Image Feature Fusion-based Federated Client Unlearning (FCU)
For federated learning systems that must comply with data privacy regulations, this work provides a method to improve the trade-off between unlearning and model retention, though the improvement is incremental.
The paper addresses catastrophic forgetting in federated unlearning by proposing IFF-FCU, which uses a linear image feature fusion (Mixup) mechanism to balance unlearning effectiveness and model generalization. On medical imaging benchmarks (RSNA-ICH and ISIC2018), it achieves competitive error deviation from the retrained gold standard, outperforming existing baselines.
Major data protection regulations all mention the "right to be forgotten," and that's what pushed federated unlearning (FU) techniques forward. But one stubborn issue remains: catastrophic forgetting--you erase the target knowledge, yet somehow you also end up throwing out essential retained knowledge, which then hurts the model's global generalization. To get a better balance between unlearning effectiveness and generalization ability, we propose something called Image Feature Fusion-based Federated Client Unlearning (IFF-FCU). The idea is to bring in a linear Image Feature Fusion mechanism (Mixup) that dynamically creates mixed samples, bridging the gap between forget-distribution and retain-distribution. What this strategy does isn't just deleting a few discrete data points--it theoretically widens and regularizes the forgetting boundary. We ran extensive experiments on medical imaging benchmarks (RSNA-ICH and ISIC2018), and the results show that our approach achieves reasonably good unlearning. For instance, on the ICH dataset, IFF-FCU achieves a highly competitive Error deviation from the retrained gold standard, demonstrating robust improvements over existing baselines.