AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training

Weilin Wan, Fan Yi, Weizhong Zhang, Quan Zhou, Cheng Jin

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning · 0 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 30% weight pruning to coreset selection (SWaST-cut)coreset-only training · CIFAR-100 1% coreset, ResNet-18accuracy (%): 36.42 -> 39.55Improved
add pruning to coreset selection (SWaST-cut, 30% prune)coreset-only · CIFAR-10 1% coreset, ResNet-101accuracy (%): 49.72 -> 67.55 (+17.83)Improved
add pruning to coreset selection (SWaST-trim 90%)coreset-only · CIFAR-10 10% coreset, ResNet-18accuracy (%): 92.20 -> 92.58No clear effect
shrink coreset size (10% -> 1%) (ablation)SWaST · CIFAR-10, ResNet-101accuracy gain over coreset-only: +1.47 -> +16.51Improved
aggressive 90% backbone pruning with SWaST-cut (ablation)SWaST-cut · CIFAR-10 10% coreset, ResNet-18accuracy (%): 92.20 -> 91.53 (-0.67)Hurt
aggressive 90% backbone pruning with SWaST-cut (ablation)SWaST-cut · CIFAR-100 10% coreset, ResNet-18accuracy (%): 70.97 -> 67.98 (-2.99)Hurt
add coreset selection to pruning-only trainingSWaST-cut · CIFAR-10 at 90% prune rateaccuracy (%): +3.33 to 93.15Improved
add pruning to coreset selection with label noiseSWaST-cut · noisy CIFAR, EL2N coresetnoise ratio in coreset: 10.62% reductionImproved
add pruningSWaST · coreset training overfittingtest minus val lossImproved
add state preservation (KL consistency, lambda 0.1) (ablation)SWaST-cut · aggressive pruningtraining stabilityImproved

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