FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898046390> ?p ?o ?g. }

• W2898046390 abstract "One of the leading approaches to collaborative filtering is to use matrix factorization to discover a set of latent factors that explain the pattern of preferences. In this paper, we apply a resilient stochastic gradient descent approach that uses only the sign of the gradient, similar to the R-Prop algorithm in neural network training, to matrix factorization for collaborative filtering. We evaluate the performance of our approach on the MovieLens 1M dataset, and find that test set accuracy markedly improves compared to standard gradient descent. As a follow-up experiment, we apply clustering to the learned item-factor matrix in factor space, and attempt to manually characterize each cluster of movies." @default.
• W2898046390 created "2018-10-26" @default.
• W2898046390 creator A5038037619 @default.
• W2898046390 creator A5068380625 @default.
• W2898046390 creator A5079888480 @default.
• W2898046390 creator A5080571610 @default.
• W2898046390 date "2018-07-01" @default.
• W2898046390 modified "2023-09-25" @default.
• W2898046390 title "Matrix Factorization Based Collaborative Filtering With Resilient Stochastic Gradient Descent" @default.
• W2898046390 cites W1246381107 @default.
• W2898046390 cites W1566309885 @default.
• W2898046390 cites W1880262756 @default.
• W2898046390 cites W1971040550 @default.
• W2898046390 cites W1992270714 @default.
• W2898046390 cites W1994389483 @default.
• W2898046390 cites W2042281163 @default.
• W2898046390 cites W2049455633 @default.
• W2898046390 cites W2056760161 @default.
• W2898046390 cites W2085937320 @default.
• W2898046390 cites W2099866409 @default.
• W2898046390 cites W2100235918 @default.
• W2898046390 cites W2110325612 @default.
• W2898046390 cites W2123427850 @default.
• W2898046390 cites W2134023113 @default.
• W2898046390 cites W2136944193 @default.
• W2898046390 cites W2137245235 @default.
• W2898046390 cites W2143908786 @default.
• W2898046390 cites W2144359569 @default.
• W2898046390 cites W2147152072 @default.
• W2898046390 cites W2148125505 @default.
• W2898046390 cites W2151385136 @default.
• W2898046390 cites W2155106456 @default.
• W2898046390 cites W2159094788 @default.
• W2898046390 cites W2165949563 @default.
• W2898046390 cites W2169086952 @default.
• W2898046390 cites W2171960770 @default.
• W2898046390 cites W2172249709 @default.
• W2898046390 cites W2219888463 @default.
• W2898046390 cites W2278138779 @default.
• W2898046390 cites W2341865734 @default.
• W2898046390 cites W2463645429 @default.
• W2898046390 cites W281665770 @default.
• W2898046390 doi "https://doi.org/10.1109/ijcnn.2018.8489528" @default.
• W2898046390 hasPublicationYear "2018" @default.
• W2898046390 type Work @default.
• W2898046390 sameAs 2898046390 @default.
• W2898046390 citedByCount "1" @default.
• W2898046390 countsByYear W28980463902019 @default.
• W2898046390 crossrefType "proceedings-article" @default.
• W2898046390 hasAuthorship W2898046390A5038037619 @default.
• W2898046390 hasAuthorship W2898046390A5068380625 @default.
• W2898046390 hasAuthorship W2898046390A5079888480 @default.
• W2898046390 hasAuthorship W2898046390A5080571610 @default.
• W2898046390 hasConcept C106487976 @default.
• W2898046390 hasConcept C11413529 @default.
• W2898046390 hasConcept C119857082 @default.
• W2898046390 hasConcept C121332964 @default.
• W2898046390 hasConcept C152671427 @default.
• W2898046390 hasConcept C153180895 @default.
• W2898046390 hasConcept C153258448 @default.
• W2898046390 hasConcept C154945302 @default.
• W2898046390 hasConcept C158693339 @default.
• W2898046390 hasConcept C159985019 @default.
• W2898046390 hasConcept C177264268 @default.
• W2898046390 hasConcept C192562407 @default.
• W2898046390 hasConcept C199360897 @default.
• W2898046390 hasConcept C206688291 @default.
• W2898046390 hasConcept C21569690 @default.
• W2898046390 hasConcept C2776156558 @default.
• W2898046390 hasConcept C2781039887 @default.
• W2898046390 hasConcept C41008148 @default.
• W2898046390 hasConcept C42355184 @default.
• W2898046390 hasConcept C50644808 @default.
• W2898046390 hasConcept C557471498 @default.
• W2898046390 hasConcept C62520636 @default.
• W2898046390 hasConcept C73555534 @default.
• W2898046390 hasConceptScore W2898046390C106487976 @default.
• W2898046390 hasConceptScore W2898046390C11413529 @default.
• W2898046390 hasConceptScore W2898046390C119857082 @default.
• W2898046390 hasConceptScore W2898046390C121332964 @default.
• W2898046390 hasConceptScore W2898046390C152671427 @default.
• W2898046390 hasConceptScore W2898046390C153180895 @default.
• W2898046390 hasConceptScore W2898046390C153258448 @default.
• W2898046390 hasConceptScore W2898046390C154945302 @default.
• W2898046390 hasConceptScore W2898046390C158693339 @default.
• W2898046390 hasConceptScore W2898046390C159985019 @default.
• W2898046390 hasConceptScore W2898046390C177264268 @default.
• W2898046390 hasConceptScore W2898046390C192562407 @default.
• W2898046390 hasConceptScore W2898046390C199360897 @default.
• W2898046390 hasConceptScore W2898046390C206688291 @default.
• W2898046390 hasConceptScore W2898046390C21569690 @default.
• W2898046390 hasConceptScore W2898046390C2776156558 @default.
• W2898046390 hasConceptScore W2898046390C2781039887 @default.
• W2898046390 hasConceptScore W2898046390C41008148 @default.
• W2898046390 hasConceptScore W2898046390C42355184 @default.
• W2898046390 hasConceptScore W2898046390C50644808 @default.
• W2898046390 hasConceptScore W2898046390C557471498 @default.
• W2898046390 hasConceptScore W2898046390C62520636 @default.
• W2898046390 hasConceptScore W2898046390C73555534 @default.
• W2898046390 hasLocation W28980463901 @default.

• next