A sharing data approach oriented to distributed online learning

被引：0
|
作者：
Zhang Y. [1 ,2 ]
Liu W. [1 ]
Shao L.-S. [2 ]
机构：
[1] College of Science, Liaoning Technical University, Fuxin
[2] Research Centre in Management Science, Liaoning Technical University, Huludao
来源：
Kongzhi yu Juece/Control and Decision | 2021年 / 36卷 / 08期
关键词：
Distributed data stream; Global learner; Online learning; Rebuilding data set; Semi-supervised clustering; Sharing data;
D O I：
10.13195/j.kzyjc.2019.1811
中图分类号：
学科分类号：
摘要：
Distributed data stream generated by current data-driven applications has become a main data representation. Although distributed data stream is captured from different data sources, they are correlated to a common event. Hence, the key issue of distributed online learning is how to build global learners by sharing data of local node. For this problem, this paper proposes a sharing data solution for distributed online learning, containing the semi-supervised clustering approach based on exponential loss and the sharing data approach based on covariance matrixes and mean vectors, and proves the cumulative absolute error between the rebuilding data set and the original data set is bounded on the given threshold under some probability. Experimental study demonstrates that the proposed approach has lower network traffic between nodes, and gets the learner having better generalization capability. Copyright ©2021 Control and Decision.
引用
收藏
页码：1871 / 1880
页数：9
相关论文
共 35 条
  • [1] Domingos P, Hulten G., Mining high-speed data streams, Proceedings of the 6th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 71-80, (2000)
  • [2] Widmer G, Kubat M., Learning in the presence of concept drift and hidden contexts, Machine Learning, 23, 1, pp. 69-101, (1996)
  • [3] Masud M M, Chen Q, Khan L, Et al., Addressing concept-evolution in concept-drifting data streams, IEEE International Conference on Data Mining, pp. 14-17, (2010)
  • [4] Minku White A P L L, Yao X., The impact of diversity on online ensemble learning in the presence of concept drift, IEEE Transactions on Knowledge and Data Engineering, 22, 5, pp. 730-742, (2010)
  • [5] Masud M M, Chen Q, Khan L, Et al., Classification and adaptive novel class detection of feature-evolving data streams, IEEE Transactions on Knowledge and Data Engineering, 25, 7, pp. 1484-1497, (2013)
  • [6] Barddal J P, Gomes H M, Enembreck F, Et al., A survey on feature drift adaptation: Definition, benchmark, challenges and future directions, Journal of Systems and Software, 127, 5, pp. 278-294, (2017)
  • [7] Masud M M, Chen Q, Gao J, Et al., Classification and novel class detection of data streams in a dynamic feature space, European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 337-352, (2010)
  • [8] Wolff R, Bhaduri K, Kargupta H., A generic local algorithm for mining data streams in large distributed systems, IEEE Transactions on Knowledge and Data Engineering, 21, 4, pp. 465-478, (2009)
  • [9] Tekin C, Yoon J, Van der Schaar M., Adaptive ensemble learning with confidence bounds, IEEE Transactions on Signal Processing, 65, 4, pp. 888-903, (2017)
  • [10] Vanli N D, Sayin M O, Delibalta I, Et al., Sequential nonlinear learning for distributed multiagent systems via extreme learning machines, IEEE Transactions on Neural Networks and Learning Systems, 28, 3, pp. 546-558, (2017)
1234