{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T18:29:46Z","timestamp":1714156186863},"reference-count":25,"publisher":"IGI Global","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"abstract":"<jats:p>In numerous solutions, the distributed stochastic gradient descent algorithm is one of the most popular algorithms for parallelization matrix decomposition. However, in parallel calculation, the computing speed of each computing node was greatly different because of the imbalance of the computing nodes. This article reduced the data skew for all computing nodes during distributed execution to solve the problem of locking waiting. The improved algorithm on DSGD was named D-DSGD, which reduced the time consumption of the algorithm and improved the utilization rate of the nodes. Meanwhile, the dynamic step size adjusting strategy was applied to improve the convergence rate of the algorithm. To ensure the non-negative matrix decomposition, non-negative control was added into D-DSGD and the improved algorithm was named D-NMF. Compared with the existing methods, the proposed algorithm in this article has a marked impact on reducing the latency and speed of convergence.<\/jats:p>","DOI":"10.4018\/ijdst.2018070102","type":"journal-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T15:32:48Z","timestamp":1528731168000},"page":"24-38","source":"Crossref","is-referenced-by-count":1,"title":["A Fast Distributed Non-Negative Matrix Factorization Algorithm Based on DSGD"],"prefix":"10.4018","volume":"9","author":[{"given":"Yan","family":"Gao","sequence":"first","affiliation":[{"name":"Central South University, Changsha, China"}]},{"given":"Lingjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]},{"given":"Baifan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Central South University, Changsha, China"}]},{"given":"Xiaobing","family":"Xing","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]}],"member":"2432","reference":[{"key":"IJDST.2018070102-0","doi-asserted-by":"publisher","DOI":"10.2478\/cait-2014-0031"},{"key":"IJDST.2018070102-1","doi-asserted-by":"publisher","DOI":"10.1145\/3015144"},{"key":"IJDST.2018070102-2","doi-asserted-by":"crossref","unstructured":"Bottou, L. (2010). Large-scale machine learning with stochastic gradient descent.","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"IJDST.2018070102-3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2356470"},{"key":"IJDST.2018070102-4","unstructured":"Chu, M., Diele, F., Plemmons, R., & Ragni, S. (2004). Optimality, computation, and interpretation of nonnegative matrix factorizations."},{"key":"IJDST.2018070102-5","unstructured":"Dabney, W. C. (2014). Adaptive step-sizes for reinforcement learning."},{"key":"IJDST.2018070102-6","first-page":"10","article-title":"MapReduce: simplified data processing on large clusters.","volume":"Vol. 51","author":"J.Dean","year":"2010","journal-title":"Conference on Symposium on Operating Systems Design & Implementation"},{"key":"IJDST.2018070102-7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31454-4_6"},{"key":"IJDST.2018070102-8","unstructured":"Dror, G., Koenigstein, N., Koren, Y., & Weimer, M. (2011). The Yahoo! Music Dataset and KDD-Cup'11. In International Conference on Kdd Cup (Vol.18, pp.3-18), JMLR.org."},{"key":"IJDST.2018070102-9","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020426"},{"key":"IJDST.2018070102-10","doi-asserted-by":"crossref","unstructured":"Hsieh, ChoJui, Dhillon, & Inderjit, S. (2011). Fast coordinate descent methods with variable selection for non-negative matrix factorization.","DOI":"10.1145\/2020408.2020577"},{"key":"IJDST.2018070102-11","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"IJDST.2018070102-12","first-page":"535","article-title":"Algorithms for non-negative matrix factorization.","volume":"Vol. 32","author":"D.Lee","year":"2000","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"IJDST.2018070102-13","first-page":"77","article-title":"A fast distributed stochastic gradient descent algorithm for matrix factorization.","author":"F.Li","year":"2014","journal-title":"Proceedings of the 3rd International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications"},{"key":"IJDST.2018070102-14","doi-asserted-by":"publisher","DOI":"10.1016\/j.gpb.2013.06.001"},{"key":"IJDST.2018070102-15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.07.150"},{"key":"IJDST.2018070102-16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.11.099"},{"key":"IJDST.2018070102-17","first-page":"693","article-title":"Hogwild!: A lock-free approach to parallelizing stochastic gradient descent.","volume":"24","author":"F.Niu","year":"2011","journal-title":"Advances in Neural Information Processing Systems"},{"key":"IJDST.2018070102-18","unstructured":"Rajkumar, A., & Agarwal, S. (2012). A differentially private stochastic gradient descent algorithm for multiparty classification."},{"key":"IJDST.2018070102-19","first-page":"81","article-title":"Weighted Frequent Pattern Mining using RDD, the Basic Spark Abstraction.","author":"R.Visakh","year":"2014","journal-title":"International Conference on Information and Communication Technology for Competitive Strategies"},{"key":"IJDST.2018070102-20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44845-8_22"},{"key":"IJDST.2018070102-21","first-page":"765","article-title":"Scalable Coordinate Descent Approaches to Parallel Matrix Factorization for Recommender Systems. In","volume":"Vol. 41","author":"H.Yu","year":"2012","journal-title":"International Conference on Data Mining"},{"key":"IJDST.2018070102-22","first-page":"1278","article-title":"Text Clustering via Constrained Nonnegative Matrix Factorization. In","author":"Y.Zhu","year":"2011","journal-title":"International Conference on Data Mining"},{"key":"IJDST.2018070102-23","doi-asserted-by":"publisher","DOI":"10.1145\/2507157.2507164"},{"key":"IJDST.2018070102-24","unstructured":"Zinkevich, M., Weimer, M., Smola, A. J., & Li, L. (2010). Parallelized Stochastic Gradient Descent. Advances in Neural Information Processing Systems 23: Conference on Neural Information Processing Systems 2010. Proceedings of A Meeting Held 6-9 December 2010, Vancouver, British Columbia, Canada (Vol.23, pp.2595-2603). DBLP."}],"container-title":["International Journal of Distributed Systems and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=207690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T00:10:21Z","timestamp":1651795821000},"score":1,"resource":{"primary":{"URL":"http:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJDST.2018070102"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":25,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.4018\/ijdst.2018070102","relation":{},"ISSN":["1947-3532","1947-3540"],"issn-type":[{"value":"1947-3532","type":"print"},{"value":"1947-3540","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}