Bayesian Variational Federated Learning and Unlearning in Decentralized Networks
This work addresses the need for privacy and legal compliance in federated learning by providing a method for efficient unlearning, though it is incremental as it builds on existing Bayesian and variational techniques.
The paper tackled the problem of enabling agents in decentralized networks to both collaboratively train models and efficiently delete their contributions (unlearning) under a Bayesian framework, achieving this through federated variational inference and gossip-driven communication.
Federated Bayesian learning offers a principled framework for the definition of collaborative training algorithms that are able to quantify epistemic uncertainty and to produce trustworthy decisions. Upon the completion of collaborative training, an agent may decide to exercise her legal "right to be forgotten", which calls for her contribution to the jointly trained model to be deleted and discarded. This paper studies federated learning and unlearning in a decentralized network within a Bayesian framework. It specifically develops federated variational inference (VI) solutions based on the decentralized solution of local free energy minimization problems within exponential-family models and on local gossip-driven communication. The proposed protocols are demonstrated to yield efficient unlearning mechanisms.