A Fair Federated Learning Framework With Reinforcement Learning

05/26/2022
by   Yaqi Sun, et al.
0

Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. However, heterogeneous data distributions over different clients remain a challenge to mainstream FL algorithms, which may cause slow convergence, overall performance degradation and unfairness of performance across clients. To address these problems, in this study we propose a reinforcement learning framework, called PG-FFL, which automatically learns a policy to assign aggregation weights to clients. Additionally, we propose to utilize Gini coefficient as the measure of fairness for FL. More importantly, we apply the Gini coefficient and validation accuracy of clients in each communication round to construct a reward function for the reinforcement learning. Our PG-FFL is also compatible to many existing FL algorithms. We conduct extensive experiments over diverse datasets to verify the effectiveness of our framework. The experimental results show that our framework can outperform baseline methods in terms of overall performance, fairness and convergence speed.

READ FULL TEXT
research
05/20/2022

E2FL: Equal and Equitable Federated Learning

Federated Learning (FL) enables data owners to train a shared global mod...
research
10/27/2021

FedPrune: Towards Inclusive Federated Learning

Federated learning (FL) is a distributed learning technique that trains ...
research
10/12/2022

Aergia: Leveraging Heterogeneity in Federated Learning Systems

Federated Learning (FL) is a popular approach for distributed deep learn...
research
06/26/2023

Correct orchestration of Federated Learning generic algorithms: formalisation and verification in CSP

Federated learning (FL) is a machine learning setting where clients keep...
research
02/03/2022

Equality Is Not Equity: Proportional Fairness in Federated Learning

Ensuring fairness of machine learning (ML) algorithms is becoming an inc...
research
12/12/2022

Collaborating Heterogeneous Natural Language Processing Tasks via Federated Learning

The increasing privacy concerns on personal private text data promote th...
research
04/30/2021

Federated Learning with Fair Averaging

Fairness has emerged as a critical problem in federated learning (FL). I...

Please sign up or login with your details

Forgot password? Click here to reset