Erased, but Not Gone: Output Forgetting Is Not True Forgetting
cs.LG, cs.AI
Submitted: 2026-06-23
Updated: 2026-10-09
Terminology
Sources
- POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Representation Unlearning: Forgetting through Information Compression
- Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
- Erase at the Core: Representation Unlearning for Machine Unlearning
- DUCK: Distance-based Unlearning via Centroid Kinematics
- Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
- On the Impossibility of Retrain Equivalence in Machine Unlearning
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks