AI Paper Atlas

Research map / Optimization / Optimizers

Machine Unlearning via Adaptive Gradient Reweighting and Multi-stage Objective Optimization

Juxin Lu, Haoyu Shi, Mengyao Wang, Huaiwen Zhang

CVPR 2026 · Optimization › Optimizers · approach: Multi-objective gradient methods

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 Adaptive Gradient Reweighting (ablation)unlearning with multi-stage optimization · CIFAR-10 10% random forgettingAvg Gap: 2.78 -> 1.57Improved
add Adaptive Gradient Reweighting (ablation)unlearning with multi-stage optimization · CIFAR-10 single-class forgettingGap Score: 0.205 -> 0.020Improved
add Direction Rectification (ablation)unlearning method · CIFAR-10 10% random forgettingAvg Gap: 3.37 -> 1.57Improved
add Direction Rectification (ablation)unlearning method · CIFAR-10 single-class forgettingGap Score: 0.420 -> 0.020Improved
add Temporal Stabilization (ablation)unlearning method · CIFAR-10 10% random forgettingAvg Gap: 3.49 -> 1.57Improved
add Temporal Stabilization (ablation)unlearning method · CIFAR-10 single-class forgettingGap Score: 0.118 -> 0.020Improved
add Adaptive Objective Combination (ablation)unlearning method · CIFAR-10 10% random forgettingAvg Gap: 3.13 -> 1.57Improved
add Adaptive Objective Combination (ablation)unlearning method · CIFAR-10 single-class forgettingGap Score: 0.740 -> 0.020Improved
add all components (ablation)baseline unlearning · CIFAR-10 single-class forgettingRAL: -3.14 -> +0.28Improved
scale number of forgotten classes from 1 to 20Ours · CIFAR-100H-Mean: 80.47 (1 class) -> 74.72 (20 classes)No clear effect
increase forget ratio to 50%baselines vs Ours · CIFAR-100 (ResNet18)Avg Gap: LoTUS 17.25 vs Ours 8.88Improved
apply to medical unlearningOurs vs original · ISIC 2019Mean confidence: 97.1 -> 89.1Improved

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