AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Transferring Fairness under Distribution Shifts via Fair Consistency Regularization

Bang An, Zora Che, Mucong Ding, Furong Huang

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 10 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 fair consistency regularization to Laftr self-trainingLaftr+FixMatch · FairFace (target)V_acc: 8.21 -> 2.82Improved
Add fair consistency regularization to Laftr self-trainingLaftr+FixMatch · FairFace (target)equalized odds: 9.32 -> 5.70Improved
Add fair consistency regularization to Laftr self-trainingLaftr+FixMatch · FairFace (target)accuracy: 83.87 -> 85.52Improved
Remove consistency training on target data (ablation)Ours (w/ Laftr) · FairFace (target)accuracy: 85.52 -> 82.43Hurt
Remove consistency training on target data (ablation)Ours (w/ Laftr) · FairFace (target)V_acc: 2.82 -> 6.80Hurt
Remove consistency training on source data (ablation)Ours (w/ Laftr) · FairFace (target)equalized odds: 5.70 -> 8.18Hurt
Use equal group weights instead of dynamic weights (ablation)Ours (w/ Laftr) · FairFace (target)V_acc: 2.82 -> 6.86Hurt
Keep the teacher classifier fixed instead of updating it (ablation)Ours (w/ Laftr) · FairFace (target)accuracy: 85.52 -> 79.13Hurt
Use weaker cropping-and-flipping transformations instead of RandAugment (ablation)Ours (w/ Laftr) · FairFace (target)accuracy: 85.52 -> 77.32Hurt
Use standard rather than group-balanced consistency regularizationLaftr self-training · FairFace (target)V_acc: 2.82 -> 8.21Hurt
Apply DANN domain adaptationLaftr · FairFace (target)accuracy: 74.35 -> 74.28No clear effect

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