Research map / Label-efficient and robust learning / Recognition and long-tail
Feature Unlearning: Theoretical Foundations and Practical Applications with Shuffling
Yue Yang, Jinhao Li, Hao Wang
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 a simple feature unlearning approach using shuffling of the target feature, with theoretical foundations for removing a feature's effect from a trained model.
Problem
Feature unlearning: eliminating the effect of specific features from an already trained model, which has distinct challenges not comprehensively addressed by existing machine unlearning work.
Approach
A novel and straightforward feature unlearning approach that employs a targeted shuffling of the feature to remove its influence from a trained model, backed by theoretical analysis.
Closest papers by meaning
- What makes unlearning hard and what to do about it (NeurIPS 2024 · similarity 0.90)
- Machine Unlearning in Low-Dimensional Feature Subspace (NeurIPS 2026 · similarity 0.88)
- Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity (NeurIPS 2024 · similarity 0.88)
- Adversarial Mixup Unlearning (ICLR 2025 · similarity 0.88)
- When to Forget? Complexity Trade-offs in Machine Unlearning (ICML 2025 · similarity 0.87)
- Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning (ICLR 2025 · similarity 0.87)
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.
