$\texttt{FedBC}$: Calibrating Global and Local Models via Federated Learning Beyond Consensus. (arXiv:2206.10815v1 [cs.LG])

In federated learning (FL), the objective of collaboratively learning a
global model through aggregation of model updates across devices tends to
oppose the goal of personalization via local information. In this work, we
calibrate this tradeoff in a quantitative manner through a multi-criterion
optimization-based framework, which we cast as a constrained program: the
objective for a device is its local objective, which it seeks to minimize while
satisfying nonlinear constraints that quantify the proximity between the local
and the global …

arxiv federated learning global learning lg