Multi-Class Unlearning for Image Classification via Weight Filtering
This addresses the need for efficient and explainable unlearning in machine learning systems, though it appears incremental as it builds on existing unlearning methods.
The paper tackles the problem of machine unlearning for image classification by developing a framework that can unlearn all classes in a single round using weight filtering and memory matrices, achieving selective unlearning behavior and explainable class representations.
Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single round. We achieve this by modulating the network's components using memory matrices, enabling the network to demonstrate selective unlearning behavior for any class after training. By discovering weights that are specific to each class, our approach also recovers a representation of the classes which is explainable by design. We test the proposed framework on small- and medium-scale image classification datasets, with both convolution- and Transformer-based backbones, showcasing the potential for explainable solutions through unlearning.