GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning

no code implementations • 7 Jan 2024 • Syed Irfan Ali Meerza, Luyang Liu, Jiaxin Zhang, Jian Liu

Specifically, we utilize constrained optimization to enforce local fairness on the client side and adopt a fairness-aware clustering-based aggregation on the server to further ensure the global model fairness across different sensitive groups while maintaining high utility.

Fairness Federated Learning

RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense

no code implementations • 11 Apr 2023 • Yue Cui, Syed Irfan Ali Meerza, Zhuohang Li, Luyang Liu, Jiaxin Zhang, Jian Liu

In this paper, we seek to reconcile utility and privacy in FL by proposing a user-configurable privacy defense, RecUP-FL, that can better focus on the user-specified sensitive attributes while obtaining significant improvements in utility over traditional defenses.

Adversarial Attack Attribute +4