AI Paper Atlas

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

A Reduction to Binary Approach for Debiasing Multiclass Datasets

Ibrahim Alabdulmohsin, Jessica Schrouff, Oluwasanmi O Koyejo

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 3 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 R2B instead of the best listed baseline (DPR)Adult Income, p=0.0, RF · Adult Income, p=0.0, RFDP [%]: 1.5±.3 -> 2.2±.2Hurt
Use R2B instead of the best listed baselineAdult Income, p=0.0, k-NN · Adult Income, p=0.0, k-NNDP [%]: 3.0±.7 -> 2.1±.4Improved
Use R2B instead of the best listed baselineAdult Income, p=0.5, RF · Adult Income, p=0.5, RFDP [%]: 1.7±.3 -> 1.0±.2Improved
Use R2B instead of the best listed baselineAdult Income, p=0.5, k-NN · Adult Income, p=0.5, k-NNDP [%]: 2.9±.4 -> 1.1±.2Improved
Use R2B rather than no debiasingAdult Income, p=0.5, RF · Adult Income, p=0.5, RFaccuracy [%]: 42.0±0.7 -> 34.0±0.4Hurt
Use R2B rather than no debiasingAdult Income, p=0.5, k-NN · Adult Income, p=0.5, k-NNaccuracy [%]: 34.9±0.5 -> 31.1±0.4Hurt
Use R2B instead of OSTCOCO, p=0.0 · COCO, p=0.0DP [%]: 2.2±.3 -> 2.4±.4Hurt
Use R2B instead of OSTCOCO, p=0.5 · COCO, p=0.5DP [%]: 0.7±.2 -> 1.1±.4Hurt
Use R2B rather than no debiasingCOCO, p=0.0 · COCO, p=0.0accuracy [%]: 40.4±.2 -> 41.3±.2Improved
Use R2B rather than no debiasingCOCO, p=0.5 · COCO, p=0.5accuracy [%]: 43.8±.3 -> 48.1±.4Improved
Use R2B rather than OSTDermatology test · Dermatology testDP [%]: 5.1±1.0 -> 5.0±0.5Hurt
Use R2B rather than the strongest listed baselineDermatology test · Dermatology testTop-1 accuracy [%]: 58.6±0.5 -> 59.1±0.6Improved

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