AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

Geng Yuan, Yanyu Li, Sheng Li, Zhenglun Kong, Sergey Tulyakov, Xulong Tang, Yanzhi Wang, Jian Ren

NeurIPS 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Sparse training from scratch · 4 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
Add layer freezing with 20% FLOPs reduction (ablation)MEST sparse training · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 71.30 -> 71.29No clear effect
Add layer freezing with 20% FLOPs reduction (ablation)MEST sparse training · CIFAR-100, ResNet-32, 60% sparsityaccuracy: 73.97 -> 73.76Hurt
Add layer freezing with 35% FLOPs reduction (ablation)MEST sparse training · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 71.30 -> 70.26Hurt
Add data sieving with 20% FLOPs reduction (ablation)MEST sparse training · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 71.3 -> 71.33No clear effect
Add data sieving with 35% FLOPs reduction (ablation)MEST sparse training · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 71.3 -> 70.59Hurt
Combine freezing and sieving instead of freezing only at 35% FLOPs reduction (ablation)SpFDE · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 70.26 -> 71.25Improved
Combine freezing and sieving instead of data sieving only at 35% FLOPs reduction (ablation)SpFDE · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 70.59 -> 71.25Improved
Use single-shot freezing instead of periodic freezing (ablation)SpFDE · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 70.86 -> 71.30Improved
Use single-shot freezing instead of single-shot freezing & resume (ablation)SpFDE · CIFAR-100, ResNet-32, 60% sparsityaccuracy: 73.49 -> 73.61Improved
Raise data sieving update ratio from 10% to 30% (remove 15%) (ablation)SpFDE · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 70.68 -> 71.35Improved
Raise data sieving update ratio from 30% to 50% (remove 15%) (ablation)SpFDE · CIFAR-100, ResNet-32, 90% sparsityaccuracy: 71.35 -> 70.92Hurt
Replace MEST with SpFDE 15%+15% at 80% sparsitySpFDE · ImageNet, ResNet-50top-1 accuracy: 75.70 -> 75.75Improved

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