A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can simultaneously capture generalization and personalization capabilities for efficient inference across resource-constrained clients (e.g., mobile/IoT devices). Our key idea is to split the full ML model into client-side and server-side components, and impose different roles to them: the client-side model is trained to have strong personalization capability optimized to each client's main task, while the server-side model is trained to have strong generalization capability for handling all clients' out-of-distribution tasks. We analytically characterize the convergence behavior of SplitGP, revealing that all client models approach stationary points asymptotically. Further, we analyze the inference time in SplitGP and provide bounds for determining model split ratios. Experimental results show that SplitGP outperforms existing baselines by wide margins in inference time and test accuracy for varying amounts of out-of-distribution samples.
翻译:提供边缘AI服务的一个基本挑战是需要一种机器学习(ML)模式,既能实现个性化(即对个别客户),又能实现一般化(即对隐蔽数据)特性(即对隐蔽数据)的普通化(即对隐蔽数据)特性。联邦学习(FL)的现有技术在这些目标之间遇到了巨大的权衡,并在培训和推论期间对边缘设备规定了大量的计算要求。在本文件中,我们提议SplitGP,这是一个新的分解学习解决方案,可以同时捕捉对受资源限制的客户(例如移动/IoT设备)进行有效推断的概括化和个性化能力。我们的主要想法是将完整的ML模型分为客户端和服务器端组成部分,并赋予它们不同的作用:客户端学习(FL)的现有技术在这些目标之间遇到了巨大的权衡,并在每个客户的主要任务中实现了巨大的计算要求。我们提议SlipGPGP, 新的分解式学习方法可以捕捉到对受资源限制的客户群体(例如移动/IoT设备)的有效推断。我们分析后发现,所有客户模式采用固定式的固定点的固定点,从客户端和服务器的分流中提供不同的精确度。我们进一步分析了在模型中分析现有模型中用来分析现有模型的精确度。我们从模型分析了现有模型的模型的分差分解的分解的分差差间分析了时间差差差差差差间,以显示的精确度,以便的精确度。我们。