Edge device participation in federating learning (FL) has been typically studied under the lens of device-server communication (e.g., device dropout) and assumes an undying desire from edge devices to participate in FL. As a result, current FL frameworks are flawed when implemented in real-world settings, with many encountering the free-rider problem. In a step to push FL towards realistic settings, we propose RealFM: the first truly federated mechanism which (1) realistically models device utility, (2) incentivizes data contribution and device participation, and (3) provably removes the free-rider phenomena. RealFM does not require data sharing and allows for a non-linear relationship between model accuracy and utility, which improves the utility gained by the server and participating devices compared to non-participating devices as well as devices participating in other FL mechanisms. On real-world data, RealFM improves device and server utility, as well as data contribution, by up to 3 magnitudes and 7x respectively compared to baseline mechanisms.

翻译：边缘设备参与联邦学习（FL）通常被置于设备-服务器通信（例如设备退出）的视角下进行研究，并假设边缘设备对参与FL有着永不衰减的渴望。因此，现有FL框架在实际部署中存在缺陷，许多框架面临搭便车问题。为推动FL向真实场景迈进，我们提出RealFM：首个真正联邦化的机制，它能够（1）真实地建模设备效用，（2）激励数据贡献与设备参与，以及（3）可证明地消除搭便车现象。RealFM无需数据共享，并允许模型准确率与效用之间存在非线性关系，相较于非参与设备及参与其他FL机制的设备，这能提升服务器与参与设备获得的效用。在实际数据集上，相比基线机制，RealFM将设备与服务器效用及数据贡献分别提升至多3个数量级和7倍。