# Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?

arXiv: https://arxiv.org/abs/1907.02124 · HTML: https://mlsanity.com/paper/1907.02124/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 30 of 32)

- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge](https://mlsanity.com/paper/2110.14032/) (2021)
- [FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos](https://mlsanity.com/paper/2212.12294/) (2022)
- [Teachers Do More Than Teach: Compressing Image-to-Image Models](https://mlsanity.com/paper/2103.03467/) (2021)
- [CHEX: CHannel EXploration for CNN Model Compression](https://mlsanity.com/paper/2203.15794/) (2022)
- [Effective Model Sparsification by Scheduled Grow-and-Prune Methods](https://mlsanity.com/paper/2106.09857/) (2021)
- [Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers](https://mlsanity.com/paper/2402.04744/) (2024)
- [Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design](https://mlsanity.com/paper/2103.15750/) (2021)
- [FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator](https://mlsanity.com/paper/2106.09144/) (2021)
- [Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask](https://mlsanity.com/paper/2209.07617/) (2022)
- [Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training](https://mlsanity.com/paper/2209.11204/) (2022)
- [Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions](https://mlsanity.com/paper/2303.08595/) (2023)
- [Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI](https://mlsanity.com/paper/2106.09166/) (2021)
- [Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization](https://mlsanity.com/paper/2312.15322/) (2023)
- [Complexity-Driven CNN Compression for Resource-constrained Edge AI](https://mlsanity.com/paper/2208.12816/) (2022)
- [DNNShifter: An Efficient DNN Pruning System for Edge Computing](https://mlsanity.com/paper/2309.06973/) (2023)
- [ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2605.24011/) (2026)
- [Deep Model Compression based on the Training History](https://mlsanity.com/paper/2102.00160/) (2021)
- [Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration](https://mlsanity.com/paper/2111.11581/) (2021)
- [Temporal Action Detection Model Compression by Progressive Block Drop](https://mlsanity.com/paper/2503.16916/) (2025)
- [DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning](https://mlsanity.com/paper/2401.09068/) (2024)
- [SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field](https://mlsanity.com/paper/2402.16366/) (2024)
- [Model Compression Methods for YOLOv5: A Review](https://mlsanity.com/paper/2307.11904/) (2023)
- [Transfer Learning for Structured Pruning under Limited Task Data](https://mlsanity.com/paper/2311.06382/) (2023)
- [Energy-Efficient Uncertainty-Aware Biomass Composition Prediction at the Edge](https://mlsanity.com/paper/2404.11230/) (2024)
- [Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization](https://mlsanity.com/paper/2404.16877/) (2024)
- [AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning](https://mlsanity.com/paper/2412.18091/) (2024)
- [Coded Deep Learning: Framework and Algorithm](https://mlsanity.com/paper/2501.09849/) (2025)
- [Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classification](https://mlsanity.com/paper/2105.02954/) (2021)

## Abstract (arXiv)

Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression with two main approaches. Weight pruning leverages the redundancy in the number of weights and can be performed in a non-structured, which has higher flexibility and pruning rate but incurs index accesses due to irregular weights, or structured manner, which preserves the full matrix structure with lower pruning rate. Weight quantization leverages the redundancy in the number of bits in weights. Compared to pruning, quantization is much more hardware-friendly, and has become a "must-do" step for FPGA and ASIC implementations. This paper provides a definitive answer to the question for the first time. First, we build ADMM-NN-S by extending and enhancing ADMM-NN, a recently proposed joint weight pruning and quantization framework. Second, we develop a methodology for fair and fundamental comparison of non-structured and structured pruning in terms of both storage and computation efficiency. Our results show that ADMM-NN-S consistently outperforms the prior art: (i) it achieves 348x, 36x, and 8x overall weight pruning on LeNet-5, AlexNet, and ResNet-50, respectively, with (almost) zero accuracy loss; (ii) we demonstrate the first fully binarized (for all layers) DNNs can be lossless in accuracy in many cases. These results provide a strong baseline and credibility of our study. Based on the proposed comparison framework, with the same accuracy and quantization, the results show that non-structrued pruning is not competitive in terms of both storage and computation efficiency. Thus, we conclude that non-structured pruning is considered harmful. We urge the community not to continue the DNN inference acceleration for non-structured sparsity.