GPUSGD: A GPU‐accelerated stochastic gradient descent algorithm for matrix factorization. (18th December 2015)

• Record Type: Journal Article
• Authors: Jin, Jing; Lai, Siyan; Hu, Su; Lin, Jing; Lin, Xiaola
• Other Names: Higuera‐Toledano M. Teresa guestEditor.; Brinkschulte Uwe guestEditor.; Rettberg Achim guestEditor.; Qiang Weizhong guestEditor.; Zheng Xianghan guestEditor.; Hsu Ching‐Hsien guestEditor.
• Is Part Of: Concurrency and computation. Volume 28:Number 14(2016)
• Page Start: 3844
• Page End: 3865
• Publication Date: 2015-12-18
• Subjects: parallel matrix factorization -- GPU computing -- over‐writing problem -- thread divergence -- stochastic gradient descent; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.3722
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Matrix factorization is one of the leading techniques for many applications such as social network‐based recommendation systems. As of today, many parallel stochastic gradient descent (SGD) methods have been proposed to address the matrix factorization issue on shared‐memory (multi‐core) systems and distributed systems. However, these methods cannot be improved significantly on graphics processing unit (GPU) because the serious over‐writing problem and thread divergence may occur. The fundamental reason for such undesired results is that GPU is a parallel single instruction multiple data device, which only can greatly improve the applications with fine‐grained parallelism. In this paper, we propose an efficient GPU algorithm, named GPUSGD, to solve the matrix factorization problem based on SGD method. The major advantage of the proposed GPUSGD is that such method not only can handle the over‐writing problem but also can avoid the performance loss caused by the thread divergence. The experimental results show that GPUSGD performs much better in accelerating the matrix factorization compared with the existing state‐of‐the‐art parallel methods. To the best of our knowledge, this is the first work that develops a parallel SGD method to improve the matrix factorization on GPU. Copyright © 2015 John Wiley & Sons, Ltd.