AI Paper Atlas

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

FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning

Liheng Yu, Zhe Zhao, Yuxuan Wang, Pengkun Wang, Xiaofeng Cao, Binwu Wang, Yang Wang

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 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
apply FaLW reweighting to unlearningSalUn · CIFAR-100 gamma=2, 30% forgetAvg. Gap: 2.29 -> 1.30Improved
apply FaLW reweightingSalUn · CIFAR-100 gamma=0 (balanced), 30% forgetAvg. Gap: 1.55 -> 0.68Improved
apply FaLWbest baselines · Tiny-ImageNet VGG-16 gamma=1Avg. Gap: 2.45 -> 0.35Improved
apply FaLWbest baselines · CIFAR-10 VGG-16 gamma=1/2 40%Avg. Gap: 2.14 -> 0.40Improved
add class-aware balance factor (ablation)FaLW · CIFAR-100 gamma=2tail-class FA gap: -18.76 -> -13.04Improved
add class-aware balance factor (ablation)FaLW · CIFAR-100 gamma=1.5tail-class FA gap: -12.19 -> -9.46Improved
add class-aware balance factor (ablation)FaLW · CIFAR-100 gamma=2head-class FA gap: 1.22 -> 1.33Hurt
increase forget-set imbalance gammaSalUn · CIFAR-100 30% forgetforget accuracy vs Retrain: FA below Retrain at low gamma (e.g. 56.93 vs 59.11) to above at high gamma (4.79 vs 1.82)Hurt
apply FaLW across forget ratios 10%-40%SalUn · CIFAR-100 gamma=1/4Avg. Gap: 20%: 2.44 -> 0.33Improved
apply FaLW at 30% forgetSFRon · CIFAR-100 gamma=1/4 30%Avg. Gap: 1.71 -> 0.91Improved

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