Unlearning or Not: A Strategic Data Forgetting Scheme for Federated Unlearning With Bounded Rationality

Summary

Researchers propose a strategic data forgetting scheme for federated unlearning that accounts for a boundedly rational federated learning server. The scheme uses a prospect theory-driven data forgetting game to design a truthful incentive mechanism that encourages clients to retain more data during unlearning. A penalty mechanism discourages selfish behavior, and a zero-payment mechanism aims for equitable reward distribution. Simulations are reported to confirm the scheme motivates high-quality models and improves the accuracy of unlearned models.