Page 85 - ITU Journal, ICT Discoveries, Volume 3, No. 1, June 2020 Special issue: The future of video and immersive media

ITU Journal: ICT Discoveries, Vol. 3(1), June 2020

IEEE Conference on Computer Vision and Pattern
Recognition, pages 5687–5695, 2017.
[85] S.-K. Yeom, P. Seegerer, S. Lapuschkin, S. Wiede-
mann, K.-R. Müller, and W. Samek. Pruning by
explaining: A novel criterion for deep neural net-
work pruning. arXiv preprint arXiv:1912.08881,
2019.

[86] H. Yu, S. Yang, and S. Zhu. Parallel restarted sgd
with faster convergence and less communication:
Demystifying why model averaging works for deep
learning. In Proceedings of the AAAI Conference
on Artificial Intelligence, volume 33, pages 5693–
5700, 2019.

[87] X. Yu, T. Liu, X. Wang, and D. Tao. On compress-
ing deep models by low rank and sparse decompo-
sition. In Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, pages
7370–7379, 2017.
[88] W. Zhang, S. Gupta, X. Lian, and J. Liu. Staleness-
aware async-sgd for distributed deep learning.
arXiv preprint arXiv:1511.05950, 2015.

[89] Y. Zhao, M. Li, L. Lai, N. Suda, D. Civin, and
V. Chandra. Federated learning with non-iid data.
arXiv preprint arXiv:1806.00582, 2018.

© International Telecommunication Union, 2020 63