AI Paper Atlas

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

Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias

JuneHyoung Kwon, MiHyeon Kim, Eunju Lee, Yoonji Lee, Seunghoon Lee, YoungBin Kim

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 2 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 Sharpness-Aware Partitioning to NegGrad (ablation)CUPID · Waterbirds (biased train forget set)FA: 34.96 -> 20.38Improved
add Sharpness-Aware Partitioning to NegGrad (ablation)CUPID · Waterbirds (biased train forget set)RA: 99.81 -> 91.32Hurt
add Causal Pathway Identification (ablation)CUPID · Waterbirds (biased train forget set)FA: 20.38 -> 14.56Improved
add Causal Pathway Identification (ablation)CUPID · Waterbirds (biased train forget set)RA: 91.32 -> 99.45Improved
add Targeted Pathway Update (ablation)CUPID · Waterbirds (biased train forget set)FA: 14.56 -> 6.91Improved
add projected causal gradient only to the standard gradient (ablation)CUPID · Waterbirds (unbiased test)FA: 18.67 -> 12.77Improved
add bias gradient only to the standard gradient (ablation)CUPID · Waterbirds (unbiased test)FA: 18.67 -> 17.73No clear effect
apply both projected causal and bias gradients to their pathways (ablation)CUPID · Waterbirds (unbiased test)FA: 18.67 -> 6.02Improved
add sharpness reweighting of the update (ablation)CUPID · Waterbirds (unbiased test)FA: 17.77 -> 6.02Improved
add sharpness reweighting of the update (ablation)CUPID · Waterbirds (unbiased test)MIA: 30.81 -> 21.79Improved
choose sharpness percentile k=5% rather than a purer smaller k (ablation)CUPID · sharpness threshold analysisperformanceImproved
compare CUPID with strongest baselineCUPID vs NegGrad · BAR (unbiased test)FA: 30.26 -> 3.75Improved

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