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
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
- Learning to Unlearn: Instance-Wise Unlearning for Pre-trained Classifiers (AAAI 2024 · similarity 0.90)
- Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models (NeurIPS 2024 · similarity 0.89)
- Not All Wrong is Bad: Using Adversarial Examples for Unlearning (ICML 2025 · similarity 0.89)
- On Effects of Steering Latent Representation for Large Language Model Unlearning (AAAI 2025 · similarity 0.89)
- Adversarial Mixup Unlearning (ICLR 2025 · similarity 0.88)
- From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization (NeurIPS 2025 · similarity 0.88)
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.
