Papers with Network pruning
WRP: Weight Recover Prune for Structured Sparsity (2024.acl-long)
Copied to clipboard
| Challenge: | Existing pruning and quantization algorithms could compress LLMs to 4 bits without retraining. |
| Approach: | They propose a method to prune models using a minimal set of critical weights . they compare the method to a 2:4 structured sparsity method . |
| Outcome: | The proposed method outperforms other methods on LLAMA2 and OPT models while maintaining the efficiency of the compression. |
CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information (2025.coling-main)
Copied to clipboard
Yuxin Wang, MingHua Ma, Zekun Wang, Jingchang Chen, Shan Liping, Qing Yang, Dongliang Xu, Ming Liu, Bing Qin
| Challenge: | Existing LLM pruning works focus on unstructured pruning, which typically requires special hardware support for a practical speed-up. |
| Approach: | They propose a network pruning framework that leverages both coarse and fine-grained activation information as an importance criterion to guide pruning. |
| Outcome: | The proposed framework outperforms existing pruning methods on diverse models across sparsity budgets. |
Structured Optimal Brain Pruning for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing pruning methods for Large Language Models rely on unstructured pruning or require special hardware to accelerate computation. |
| Approach: | They propose a retraining-free structured pruning method called SoBP . they evaluate the effectiveness of SoBP across 14 models from 3 LLM families . |
| Outcome: | The proposed method outperforms current state-of-the-art pruning methods on 8 datasets. |
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning (2024.emnlp-main)
Copied to clipboard
Abhinav Bandari, Lu Yin, Cheng-Yu Hsieh, Ajay Jaiswal, Tianlong Chen, Li Shen, Ranjay Krishna, Shiwei Liu
| Challenge: | Existing approaches to prune LLMs rely on the C4 dataset as calibration data . arithmetic datasets perform better than pre-training datasets for pruning, whereas chain-of-thought is only useful on certain tasks. |
| Approach: | They evaluate the selection of calibration data for LLM pruning across a wide range of datasets . they find that C4 is not the optimal calibration data, and that CoT is only useful on certain tasks. |
| Outcome: | The chosen calibration data significantly impacts the performance of pruned LLMs, the authors found . their results shed light on the importance of carefully selecting calibration data for LLM pruning . |