AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Selective Unlearning via Representation Erasure Using Domain Adversarial Training

Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, James J. Clark, Daniel M. Roy, Gintare Karolina Dziugaite

ICLR 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes SURE, a targeted machine unlearning method that treats forgetting as domain adaptation, using domain-adversarial training to erase the forget set's representation while retaining validation-set behavior.

Problem

Removing specific data points or subsets from a trained model after training (machine unlearning) without full retraining.

Approach

Inspired by DANN, treats the forget set as a source domain to be made indistinguishable from a validation set drawn from the same distribution, so that the learned representation erases information about the forget set.

Experimental setup

Builds on: DANN

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