Preprint · 2020 · Open access

BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method

Xiaolong Ma, Zhengang Li, Gong, Yifan, Tianyun Zhang, Wei Niu, Zheng Zhan, Pu Zhao, Jian Tang, Xue Lin, Bin Ren, Yanzhi Wang

arXiv (Cornell University) · Published 23 January 2020 · DOI 10.48550/arxiv.2001.08357

Open PDFView at the publisherCite this paper

In brief

“BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method” is a 2020 preprint by Xiaolong Ma and 10 co-authors, published in arXiv (Cornell University). OpenAlex counts 15 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
15
Most cited in
2022 (7)
References
28
Authors
11

Abstract

Accelerating DNN execution on various resource-limited computing platforms has been a long-standing problem. Prior works utilize l1-based group lasso or dynamic regularization such as ADMM to perform structured pruning on DNN models to leverage the parallel computing architectures. However, both of the pruning dimensions and pruning methods lack universality, which leads to degraded performance and limited applicability. To solve the problem, we propose a new block-based pruning framework that comprises a general and flexible structured pruning dimension as well as a powerful and efficient reweighted regularization method. Our framework is universal, which can be applied to both CNNs and RNNs, implying complete support for the two major kinds of computation-intensive layers (i.e., CONV and FC layers). To complete all aspects of the pruning-for-acceleration task, we also integrate compiler-based code optimization into our framework that can perform DNN inference in a real-time manner. To the best of our knowledge, it is the first time that the weight pruning framework achieves universal coverage for both CNNs and RNNs with real-time mobile acceleration and no accuracy compromise.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ma, X., Li, Z., Yifan, G., Zhang, T., Niu, W., Zhan, Z., Zhao, P., Tang, J., Lin, X., Ren, B., & Wang, Y. (2020). BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2001.08357

MLA 9

Ma, Xiaolong, et al. “BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method.” arXiv (Cornell University), 2020. https://doi.org/10.48550/arxiv.2001.08357.

Chicago

Ma, Xiaolong, Zhengang Li, Gong, Yifan, Tianyun Zhang, Wei Niu, Zheng Zhan, Pu Zhao, et al. 2020. “BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2001.08357.

Harvard

Ma, X. et al. (2020) ‘BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method’, arXiv (Cornell University). doi:10.48550/arxiv.2001.08357.

IEEE

X. Ma et al., “BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method,” arXiv (Cornell University), 2020, doi: 10.48550/arxiv.2001.08357.

BibTeX

@misc{ma2020unified,
  title     = {{BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method}},
  author    = {Ma, Xiaolong and Li, Zhengang and Yifan, Gong, and Zhang, Tianyun and Niu, Wei and Zhan, Zheng and Zhao, Pu and Tang, Jian and Lin, Xue and Ren, Bin and Wang, Yanzhi},
  howpublished = {arXiv (Cornell University)},
  year      = {2020},
  doi       = {10.48550/arxiv.2001.08357},
  url       = {https://doi.org/10.48550/arxiv.2001.08357}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202011
202122
202277
202322
202411
202522

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • weight pruning
  • convolutional neural networks
  • recurrent neural networks
  • mobile edge computing
  • resource-constrained devices

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Ma, X., Li, Z., Yifan, G., Zhang, T., Niu, W., Zhan, Z., Zhao, P., Tang, J., Lin, X., Ren, B., & Wang, Y. (2020). BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2001.08357

How many times has this paper been cited?

15 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Xiaolong Ma, Zhengang Li, Gong, Yifan, Tianyun Zhang, Wei Niu, Zheng Zhan, Pu Zhao, Jian Tang, Xue Lin, Bin Ren, Yanzhi Wang.

What is the DOI of this paper?

10.48550/arxiv.2001.08357, permanently at https://doi.org/10.48550/arxiv.2001.08357. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.