Federated Learning (FL) is a decentralized machine learning framework that enables collaborative model training while respecting data privacy. In various applications, non-uniform availability or participation of users is unavoidable due to an adverse or stochastic environment, the latter often being uncontrollable during learning. Here, we posit a generic user selection mechanism implementing a possibly randomized, stationary selection policy, suggestively termed as a Random Access Model (RAM). We propose a new formulation of the FL problem which effectively captures and mitigates limited participation of data originating from infrequent, or restricted users, at the presence of a RAM. By employing the Conditional Value-at-Risk (CVaR) over the (unknown) RAM distribution, we extend the expected loss FL objective to a risk-aware objective, enabling the design of an efficient training algorithm that is completely oblivious to the RAM, and with essentially identical complexity as FedAvg. Our experiments on synthetic and benchmark datasets show that the proposed approach achieves significantly improved performance as compared with standard FL, under a variety of setups.

翻译：联邦学习（FL）是一种去中心化的机器学习框架，能够在保护数据隐私的同时实现协作式模型训练。在各种应用中，由于不利环境或随机环境的影响，用户的非均匀可用性或参与是不可避免的，后者在学习过程中往往难以控制。本文提出了一种通用的用户选择机制，该机制实现了一种可能随机化的平稳选择策略，我们将其称为随机接入模型（RAM）。我们提出了联邦学习问题的一种新表述，在存在RAM的情况下，有效捕捉并缓解来自不频繁或受限用户的有限数据参与。通过基于（未知的）RAM分布采用条件风险价值（CVaR），我们将期望损失联邦学习目标扩展为风险感知目标，从而设计出一种完全对RAM无感知的高效训练算法，其复杂度与FedAvg基本一致。我们在合成数据集和基准数据集上的实验表明，在多种设置下，所提方法相比标准联邦学习取得了显著更优的性能。