A Fast Parallel Stochastic Gradient Method for Matrix Factorization in Shared Memory Systems

被引：73

作者：

Chin, Wei-Sheng ^{[1
]}

Zhuang, Yong ^{[1
]}

Juan, Yu-Chin ^{[1
]}

Lin, Chih-Jen ^{[1
]}

机构：

[1] Natl Taiwan Univ, Dept Comp Sci, Taipei, Taiwan

来源：

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY | 2015年 / 6卷 / 01期

关键词：

Parallel and Vector Implementations; Recommender system; matrix factorization; stochastic gradient descent; parallel computing; shared memory algorithm;

D O I：

10.1145/2668133

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Matrix factorization is known to be an effective method for recommender systems that are given only the ratings from users to items. Currently, stochastic gradient (SG) method is one of the most popular algorithms for matrix factorization. However, as a sequential approach, SG is difficult to be parallelized for handling web-scale problems. In this article, we develop a fast parallel SG method, FPSG, for shared memory systems. By dramatically reducing the cache-miss rate and carefully addressing the load balance of threads, FPSG is more efficient than state-of-the-art parallel algorithms for matrix factorization.

引用

页数：24

共 50 条

[1] LIBMF: A Library for Parallel Matrix Factorization in Shared-memory Systems
Chin, Wei-Sheng
Yuan, Bo-Wen
Yang, Meng-Yuan
Zhuang, Yong
Juan, Yu-Chin
Lin, Chih-Jen
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2016, 17
[2] High Performance Parallel Stochastic Gradient Descent in Shared Memory
Sallinen, Scott
Satish, Nadathur
Smelyanskiy, Mikhail
Sury, Samantika S.
Re, Christopher
[J]. 2016 IEEE 30TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2016), 2016, : 873 - 882
[3] A parallel matrix factorization based recommender by alternating stochastic gradient decent
Luo, Xin
Liu, Huijun
Gou, Gaopeng
Xia, Yunni
Zhu, Qingsheng
[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2012, 25 (07) : 1403 - 1412
[4] Efficient Parallel Stochastic Gradient Descent for Matrix Factorization Using GPU
Nassar, Mohamed A.
El-Sayed, Layla A. A.
Taha, Yousry
[J]. 2016 11TH INTERNATIONAL CONFERENCE FOR INTERNET TECHNOLOGY AND SECURED TRANSACTIONS (ICITST), 2016, : 63 - 68
[5] Parallelizing Stochastic Gradient Descent with Hardware Transactional Memory for Matrix Factorization
Wu, Zhenwei
Luo, Yingqi
Lu, Kai
Wang, Xiaoping
[J]. 2018 3RD INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS ENGINEERING (ICISE), 2018, : 118 - 121
[6] Limited-Memory Fast Gradient Descent Method for Graph Regularized Nonnegative Matrix Factorization
Guan, Naiyang
Wei, Lei
Luo, Zhigang
Tao, Dacheng
[J]. PLOS ONE, 2013, 8 (10):
[7] A Fast Parallel Particle Filter for Shared Memory Systems
Varsi, Alessandro
Taylor, Jack
Kekempanos, Lykourgos
Pyzer Knapp, Edward
Maskell, Simon
[J]. IEEE SIGNAL PROCESSING LETTERS, 2020, 27 : 1570 - 1574
[8] Fast brain tumor detection using adaptive stochastic gradient descent on shared-memory parallel environment
Qin, Chuandong
Li, Baosheng
Han, Baole
[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 120
[9] PARALLEL GIVENS FACTORIZATION ON A SHARED MEMORY MULTIPROCESSOR
DAOUDI, E
LIBERT, G
[J]. LECTURE NOTES IN COMPUTER SCIENCE, 1990, 457 : 131 - 142
[10] Stochastic Gradient Descent for matrix completion: Hybrid parallelization on shared- and distributed-memory systems
Buyukkaya, Kemal
Karsavuran, M. Ozan
Aykanat, Cevdet
[J]. KNOWLEDGE-BASED SYSTEMS, 2024, 283

← 1 2 3 4 5 →