Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning
cs.LG, cs.CV
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/Yasaman-dt/SFRA
Terminology
Sources
- RULER: Representation-Level Verification of Machine Unlearning
- Do Unlearning Methods Remove Information from Language Model Weights?
- Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
- Erase at the Core: Representation Unlearning for Machine Unlearning
- LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
- Eight Methods to Evaluate Robust Unlearning in LLMs
- Selective Forgetting of Deep Networks at a Finer Level than Samples
- UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
- Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition
- Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks