999649805 hasConceptScore W2999649805C121332964 @default.
• W2999649805 hasConceptScore W2999649805C124101348 @default.
• W2999649805 hasConceptScore W2999649805C140779682 @default.
• W2999649805 hasConceptScore W2999649805C154945302 @default.
• W2999649805 hasConceptScore W2999649805C158693339 @default.

• next