Federated learning (FL) is a heavily promoted approach for training ML models on sensitive data, e.g., text typed by users on their smartphones. FL is expressly designed for training on data that are unbalanced and non-iid across the participants. To ensure privacy and integrity of the fedeated model, latest FL approaches use differential privacy or robust aggregation. We look at FL from the \emph{local} viewpoint of an individual participant and ask: (1) do participants have an incentive to participate in FL? (2) how can participants \emph{individually} improve the quality of their local models, without re-designing the FL framework and/or involving other participants? First, we show that on standard tasks such as next-word prediction, many participants gain no benefit from FL because the federated model is less accurate on their data than the models they can train locally on their own. Second, we show that differential privacy and robust aggregation make this problem worse by further destroying the accuracy of the federated model for many participants. Then, we evaluate three techniques for local adaptation of federated models: fine-tuning, multi-task learning, and knowledge distillation. We analyze where each is applicable and demonstrate that all participants benefit from local adaptation. Participants whose local models are poor obtain big accuracy improvements over conventional FL. Participants whose local models are better than the federated model\textemdash and who have no incentive to participate in FL today\textemdash improve less, but sufficiently to make the adapted federated model better than their local models.
翻译:联邦学习(FL)是一种大力推广的方法,用于培训敏感数据ML模型,例如,用户在智能手机上输入文字。FL明确设计用于培训参与者之间不平衡和非二的数据。为了确保Fedeed模型的隐私和完整性,最新的FL方法使用不同的隐私或强力聚合。我们从个人参与者的方观点来看FL,并询问:(1)参与者是否有参加FL的动力?(2)参与者如何能够提高当地模型的质量,而不重新指定FL框架和/或让其他参与者参与?首先,我们显示,在诸如下一个词预测等标准任务方面,许多参与者没有从FL获得任何好处,因为FL的最新模型在他们的数据上比他们自己在当地培训的模型更准确。第二,我们从一个个体参与者的角度来看FL的模型差异隐私和稳健的汇总使得这一问题更加糟糕,因为它进一步破坏了Federferd模型的准确性,但是对许多参与者来说,我们评估了当地更新FL框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架框架的改进的改进的改进的三种改进的改进的改进,每个参与者都不断改进的改进。我们每个参与者都不断改进的改进,学习的改进。