Accelerating Fair Federated Learning: Adaptive Federated Adam

01/23/2023
by   Li Ju, et al.
0

Federated learning is a distributed and privacy-preserving approach to train a statistical model collaboratively from decentralized data of different parties. However, when datasets of participants are not independent and identically distributed (non-IID), models trained by naive federated algorithms may be biased towards certain participants, and model performance across participants is non-uniform. This is known as the fairness problem in federated learning. In this paper, we formulate fairness-controlled federated learning as a dynamical multi-objective optimization problem to ensure fair performance across all participants. To solve the problem efficiently, we study the convergence and bias of Adam as the server optimizer in federated learning, and propose Adaptive Federated Adam (AdaFedAdam) to accelerate fair federated learning with alleviated bias. We validated the effectiveness, Pareto optimality and robustness of AdaFedAdam in numerical experiments and show that AdaFedAdam outperforms existing algorithms, providing better convergence and fairness properties of the federated scheme.

READ FULL TEXT
research
09/13/2021

FedFair: Training Fair Models In Cross-Silo Federated Learning

Building fair machine learning models becomes more and more important. A...
research
10/29/2021

Improving Fairness via Federated Learning

Recently, lots of algorithms have been proposed for learning a fair clas...
research
05/26/2022

Cali3F: Calibrated Fast Fair Federated Recommendation System

The increasingly stringent regulations on privacy protection have sparke...
research
06/20/2020

FedMGDA+: Federated Learning meets Multi-objective Optimization

Federated learning has emerged as a promising, massively distributed way...
research
06/07/2022

FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning

Vertical federated learning (VFL) is a privacy-preserving machine learni...
research
11/20/2020

Towards Building a Robust and Fair Federated Learning System

Federated Learning (FL) has emerged as a promising practical framework f...
research
09/16/2020

FedSmart: An Auto Updating Federated Learning Optimization Mechanism

Federated learning has made an important contribution to data privacy-pr...

Please sign up or login with your details

Forgot password? Click here to reset