AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations

Hongrong Cheng, Miao Zhang, Qinfeng Shi

TPAMI 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 693 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use unstructured instead of structured pruning (SNIP) (ablation)SNIP on VGG-16 · CIFAR-100 (50% pruned)Top-1 accuracy: 70.68 -> 72.67Improved
use unstructured instead of structured pruning (GraSP) (ablation)GraSP on VGG-16 · CIFAR-10 (40% pruned)Top-1 accuracy: 93.04 -> 93.18Improved
use unstructured instead of structured pruning at 10% on GraSP (ablation)GraSP on VGG-16 · CIFAR-10 (10% pruned)Top-1 accuracy: 93.67 -> 93.58No clear effect
use unstructured instead of 2:4 semi-structured pruning (ablation)SparseGPT on OPT-125M · WikiText2perplexity: 45.51 -> 33.17Improved
use 2:4 semi-structured instead of structured pruning (ablation)K-OBD on OPT-125M · WikiText2perplexity: 75.95 -> 68.74Improved
use unstructured instead of structured pruning (ablation)LLM-Surgeon on OPT-6.7B · WikiText2perplexity: 14.90 -> 10.97Improved
use iterative instead of one-shot pruning (ablation)SynFlow, Magnitude, SparseGPT · CIFAR-10, PTBaccuracy / perplexityImproved
increase the number of pruning iterations (ablation)pruning of OPT-1.3B · WikiText2perplexityImproved
use data-driven SNIP instead of data-free Random pruning (ablation)VGG-16 · CIFAR-10 (90% pruned)Top-1 accuracy: 90.68 -> 93.40Improved
use data-free SynFlow instead of data-driven GraSP (ablation)VGG-16 · CIFAR-10 (90% pruned)Top-1 accuracy: 92.51 -> 93.26Improved
use data-driven LoRAPruner instead of data-free L2-norm (ablation)LLaMA-7B (20% pruned) · zero-shot common sense avgaccuracy: 66.84 -> 69.42Improved
use LoRAPruner instead of Wanda at 50% ratio (ablation)LLaMA-7B · zero-shot common sense avgaccuracy: 50.60 -> 59.07Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy