Federated Unlearning via Class-Discriminative Pruning
Junxiao Wang, Song Guo, Xin Xie, Heng Qi
Abstract
We explore the problem of selectively forgetting categories from trained CNN classification models in federated learning (FL). Given that the data used for training cannot be accessed globally in FL, our insights probe deep into the internal influence of each channel. Through the visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification.
Topics & Concepts
Discriminative modelForgettingComputer sciencePruningArtificial intelligenceClass (philosophy)VisualizationFeature (linguistics)Contextual image classificationPattern recognition (psychology)Channel (broadcasting)Machine learningImage (mathematics)PhilosophyLinguisticsAgronomyComputer networkBiologyPrivacy-Preserving Technologies in DataAdversarial Robustness in Machine LearningStochastic Gradient Optimization Techniques