This study considers a federated learning setup where cost-sensitive and strategic agents train a learning model with a server. During each round, each agent samples a minibatch of training data and sends his gradient update. As an increasing function of his minibatch size choice, the agent incurs a cost associated with the data collection, gradient computation and communication. The agents have the freedom to choose their minibatch size and may even opt out from training. To reduce his cost, an agent may diminish his minibatch size, which may also cause an increase in the noise level of the gradient update. The server can offer rewards to compensate the agents for their costs and to incentivize their participation but she lacks the capability of validating the true minibatch sizes of the agents. To tackle this challenge, the proposed reward mechanism evaluates the quality of each agent's gradient according to the its distance to a reference which is constructed from the gradients provided by other agents. It is shown that the proposed reward mechanism has a cooperative Nash equilibrium in which the agents determine the minibatch size choices according to the requests of the server.
翻译:本研究考虑了一个联合学习装置,在这种装置中,成本敏感和战略代理人用服务器培训学习模式。在每轮试验中,每个代理人都抽样收集培训数据,并发送其梯度更新。作为其微型批量选择的日益增强的功能,该代理人承担与数据收集、梯度计算和通信有关的费用。该代理人可以自由选择其小型批量大小,甚至可以选择不参加培训。为了降低成本,一个代理人可以减少其小批量尺寸,这也可能增加梯度更新的噪音水平。服务器可以提供奖励,补偿代理人的费用,鼓励他们参与,但她没有能力验证代理人真正的微型批量大小。为了应对这一挑战,拟议的奖励机制根据每个代理人的梯度与从其他代理人提供的梯度中构建的参考距离,评估每个代理人梯度的质量。证明拟议的奖励机制具有合作性纳什平衡,使代理人根据服务器的要求确定小型批量选择。