Equity and Equality in Fair Federated Learning-猫眼课题宝

DOI：

发表时间：

2022

期刊：

2008 International Workshop on Content-Based Multimedia Indexing

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Hamid Mozaffari;Amir Houmansadr

联邦学习（FL）使数据所有者能够在不共享其私有数据的情况下训练共享的全局模型。不幸的是，FL容易受到内在公平性问题的影响：由于客户端数据分布的异质性，最终训练的模型可能会在参与的客户端中提供不成比例的优势。在这项工作中，我们提出了平等和公平联邦学习（E2FL），通过同时保留两个主要的公平属性，公平和平等，来产生公平的联邦学习模型。我们在不同的实际FL应用中验证了E2FL的效率和公平性，并表明E2FL在结果效率、不同群体的公平性和所有个体客户端的公平性方面优于现有基准。

Federated Learning (FL) enables data owners to train a shared global model without sharing their private data. Unfortunately, FL is susceptible to an intrinsic fairness issue: due to heterogeneity in clients’ data distributions, the final trained model can give disproportionate advantages across the participating clients. In this work, we present Equal and Equitable Federated Learning (E2FL) to produce fair federated learning models by preserving two main fairness properties, equity and equality, concurrently . We validate the efficiency and fairness of E2FL in different real-world FL applications, and show that E2FL outperforms existing baselines in terms of the resulting efficiency, fairness of different groups, and fairness among all individual clients.

Equity and Equality in Fair Federated Learning

文献摘要

相似文献