UnAct: Gradient-Free Unlearning via Targeted Activation Intervention
cs.LG, cs.CV
Submitted: 2026-10-03
Updated: 2026-10-03
Code: https://github.com/abdulmuizz0903/UnAct
Sources
- Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- An Information Theoretic Approach to Machine Unlearning
- Loss-Free Machine Unlearning
- Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
- Model Sparsity Can Simplify Machine Unlearning
- Pruning Filters for Efficient ConvNets
- Eight Methods to Evaluate Robust Unlearning in LLMs
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- Dissecting Language Models: Machine Unlearning via Selective Pruning
- Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening
- Few-Shot Unlearning by Model Inversion
- What makes unlearning hard and what to do about it
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