AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Fair and Accurate Decision Making through Group-Aware Learning

Ramtin Hosseini, Li Zhang, Bhanu Garg, Pengtao Xie

ICML 2023 · Learning theory and algorithms › Fairness · approach: Causal and policy fairness in decisions

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
add Learning by Grouping (LBG)ResNet18 · CelebADEO: 0.5683 -> 0.0596Improved
add LBGDARTS · CelebAerror (%): 16.39 -> 15.91Improved
add domain adaptation (DALBG) on top of LBGLBG-DARTS · CelebAerror (%): 15.91 -> 15.22Improved
add domain adaptation (DALBG) on top of LBGLBG-ResNet18 · CelebADEO: 0.0596 -> 0.0835Hurt
add LBGResNet18 · ISIC-18error (%): 14.3 -> 12.8Improved
add LBGDARTS · ISIC-18SPD: 0.121 -> 0.048Improved
add DALBG to ResNet56 instead of vanillaResNet56 · CIFAR-100test error (%): 31.46 -> 27.95Improved
apply DALBG to Swin-TSwin-T · ImageNettest error (%): 18.70 -> 16.64Improved
apply DALBG to DARTSDARTS · CIFAR-100test error (%): 20.58 -> 17.97Improved
apply LBG to PC-DARTSPC-DARTS · CIFAR-100test error (%): 17.96 -> 16.21Improved
apply DALBG to PC-DARTSPC-DARTS · ImageNettop-1 error (%): 24.8 -> 23.1Improved
increase tradeoff lambda 0 -> 0.1 -> 1 (ablation)DALBG-DARTS · CelebAerror (%): 15.91 -> 15.22 -> 15.38Mixed

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