In federated learning, differences in the data or objectives between the participating nodes motivate approaches to train a personalized machine learning model for each node. One such approach is weighted averaging between a locally trained model and the global model. In this theoretical work, we study weighted model averaging for arbitrary scalar mean estimation problems under minimal assumptions on the distributions. In a variant of the bias-variance trade-off, we find that there is always some positive amount of model averaging that reduces the expected squared error compared to the local model, provided only that the local model has a non-zero variance. Further, we quantify the (possibly negative) benefit of weighted model averaging as a function of the weight used and the optimal weight. Taken together, this work formalizes an approach to quantify the value of personalization in collaborative learning and provides a framework for future research to test the findings in multivariate parameter estimation and under a range of assumptions.
翻译:在联合学习中,参与节点之间在数据或目标上的差异激励了为每个节点培训个性化机器学习模式的方法。其中一种方法在本地培训模式和全球模式之间加权平均。在这种理论工作中,我们研究的是根据分配最低假设任意的天平平均估计问题平均加权模型。在偏差权衡的变式中,我们发现,平均模型总是有一些正数,能够比当地模式减少预期的平方差,只要当地模式有非零差。此外,我们用加权模型的平均效益(可能是负数)作为所用重量和最佳重量的函数加以量化。加在一起,这项工作形成了一种在合作学习中量化个性化价值的方法,并为未来研究提供了一个框架,以测试多变参数估计和一系列假设中的调查结果。