Improving post-training structured pruning via two-stage reconstruction
文献类型：期刊论文
| 作者 | Li, Chenhao1,2; Li, Lin1,2; Zhang, Zhibin2; Qiu, Qiang2; Guo, Jiafeng2; Cheng, Xueqi2 |
| 刊名 | EXPERT SYSTEMS WITH APPLICATIONS
 |
| 出版日期 | 2026-01-15 |
| 卷号 | 296页码:10 |
| 关键词 | Post-training pruning Layer reconstruction Channel pruning Calibration data |
| ISSN号 | 0957-4174 |
| DOI | 10.1016/j.eswa.2025.128930 |
| 英文摘要 | Structured pruning reduces inference costs by removing structured parameters from neural networks. However, most pruning approaches rely on lengthy retraining procedures to restore performance, rendering them impractical in many real-world settings where computational constraints prohibit extensive retraining. Existing post-training pruning methods that can restore performance within minutes mainly focuses on unstructured pruning, which performs poorly when combined with structured pruning. The information loss caused by structured pruning makes the model accuracy challenging to recover in the post-training setting. To address this issue, we introduce a two-stage activation reconstruction strategy to recover model accuracy. The first phase aggregates information into the remaining components before pruning. The second phase models the layer-wise cumulative error and calibrates the layer output discrepancy between the pruned and original models to reconstruct the activation signal. Experiments demonstrate that our method achieves significant improvements over post-training pruning methods and matches the performance of retraining-based approaches. With access to about 0.2% samples from the ImageNet training set, our method achieves a 1.73x reduction in FLOPs, while maintaining 72.58% accuracy with ResNet-50. Notably, our method recovers the accuracy of pruned networks within a few minutes, which is orders of magnitude faster than retraining-based techniques. |
| 资助项目 | Beijing Nova Program[Z211100002121141] ; Beijing Nova Program[JCKY2022130C039] |
| WOS研究方向 | Computer Science ; Engineering ; Operations Research & Management Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001536942100001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/41984]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Li, Chenhao |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Chenhao,Li, Lin,Zhang, Zhibin,et al. Improving post-training structured pruning via two-stage reconstruction[J]. EXPERT SYSTEMS WITH APPLICATIONS,2026,296:10. |
| APA | Li, Chenhao,Li, Lin,Zhang, Zhibin,Qiu, Qiang,Guo, Jiafeng,&Cheng, Xueqi.(2026).Improving post-training structured pruning via two-stage reconstruction.EXPERT SYSTEMS WITH APPLICATIONS,296,10. |
| MLA | Li, Chenhao,et al."Improving post-training structured pruning via two-stage reconstruction".EXPERT SYSTEMS WITH APPLICATIONS 296(2026):10. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。