Denseflex: A Low Rank Factorization Methodology for Adaptable Dense Layers in DNNs-Reference-Cited by-同舟云学术

Denseflex: A Low Rank Factorization Methodology for Adaptable Dense Layers in DNNs

Published:2024-05-07 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 21st ACM International Conference on Computing Frontiers
language:
Short-container-title:

Author:

Kokhazadeh Milad¹^ORCID,Keramidas Georgios¹^ORCID,Kelefouras Vasilios²^ORCID,Stamoulis Iakovos³^ORCID

Affiliation:

1. School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece

2. School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, United Kingdom

3. Think Silicon, S.A. An Applied Materials Company, Patras, Greece

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3649153.3649183

Reference46 articles.

1. G. Lee, and K. Lee. DNN Compression by ADMM-based Joint Pruning. Journal of Knowledge-Based Systems, 2022

2. J. Xiao, C. Zhang, Y. Gong, M. Yin, Y. Sui, L. Xiang, D. Tao, and B. Yuan. HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks. arXiv preprint arXiv:2301.09422, 2023

3. X. Xu, Y. Ding, S. X. Hu, M. Niemier, J. Cong, Y. Hu, and Y. Shi. Scaling for Edge Inference of Deep Neural Networks. Journal of Nature Electronics, 2018

4. M. Eo, S. Kang, and W. Rhee. An Effective Low-Rank Compression with a Joint Rank Selection Followed by a Compression-Friendly Training. Journal of Neural Networks, 2023

5. X. Long, Z. Ben, and Y. Liu. A Survey of Related Research on Compression and Acceleration of Deep Neural Networks. Journal of Physics: Conference Series, 2019

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A comprehensive review of model compression techniques in machine learning;Applied Intelligence;2024-09-02