AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Parameter-Efficient Masking Networks

Yue Bai, Huan Wang, Xu Ma, Yitian Zhang, ZHIQIANG TAO, Yun Fu

NeurIPS 2022 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 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
reduce unique parameters from MP to RP 1e-5 (ablation)PEMN ConvMixer 6-block dim 256 · CIFAR10test accuracy: 88.97 (0.08) -> 81.01 (0.38)Hurt
reduce unique parameters from MP to RP 1e-5 (ablation)PEMN ConvMixer 8-block dim 512 · CIFAR10test accuracy: 93.21 (0.05) -> 87.40 (0.22)Hurt
reduce unique parameters from MP to RP 1e-1/1e-2/1e-3 (ablation)PEMN ConvMixer · CIFAR10test accuracy: 88.97 (0.08) -> 88.89 (0.13)No clear effect
reduce unique parameters from MP to RP 1e-4/1e-5 (ablation)PEMN ViT 6-block dim 256 · CIFAR10test accuracy: 76.70 (0.10) -> 64.84 (0.21)Hurt
reduce unique parameters from MP to RP 1e-5 (ablation)PEMN ViT 8-block dim 512 · CIFAR10test accuracy: 83.66 (0.12) -> 78.84 (0.29)Hurt
increase hidden dimension from 256 to 512 (ablation)PEMN MP ConvMixer 6-block · CIFAR10test accuracy: 88.97 (0.08) -> 92.02 (0.02)Improved
increase depth from 6 to 8 blocks (ablation)PEMN MP ConvMixer dim 512 · CIFAR10test accuracy: 92.02 (0.02) -> 93.21 (0.05)Improved
increase depth from 6 to 8 blocks (ablation)PEMN MP ViT dim 256 · CIFAR10test accuracy: 76.70 (0.10) -> 79.23 (0.22)Improved
fix random weights and learn only a mask (Mask) versus dense trainingsparse selection on random weights · CIFAR10test accuracyHurt
use PEMN MP instead of 90% sparse training baselineResNet56 · CIFAR10test accuracy: 86.35 (0.22) -> 88.13 (0.19)Improved
use PEMN MP instead of 90% sparse training baselineResNet32 · CIFAR100test accuracy: 49.21 (0.29) -> 51.76 (0.25)Improved
use PEMN MP instead of 90% sparse training baselineResNet56 · CIFAR100test accuracy: 55.21 (0.36) -> 56.39 (0.29)Improved

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