Application of randomized low-rank approximation algorithm in recommendation system

CHEN Xi; DENG Jiechen; XI Shihong; LIU Xiaochen; ZHANG Xiangjun; FENG Yuehua

Volume 35 Issue 3

Sep. 2021

Turn off MathJax

Article Contents

Article Navigation > Journal of Shanghai University of Engineering Science > 2021 > 35(3): 281-284

CHEN Xi, DENG Jiechen, XI Shihong, LIU Xiaochen, ZHANG Xiangjun, FENG Yuehua. Application of randomized low-rank approximation algorithm in recommendation system[J]. Journal of Shanghai University of Engineering Science, 2021, 35(3): 281-284.

Citation:

CHEN Xi, DENG Jiechen, XI Shihong, LIU Xiaochen, ZHANG Xiangjun, FENG Yuehua. Application of randomized low-rank approximation algorithm in recommendation system[J]. Journal of Shanghai University of Engineering Science, 2021, 35(3): 281-284.

Citation:

PDF( 690 KB)

Application of randomized low-rank approximation algorithm in recommendation system

a.
School of Mechanical and Automotive Engineering
b.
School of Air Transportation and School of Flying
c.
School of Mathematics, Physics and Statistics, Shanghai University of Engineering Science, Shanghai 201620, China

Received Date: 2021-03-06
Publish Date: 2021-09-30

Abstract

Abstract

In view of the problem that with increasing large amount of datas in a recommendation system, the computing efficiency of its corresponding matrix completion algorithms need to be improved. Based on randomized algorithm strategy and efficient data access requirements, a new algorithm for solving matrix completion problem was proposed, and the Matlab software was employed to realize the algorithm. The numerical experiment result shows that the new algorithm can speed up the computing efficiency of original one by about 30%.
- singular value decomposition (SVD),
- randomized algorithm,
- low-rank approximation,
- recommendation system

FullText(HTML)

References(8)

References

[1]	王越, 程昌正. 协同过滤算法在电影推荐中的应用[J] . 兵器装备工程学报,2014(5):86 − 88.
[2]	王元涛. Netflix数据集上的协同过滤算法[D]. 北京: 清华大学, 2009.
[3]	冯栩, 李可欣, 喻文健, 等. 基于随机奇异值分解的快速矩阵补全算法及其应用[J] . 计算机辅助设计与图形学学报,2017(12):2343 − 2348.
[4]	FENG Y H, XIAO J W, GU M. Flip-flop spectrum-revealing QR Factorization and its applications on singular value decomposition[J] . Electronic Transactions on Numerical Analysis,2019,51:469 − 494.
[5]	LARSEN R M. Lanczos bidiagonalization with partial reorthogonalization[J] . DAIMI Report Series,1999,27(537):1 − 101. doi: 10.7146/dpb.v27i537.7070
[6]	DRINEAS P, KANNAN R, MAHONEY M W. Fast Monte Carlo algorithms for matrices II: computing a low-rank approximation to a matrix[J] . SIAM Journal on Computing,2006,36(1):158 − 183. doi: 10.1137/S0097539704442696
[7]	TROPP J A, YURTSEVER A, UDELL M, et al. Practical sketching algorithms for low-rank matrix approximation[J] . SIAM Journal on Matrix Analysis and Applications,2017,38(4):1454 − 1485. doi: 10.1137/17M1111590
[8]	LIN Z C, CHEN M M, MA Y. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices[EB/OL]. (2013-10-18)[2021-01-18]. http://arxiv.org/pdf/1009.5055v3.pdf.