arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2108.07313cs.LGcs.DCmath.OCstat.ML
收藏

联邦渐近:一个比较联邦学习算法的模型

Federated Asymptotics: a model to compare federated learning algorithms

Stanford University(斯坦福大学)

Gary Cheng, Karan Chadha, John Duchi

摘要:

我们提出了一个渐进的框架来分析(个性化)联邦学习算法的性能。在这个新的框架中,我们将联邦学习制定为多标准目标,其目标是使用来自所有客户端的信息最小化每个客户端的损失。我们分析一个线性回归模型,对于一个给定的客户端,我们可以在理论上比较各种算法在高维渐近极限的性能。这种渐进多准则方法自然地模拟了联邦学习的高维、多设备性质。这些工具对联邦场景中个性化和信息共享的好处做出了相当精确的预测-至少在我们的(程式化)模型中-包括具有简单客户端微调的联邦平均实现了与更复杂的元学习和近似正则化方法相同的渐近风险,并且优于没有个性化的联邦平均。我们在EMNIST、CIFAR-100、Shakespeare和Stack Overflow数据集的联邦版本上评估了这些预测,实验证实了理论预测,表明这些框架可能为实际算法开发提供有用的指导。

英文摘要:

We propose an asymptotic framework to analyze the performance of (personalized) federated learning algorithms. In this new framework, we formulate federated learning as a multi-criterion objective, where the goal is to minimize each client's loss using information from all of the clients. We analyze a linear regression model where, for a given client, we may theoretically compare the performance of various algorithms in the high-dimensional asymptotic limit. This asymptotic multi-criterion approach naturally models the high-dimensional, many-device nature of federated learning. These tools make fairly precise predictions about the benefits of personalization and information sharing in federated scenarios -- at least in our (stylized) model -- including that Federated Averaging with simple client fine-tuning achieves the same asymptotic risk as the more intricate meta-learning and proximal-regularized approaches and outperforming Federated Averaging without personalization. We evaluate these predictions on federated versions of the EMNIST, CIFAR-100, Shakespeare, and Stack Overflow datasets, where the experiments corroborate the theoretical predictions, suggesting such frameworks may provide a useful guide to practical algorithmic development.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑