Papers › StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs

StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs

29 Jul 2018arXiv:1807.11091archive 2025-07-28

Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Xiaolong Ma, Ning Liu, Linfeng Zhang, Jian Tang, Kaisheng Ma, Xue Lin, Makan Fardad, Yanzhi Wang

Weight pruning methods of DNNs have been demonstrated to achieve a good model pruning rate without loss of accuracy, thereby alleviating the significant computation/storage requirements of large-scale DNNs. Structured weight pruning methods have been proposed to overcome the limitation of irregular network structure and demonstrated actual GPU acceleration. However, in prior work the pruning rate (degree of sparsity) and GPU acceleration are limited (to less than 50%) when accuracy needs to be maintained. In this work,we overcome these limitations by proposing a unified, systematic framework of structured weight pruning for DNNs. It is a framework that can be used to induce different types of structured sparsity, such as filter-wise, channel-wise, and shape-wise sparsity, as well non-structured sparsity. The proposed framework incorporates stochastic gradient descent with ADMM, and can be understood as a dynamic regularization method in which the regularization target is analytically updated in each iteration. Without loss of accuracy on the AlexNet model, we achieve 2.58X and 3.65X average measured speedup on two GPUs, clearly outperforming the prior work. The average speedups reach 3.15X and 8.52X when allowing a moderate ac-curacy loss of 2%. In this case the model compression for convolutional layers is 15.0X, corresponding to 11.93X measured CPU speedup. Our experiments on ResNet model and on other data sets like UCF101 and CIFAR-10 demonstrate the consistently higher performance of our framework.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

KaiqiZhang/ADAM-ADMM officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Model Compression

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionADMMAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingGrouped ConvolutionKaiming InitializationLocal Response NormalizationMax PoolingPruningReLUResidual BlockResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections