AI Paper Atlas

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

Robust Learning from Noisily Labeled Long-Tailed Data via Fairness Regularizer

Jiaheng Wei, Zhaowei Zhu, Gang Niu, Tongliang Liu, Sijia Liu, Masashi Sugiyama, Yang Liu

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 0 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 fairness regularizer with 2 sub-populations (G2)CE · CIFAR-10 (long-tailed, Sym noise 0.5, r=100)accuracy: 36.44 -> 46.33Improved
add fairness regularizer (G2)Logit-adj · CIFAR-10 (long-tailed, Imb noise 0.2, r=100)accuracy: 68.18 -> 72.20Improved
add fairness regularizer (G2)Logit-adj · CIFAR-10 (long-tailed, Sym noise 0.5, r=100)accuracy: 27.32 -> 21.93Hurt
add fairness regularizer (G2)LS · CIFAR-10 (long-tailed, Imb noise 0.5, r=50)accuracy: 36.17 -> 44.11Improved
add fairness regularizer (G2)Focal · CIFAR-10 (long-tailed, Imb noise 0.2, r=100)accuracy: 57.68 -> 56.55Hurt
add fairness regularizer (G2)PL · CIFAR-10 (long-tailed, Imb noise 0.5, r=100)accuracy: 30.13 -> 28.01Hurt
split sub-populations by KNN clustering into one per classCE + FR · CIFAR-100 (long-tailed noisy)accuracy: 46.02 -> 46.18No clear effect
use 2 sub-populations from a pre-trained model instead of KNN clusters (ablation)CE + FR · CIFAR-100 (Imb noise 0.5, r=100)accuracy: 15.19 -> 15.93Improved
add fairness regularizer (KNN) to CECE · CIFAR-10 (long-tailed, Sym noise 0.5, r=100)accuracy: 36.44 -> 45.63Improved
vary FR weight theta from 0.0 to 2.0 (ablation)CE · Clothing1Maccuracy: 72.68 -> 72.99No clear effect
add FR (theta=1.0) (ablation)NLS · Clothing1Maccuracy: 74.46 -> 74.49No clear effect
add FR (theta=1.0) (ablation)Logit-adj · Clothing1Maccuracy: 72.43 -> 72.67Improved

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