CDMA: A Practical Cross-Device Federated Learning Algorithm for General Minimax Problems

TL;DR

This paper introduces CDMA, a practical federated learning algorithm designed for minimax problems in cross-device settings, addressing challenges like client unreliability and slow networks with theoretical guarantees and empirical validation.

Contribution

The paper presents the first practical cross-device federated minimax algorithm, CDMA, featuring a novel response mechanism and lightweight correction to handle client unreliability and network issues.

Findings

CDMA achieves theoretical convergence guarantees.

Experimental results show CDMA's efficiency in various tasks.

CDMA outperforms existing methods in cross-device settings.

Abstract

Minimax problems arise in a wide range of important applications including robust adversarial learning and Generative Adversarial Network (GAN) training. Recently, algorithms for minimax problems in the Federated Learning (FL) paradigm have received considerable interest. Existing federated algorithms for general minimax problems require the full aggregation (i.e., aggregation of local model information from all clients) in each training round. Thus, they are inapplicable to an important setting of FL known as the cross-device setting, which involves numerous unreliable mobile/IoT devices. In this paper, we develop the first practical algorithm named CDMA for general minimax problems in the cross-device FL setting. CDMA is based on a Start-Immediately-With-Enough-Responses mechanism, in which the server first signals a subset of clients to perform local computation and then starts to aggregate the local results reported by clients once it receives responses from enough clients in each round. With this mechanism, CDMA is resilient to the low client availability. In addition, CDMA is incorporated with a lightweight global correction in the local update steps of clients, which mitigates the impact of slow network connections. We establish theoretical guarantees of CDMA under different choices of hyperparameters and conduct experiments on AUC maximization, robust adversarial network training, and GAN training tasks. Theoretical and experimental results demonstrate the efficiency of CDMA.