The Dog Walking Theory: Rethinking Convergence in Federated Learning

arXiv:2404.11888v1 Announce Type: new
Abstract: Federated learning (FL) is a collaborative learning paradigm that allows different clients to train one powerful global model without sharing their private data. Although FL has demonstrated promising results in various applications, it is known to suffer from convergence issues caused by the data distribution shift across different clients, especially on non-independent and identically distributed (non-IID) data. In this paper, we study the convergence of FL on non-IID data and propose a novel \emph{Dog Walking …

abstract applications arxiv collaborative convergence cs.ai cs.lg data distribution dog federated learning global paradigm private data results shift theory train type walking