期刊
NEUROCOMPUTING
卷 367, 期 -, 页码 299-307出版社
ELSEVIER
DOI: 10.1016/j.neucom.2019.08.026
关键词
Big Data; QoS prediction; Temporal-aware QoS prediction; Stochastic gradient descent; Latent factorization of tensors; Momentum method
资金
- National Natural Science Foundation of China [61772493, 91646114, 51609229, 61872065]
- Chongqing Cultivation Program of Innovation and Entrepreneurship Demonstration Group [cstc2017kjrc-cxcytd0149]
- Chongqing Overseas Scholars Innovation Program [cx2017012, cx2018011]
- Chongqing Research Program of Technology Innovation and Application [cstc2017rgzn-zdyfX0020, cstc2017zdcy-zdyf0554, cstc2017rgzn-zdyf0118]
- Pioneer Hundred Talents Program of Chinese Academy of Sciences [CAS-PHP-CIGIT-001]
Quality-of-service (QoS) of Web services vary over time, making it a significant issue to discover temporal patterns from them for addressing various subsequent analyzing tasks like missing QoS prediction. A Latent factorization of tensors (LFT)-based approach proves to be highly efficient in addressing this issue, which can be built through a stochastic gradient descent (SGD) solver efficiently. However, an SGD-based LFT model frequently suffers low-tail convergence. For addressing this issue, we present a momentum-incorporated latent factorization of tensors (MLFT) model, which integrates a momentum method into an SGD-based LFT model, thereby improving its convergence rate as well as maintaining the prediction accuracy for missing QoS data. Empirical studies on two dynamic industrial QoS datasets show that compared with an SGD-based LFT model, an MLFT model achieves faster convergence rate and higher prediction accuracy. (C) 2019 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据