CoUn: Empowering Machine Unlearning via Contrastive Learning
2025/09/19 by Yasser H. Khalil, Khalil, Yasser H., Mehdi Setayesh +3
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2509.16391
openalex publication_date 2025/09/19 · openalex created_date 2025/10/16 · openalex updated_date 2026/07/28
Abstract
Machine unlearning (MU) aims to remove the influence of specific "forget" data from a trained model while preserving its knowledge of the remaining "retain" data. Existing MU methods based on label manipulation or model weight perturbations often achieve limited unlearning effectiveness. To address this, we introduce CoUn, a novel MU framework inspired by the observation that a model retrained from scratch using only retain data classifies forget data based on their semantic similarity to the retain data. CoUn emulates this behavior by adjusting learned data representations through contrastive learning (CL) and supervised learning, applied exclusively to retain data. Specifically, CoUn (1) leverages semantic similarity between data samples to indirectly adjust forget representations using CL, and (2) maintains retain representations within their respective clusters through supervised learning. Extensive experiments across various datasets and model architectures show that CoUn consistently outperforms state-of-the-art MU baselines in unlearning effectiveness. Additionally, integrating our CL module into existing baselines empowers their unlearning effectiveness.
Citations
- NoT: Federated Unlearning via Weight Negation
- What makes unlearning hard and what to do about it
- Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
- Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
- A Survey on Federated Unlearning: Challenges, Methods, and Future Directions
- SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
- Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening
- Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy
- Model Sparsity Can Simplify Machine Unlearning
- AI Model Disgorgement: Methods and Choices
- Boundary Unlearning
- A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
- Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
- Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
- Vision Transformer for Small-Size Datasets
- Towards the Generalization of Contrastive Self-Supervised Learning
- Unrolling SGD: Understanding Factors Influencing Machine Unlearning
- Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
- VICReg: Variance-Invariance-Covariance Regularization for\n Self-Supervised Learning
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- A Survey on Contrastive Self-supervised Learning
- Amnesiac Machine Learning
- CO2: Consistent Contrast for Unsupervised Visual Representation Learning
- What Makes for Good Views for Contrastive Learning?
- Supervised Contrastive Learning
- Improved Baselines with Momentum Contrastive Learning
- A Simple Framework for Contrastive Learning of Visual Representations
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep\n Networks
- A Theoretical Analysis of Contrastive Unsupervised Representation Learning
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Deep Residual Learning for Image Recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- ImageNet Large Scale Visual Recognition Challenge
- ImageNet Large Scale Visual Recognition Challenge
- Flat Minima
Related