FedCF: Fair Federated Conformal Prediction
This work addresses fairness in federated learning for applications requiring uncertainty quantification, but it is incremental as it adapts an existing fairness method to a new setting.
The paper tackles the problem of ensuring fairness in uncertainty quantification for federated learning models by extending Conformal Fairness to a federated setting, resulting in a framework that audits fairness gaps across demographic groups with empirical validation on multiple datasets.
Conformal Prediction (CP) is a widely used technique for quantifying uncertainty in machine learning models. In its standard form, CP offers probabilistic guarantees on the coverage of the true label, but it is agnostic to sensitive attributes in the dataset. Several recent works have sought to incorporate fairness into CP by ensuring conditional coverage guarantees across different subgroups. One such method is Conformal Fairness (CF). In this work, we extend the CF framework to the Federated Learning setting and discuss how we can audit a federated model for fairness by analyzing the fairness-related gaps for different demographic groups. We empirically validate our framework by conducting experiments on several datasets spanning multiple domains, fully leveraging the exchangeability assumption.