Federated Unlearning via Class-Discriminative Pruning

Junxiao Wang, Song Guo, Xin Nan Xie, Heng Qi · Proceedings of the ACM Web Conference 2022 · 2022

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.

Read the paper · More papers on PaperTik