Design of normalized fractional SGD computing paradigm for recommender systems
| Autor: | Muhammad Asif Zahoor Raja, Naveed Ishtiaq Chaudhary, Nebojsa Dedovic, Syed M. Zubair, Zeshan Aslam Khan, Farrukh Aslam Khan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer Science::Machine Learning
0209 industrial biotechnology Mean squared error Computer science 02 engineering and technology Recommender system Matrix decomposition Nonlinear system 020901 industrial engineering & automation Stochastic gradient descent Artificial Intelligence Metric (mathematics) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Algorithm Software |
| Zdroj: | Neural Computing and Applications. 32:10245-10262 |
| ISSN: | 1433-3058 0941-0643 |
| DOI: | 10.1007/s00521-019-04562-6 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink