AI Paper Atlas

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

Fairness via Representation Neutralization

Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Hu

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 27 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
Use GCE instead of standard cross entropy to train the bias-amplified model (ablation)MEPS proxy annotation generation · MEPSDP: 0.866 -> 0.839Hurt
Replace GCE proxy labels with cross-entropy-generated proxy labels (ablation)RNF · MEPSDP: 0.964 -> 0.936Hurt
Replace GCE proxy labels with random sensitive-attribute annotations (ablation)RNF · MEPSDP: 0.964 -> 0.902Hurt
Debias only the last layer instead of the last several layers (ablation)RNF · MEPSDP: 0.964 -> 0.971Improved
Debias only the last layer instead of the last several layers (ablation)RNF · CelebADP: 0.836 -> 0.966Improved
Apply RNF on top of an EOR-debiased encoder (ablation)RNF · MEPSDP: 0.964 -> 0.980Improved
Apply RNF on top of an adversarially debiased encoder (ablation)RNF · MEPSDP: 0.964 -> 0.971Improved
Use ground-truth sensitive-attribute annotations instead of proxy annotations (ablation)RNF · all datasetsfairness mitigation: 10%Improved
Neutralize representations of same-label samples from different sensitive groups and retrain the classification headRNF · AdultDP-Similarity: 0.272 -> 0.075Improved

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