no code implementations • 6 Feb 2024 • Meiying Zhang, Huan Zhao, Sheldon Ebron, Kan Yang
In this paper, we introduce a novel method called Fair, Robust, and Efficient Client Assessment (FRECA) for quantifying client contributions in FL.
no code implementations • 5 Dec 2023 • Meiying Zhang, Huan Zhao, Sheldon Ebron, Ruitao Xie, Kan Yang
Then, we formulate the initial client pool selection problem into an optimization problem that aims to maximize the overall scores of selected clients within a given budget and propose a greedy algorithm to solve it.
no code implementations • 17 Nov 2023 • Sheldon C. Ebron Jr., Kan Yang
Existing defenses measure the deviation of each update from a 'ground-truth model update.'