AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Selective Data Removal for Distributional Machine Unlearning

Youssef Allouah, Rachid Guerraoui, Sanmi Koyejo

ICLR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection

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
use selective distance-based removal instead of random removal (ablation)distributional unlearning · low-divergence Gaussiansdeletion budget (%): 65 -> 18Improved
use selective removal instead of random removal (ablation)distributional unlearning · high-divergence Gaussiansdeletion budget (%): 65 -> 50Improved
use selective removal (LR-COS) instead of random removal (ablation)distributional unlearning · Jigsaw toxic commentsdeletion budget (%) to halve recall: 100 -> 85Improved
use selective removal instead of random removal (ablation)distributional unlearning · SMS Spamdeletion budget (%): 90 -> 75Improved
use selective removal (LR-MAHA) instead of random removal (ablation)distributional unlearning · CIFAR-10 cat classdeletion budget (%): 80 -> 50Improved
use selective removal instead of random selection before retraining (ablation)retraining · CIFAR-10 cat unlearningdeletion budget (%): 80 -> 60Improved
use selective removal instead of random selection before finetuning (ablation)finetuning · CIFAR-10 cat unlearningdeletion budget (%): 98 -> 88Improved
use selective removal instead of random selection before SalUn (ablation)SalUn · CIFAR-10 cat unlearningdeletion budget (%): 68 -> 55Improved
use selective removal instead of coreset selection before SalUn (ablation)SalUn · CIFAR-10 cat unlearningdeletion budget (%): 75 -> 55Improved
use selective removal instead of coreset selection with influence functions (ablation)influence-function unlearning · low-divergence Gaussiansdeletion budget (%): 93 -> 18Improved
use centroid coreset instead of random selection with retraining (ablation)retraining · CIFAR-10 cat unlearningdeletion budget (%): 80 -> 75Improved
use centroid coreset instead of random selection with influence functions (ablation)influence-function unlearning · low-divergence Gaussiansdeletion budget (%): 91 -> 93Hurt

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