Search Results for author:
Found 2 papers, 0 papers with code
The Dog Walking Theory: Rethinking Convergence in Federated Learning
In this paper, we study the convergence of FL on non-IID data and propose a novel \emph{Dog Walking Theory} to formulate and identify the missing element in existing research.
Byzantine-Robust Federated Learning via Credibility Assessment on Non-IID Data
Federated learning is a novel framework that enables resource-constrained edge devices to jointly learn a model, which solves the problem of data protection and data islands.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
