Convergence Analysis of Sequential Federated Learning on Heterogeneous Data

Yipeng Li, Xinchen Lyu

Keywords: Federated Learning, Convergence analysis

TL;DR: This paper aims to derive the convergence guarantee of Sequential Federated Learning and compare it with Parallel Federated Learning (FedAvg) theoretically.

Abstract: There are two categories of methods in Federated Learning (FL) for joint training across multiple clients: i) parallel FL (PFL), where clients train models in a parallel manner; and ii) sequential FL (SFL), where clients train models in a sequential manner. In contrast to that of PFL, the convergence theory of SFL on heterogeneous data is still lacking. In this paper, we establish the convergence guarantees of SFL for strongly/general/non-convex objectives on heterogeneous data. The convergence guarantees of SFL are better than that of PFL on heterogeneous data with both full and partial client participation. Experimental results validate the counterintuitive analysis result that SFL outperforms PFL on extremely heterogeneous data in cross-device settings.

Submission Number: 13660