AI Paper Atlas

Research map / Continual learning / Online and replay-based

Learning to Unlearn for Robust Machine Unlearning

Mark He Huang, Lin Geng Foo, Jun Liu

ECCV 2024 · Continual learning › Online and replay-based · approach: Dynamic expansion and isolation · 25 citations (OpenAlex)

Read the paper

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 LTU with only 30% of remaining set instead of full-access baselinesLTU · CIFAR-10 random sample unlearning 10%TA gap to Retrain: SalUn 1.07 -> LTU 0.31Improved
increase accessible remaining set fraction from rho=0.1 to rho=0.3 (ablation)LTU · CIFAR-10 random sample unlearning 10%RA gap to Retrain: 7.67 -> 0.17Improved
use training-free unlearning (Fisher, SSD) on larger forgetting ratioFisher / SSD · CIFAR-10 random sample unlearning 50%RA gap to Retrain: Fisher 77.32; SSD 10.53Hurt
add meta optimization (meta-tune, meta-test, meta-update) instead of conventional training feedback (ablation)LTU · CIFAR-10 ResNet-18unlearning gapsImproved
add Gradient Harmonization instead of naive gradient addition (ablation)LTU · CIFAR-10 ResNet-18unlearning gapsImproved
remove either forgetting or remembering feedback (ablation)LTU · CIFAR-10 ResNet-18unlearning gapsImproved
apply Amnesiac unlearning at 50% forget ratioAmnesiac · CIFAR-10 random sample unlearning 50%RA gap to Retrain: RA gap 24.79Hurt

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