Previous works have implicitly studied that FL suffers from the "client-drift" problem, which is caused by the inconsistent optimum across local clients.

To tackle this problem, we rigorously analyze a representative distillation-based algorithm in the view of kernel regression.

In this paper, we review the recent development of classical federated primal dual methods and point out a serious common defect of such methods in non-convex scenarios, which we say is a "dual drift" caused by dual

In each communication round, each client uniformly samples points in the neighborhood of their projected point (top-right plot), and jointly train the solution simplex.

Due to its distributed nature, many studies have shown that it is vulnerable to backdoor attacks.