AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Towards Fairness-aware Adversarial Network Pruning

Lei Zhang, Zhibo Wang, Xiaowei Dong, Yunhe Feng, Xiaoyi Pang, Zhifei Zhang, Kui Ren

ICCV 2023 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 7 citations (OpenAlex)

Read the paper

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
optimize fairness jointly during pruning via adversarial discriminator instead of pruning onlyResNet-18 on CelebA Attractive, 80% pruned · CelebA AttractiveDEO: 0.5352 -> 0.2149Improved
joint adversarial pruning instead of debiasing first then pruning (Fair-SGDP)SGDP pruning · CelebA Attractive 80% prunedDEO: 0.3261 -> 0.2149Improved
prune from the dense pretrained network instead of training a sparse network from scratch (ablation)ResNet-18 80% sparse · CelebA AttractiveDEO: 0.5071 -> 0.2149Improved
increase pruning ratio from 80% to 90% (ablation)FARPrune · CelebA AttractiveDEO: 0.2149 -> 0.3143Hurt
increase pruning ratio from 80% to 95% (ablation)FARPrune · CelebA AttractiveDI: 0.4849 -> 0.3891Hurt
apply method to ShuffleNet v2 instead of ResNet-18 (ablation)FARPrune · CelebA Attractive 80% prunedDEO: 0.5086 -> 0.3582Improved
apply method to MobileNet v2 instead of ResNet-18 (ablation)FARPrune · CelebA Attractive 80% prunedDEO: 0.5229 -> 0.3390Improved
search the mask on a randomly initialized network without training (ablation)FARPrune · CelebA Attractive 80% prunedDEO: 0.4418 (SGDP) -> 0.1959Improved
apply method on CelebA Blond Hair targetFARPrune vs Fair-LMW · CelebA Blond Hair 80% prunedDI: 0.1181 vs 0.1188No clear effect
use fairness-aware pruning rather than SGDP, accuracy costFARPrune · CelebA Attractive random init 90% prunedACC: ACC 78.27% (SGDP) vs 76.18%, DEO 0.4675 vs 0.3444Mixed

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