Machine Unlearning for Federated Socially Fair k-Means Clustering
The research develops exact machine unlearning for federated socially fair k-means clustering to handle data deletion requests while maintaining fairness. It compares exact replay against retraining, finding that whole-client deletion is 35.8 times faster than retraining. The method preserves crucial fairness guarantees by keeping group-separated summaries, ensuring robustness even after data removal.