Matches in SemOpenAlex for { <https://semopenalex.org/work/W2906331105> ?p ?o ?g. }
- W2906331105 abstract "Recommender systems are used in most of nowadays applications. Providing real-time suggestions with high accuracy is considered as one of the most crucial challenges that face them. Matrix factorization (MF) is an effective technique for recommender systems as it improves the accuracy. Stochastic Gradient Descent (SGD) for MF is the most popular approach used to speed up MF. SGD is a sequential algorithm, which is not trivial to be parallelized, especially for large-scale problems. Recently, many researches have proposed parallel methods for parallelizing SGD. In this research, we propose GPU_MF_SGD, a novel GPU-based method for large-scale recommender systems. GPU_MF_SGD utilizes Graphics Processing Unit (GPU) resources by ensuring load balancing and linear scalability, and achieving coalesced access of global memory without preprocessing phase. Our method demonstrates 3.1X–5.4X speedup over the most state-of-the-art GPU method, CuMF_SGD." @default.
- W2906331105 created "2019-01-01" @default.
- W2906331105 creator A5003027550 @default.
- W2906331105 creator A5018185891 @default.
- W2906331105 creator A5073371122 @default.
- W2906331105 date "2018-12-27" @default.
- W2906331105 modified "2023-09-25" @default.
- W2906331105 title "GPU_MF_SGD: A Novel GPU-Based Stochastic Gradient Descent Method for Matrix Factorization" @default.
- W2906331105 cites W1582004751 @default.
- W2906331105 cites W1690919088 @default.
- W2906331105 cites W1749424093 @default.
- W2906331105 cites W1788418780 @default.
- W2906331105 cites W18599363 @default.
- W2906331105 cites W1912475167 @default.
- W2906331105 cites W1980147176 @default.
- W2906331105 cites W2009845549 @default.
- W2906331105 cites W2017899538 @default.
- W2906331105 cites W2020098476 @default.
- W2906331105 cites W2030551598 @default.
- W2906331105 cites W2054141820 @default.
- W2906331105 cites W2076246374 @default.
- W2906331105 cites W2078670469 @default.
- W2906331105 cites W2105953200 @default.
- W2906331105 cites W2108630796 @default.
- W2906331105 cites W2112856797 @default.
- W2906331105 cites W2121966774 @default.
- W2906331105 cites W2141561953 @default.
- W2906331105 cites W2142466236 @default.
- W2906331105 cites W2167675119 @default.
- W2906331105 cites W2199814763 @default.
- W2906331105 cites W2219345271 @default.
- W2906331105 cites W2219888463 @default.
- W2906331105 cites W2281927632 @default.
- W2906331105 cites W2293706247 @default.
- W2906331105 cites W2297086932 @default.
- W2906331105 cites W2487840540 @default.
- W2906331105 cites W2584355182 @default.
- W2906331105 cites W2587866992 @default.
- W2906331105 cites W2623801597 @default.
- W2906331105 cites W2642043218 @default.
- W2906331105 cites W2696534605 @default.
- W2906331105 cites W4206519735 @default.
- W2906331105 cites W966223104 @default.
- W2906331105 doi "https://doi.org/10.1007/978-3-030-03405-4_18" @default.
- W2906331105 hasPublicationYear "2018" @default.
- W2906331105 type Work @default.
- W2906331105 sameAs 2906331105 @default.
- W2906331105 citedByCount "0" @default.
- W2906331105 crossrefType "book-chapter" @default.
- W2906331105 hasAuthorship W2906331105A5003027550 @default.
- W2906331105 hasAuthorship W2906331105A5018185891 @default.
- W2906331105 hasAuthorship W2906331105A5073371122 @default.
- W2906331105 hasConcept C11413529 @default.
- W2906331105 hasConcept C119857082 @default.
- W2906331105 hasConcept C121332964 @default.
- W2906331105 hasConcept C121684516 @default.
- W2906331105 hasConcept C154945302 @default.
- W2906331105 hasConcept C158693339 @default.
- W2906331105 hasConcept C173608175 @default.
- W2906331105 hasConcept C187834632 @default.
- W2906331105 hasConcept C206688291 @default.
- W2906331105 hasConcept C21442007 @default.
- W2906331105 hasConcept C2778119891 @default.
- W2906331105 hasConcept C2779851693 @default.
- W2906331105 hasConcept C34736171 @default.
- W2906331105 hasConcept C41008148 @default.
- W2906331105 hasConcept C42355184 @default.
- W2906331105 hasConcept C48044578 @default.
- W2906331105 hasConcept C50630238 @default.
- W2906331105 hasConcept C50644808 @default.
- W2906331105 hasConcept C557471498 @default.
- W2906331105 hasConcept C62520636 @default.
- W2906331105 hasConcept C68339613 @default.
- W2906331105 hasConcept C77088390 @default.
- W2906331105 hasConceptScore W2906331105C11413529 @default.
- W2906331105 hasConceptScore W2906331105C119857082 @default.
- W2906331105 hasConceptScore W2906331105C121332964 @default.
- W2906331105 hasConceptScore W2906331105C121684516 @default.
- W2906331105 hasConceptScore W2906331105C154945302 @default.
- W2906331105 hasConceptScore W2906331105C158693339 @default.
- W2906331105 hasConceptScore W2906331105C173608175 @default.
- W2906331105 hasConceptScore W2906331105C187834632 @default.
- W2906331105 hasConceptScore W2906331105C206688291 @default.
- W2906331105 hasConceptScore W2906331105C21442007 @default.
- W2906331105 hasConceptScore W2906331105C2778119891 @default.
- W2906331105 hasConceptScore W2906331105C2779851693 @default.
- W2906331105 hasConceptScore W2906331105C34736171 @default.
- W2906331105 hasConceptScore W2906331105C41008148 @default.
- W2906331105 hasConceptScore W2906331105C42355184 @default.
- W2906331105 hasConceptScore W2906331105C48044578 @default.
- W2906331105 hasConceptScore W2906331105C50630238 @default.
- W2906331105 hasConceptScore W2906331105C50644808 @default.
- W2906331105 hasConceptScore W2906331105C557471498 @default.
- W2906331105 hasConceptScore W2906331105C62520636 @default.
- W2906331105 hasConceptScore W2906331105C68339613 @default.
- W2906331105 hasConceptScore W2906331105C77088390 @default.
- W2906331105 hasLocation W29063311051 @default.
- W2906331105 hasOpenAccess W2906331105 @default.
- W2906331105 hasPrimaryLocation W29063311051 @default.
- W2906331105 hasRelatedWork W2073991682 @default.