Federated learning (FL) is a new machine learning paradigm to overcome the challenge of data silos and has garnered significant attention. However, through our observations, a globally effective trained model may performance disparities in different clients. This implies that the jointly trained models by clients may lead to unfair outcomes. On the other hand, relevant studies indicate that the transmission of gradients or models in federated learning can also give rise to privacy leakage issues, such as membership inference attacks. To address the first issue mentioned above, we propose a federated algorithm with fairness, termed FedFair. Building upon FedFair, we introduce privacy protection to form the FedFDP algorithm to address the second issue mentioned above. In FedFDP, we devise a fairness-aware clipping strategy to achieve differential privacy while adjusting fairness. Additionally, for the extra uploaded loss values, we present an adaptive clipping approach to maximize utility. Furthermore, we theoretically prove that our algorithm converges and ensures differential privacy. Lastly, Extensive experimental results demonstrate that FedFair and FedFDP significantly outperforms state-of-the-art solutions in terms of model performance and fairness. The code is accessible at https://anonymous.4open.science/r/FedFDP-E754.

翻译：联邦学习（FL）是一种克服数据孤岛挑战的新型机器学习范式，并已引起广泛关注。然而，我们观察到全局训练效果良好的模型可能在不同客户端上表现出性能差异，这意味着客户端联合训练的模型可能导致不公平的结果。另一方面，相关研究表明，联邦学习中梯度或模型的传输也会引发隐私泄露问题，例如成员推断攻击。针对上述第一个问题，我们提出了一种具有公平性的联邦算法FedFair。在FedFair基础上，我们引入隐私保护机制形成FedFDP算法以解决第二个问题。在FedFDP中，我们设计了一种公平感知的裁剪策略，在调整公平性的同时实现差分隐私。此外，针对额外上传的损失值，我们提出了一种自适应裁剪方法来最大化效用。我们从理论上证明了算法的收敛性和差分隐私保证。最后，大量实验结果表明，FedFair和FedFDP在模型性能和公平性方面显著优于现有最优方案。相关代码可在https://anonymous.4open.science/r/FedFDP-E754获取。