Training Fair Models in Federated Learning without Data Privacy Infringement
This addresses the problem of ensuring fairness and privacy in collaborative AI for parties with sensitive data, representing a novel integration rather than an incremental step.
The paper tackles the challenge of training fair machine learning models in federated learning without violating data privacy, by proposing FedFair, a framework that estimates fairness privately and trains models with high performance, as demonstrated on three real-world datasets.
Training fair machine learning models becomes more and more important. As many powerful models are trained by collaboration among multiple parties, each holding some sensitive data, it is natural to explore the feasibility of training fair models in federated learning so that the fairness of trained models, the data privacy of clients, and the collaboration between clients can be fully respected simultaneously. However, the task of training fair models in federated learning is challenging, since it is far from trivial to estimate the fairness of a model without knowing the private data of the participating parties, which is often constrained by privacy requirements in federated learning. In this paper, we first propose a federated estimation method to accurately estimate the fairness of a model without infringing the data privacy of any party. Then, we use the fairness estimation to formulate a novel problem of training fair models in federated learning. We develop FedFair, a well-designed federated learning framework, which can successfully train a fair model with high performance without data privacy infringement. Our extensive experiments on three real-world data sets demonstrate the excellent fair model training performance of our method.