Towards Fair Federated Learning with Zero-Shot Data Augmentation

by   Weituo Hao, et al.

Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data. Although it is recognized that statistical heterogeneity of the client local data yields slower global model convergence, it is less commonly recognized that it also yields a biased federated global model with a high variance of accuracy across clients. In this work, we aim to provide federated learning schemes with improved fairness. To tackle this challenge, we propose a novel federated learning system that employs zero-shot data augmentation on under-represented data to mitigate statistical heterogeneity and encourage more uniform accuracy performance across clients in federated networks. We study two variants of this scheme, Fed-ZDAC (federated learning with zero-shot data augmentation at the clients) and Fed-ZDAS (federated learning with zero-shot data augmentation at the server). Empirical results on a suite of datasets demonstrate the effectiveness of our methods on simultaneously improving the test accuracy and fairness.



There are no comments yet.


page 8


Personalized Federated Learning through Local Memorization

Federated learning allows clients to collaboratively learn statistical m...

Fairness and Accuracy in Federated Learning

In the federated learning setting, multiple clients jointly train a mode...

Toward Understanding the Influence of Individual Clients in Federated Learning

Federated learning allows mobile clients to jointly train a global model...

WAFFLe: Weight Anonymized Factorization for Federated Learning

In domains where data are sensitive or private, there is great value in ...

GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization

Since data is presented long-tailed in reality, it is challenging for Fe...

Coded Computing for Low-Latency Federated Learning over Wireless Edge Networks

Federated learning enables training a global model from data located at ...

Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning

Federated learning is a challenging optimization problem due to the hete...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.