Please use this identifier to cite or link to this item: https://open.uns.ac.rs/handle/123456789/9839
Title: Design of normalized fractional SGD computing paradigm for recommender systems
Authors: Khan Z.
Zubair S.
Chaudhary N.
Raja M.
Khan F.
Dedović, Nebojša 
Issue Date: 1-Jan-2019
Journal: Neural Computing and Applications
Abstract: © 2019, Springer-Verlag London Ltd., part of Springer Nature. Fast and effective recommender systems are fundamental to fulfill the growing requirements of the e-commerce industry. The strength of matrix factorization procedure based on stochastic gradient descent (SGD) algorithm is exploited widely to solve the recommender system problem. Modern computing paradigms are designed by utilizing the concept of fractional gradient in standard SGD and outperform the standard counterpart. The performance of fractional SGD improves considerably by adaptively tuning the learning rate parameter. A nonlinear computing paradigm based on normalized version of fractional SGD is developed in this paper to investigate the adaptive behavior of learning rate with novel application to recommender systems. The accuracy of the proposed approach is verified through root mean square error metric by using different latent features, learning rates, fractional orders and datasets. The superiority of the designed method is validated through comparison with the state-of-the-art counterparts.
URI: https://open.uns.ac.rs/handle/123456789/9839
ISSN: 09410643
DOI: 10.1007/s00521-019-04562-6
Appears in Collections:POLJF Publikacije/Publications

Show full item record

SCOPUSTM   
Citations

14
checked on Sep 9, 2023

Page view(s)

29
Last Week
13
Last month
0
checked on May 10, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.