QuPeL：量化个性化及其在联邦学习中的应用
QuPeL: Quantized Personalization with Applications to Federated Learning
摘要：
传统上，联邦学习（FL）旨在训练单个全局模型，同时协作使用多个客户端和服务器。FL算法面临的两个自然挑战是跨客户端的数据异构性和客户端与{\em多样资源}的协作。在这项工作中，我们介绍了一个\textit{quantized}和\textit{personalized} FL算法QuPeL，有利于集体训练与异构客户端，同时尊重资源的多样性。为了个性化，我们允许客户端根据其资源使用不同的量化参数来学习\textit{compressed personalized models}。为此，首先，我们提出了一个算法，通过一个宽松的优化问题，量化值也被优化的学习量化模型。当参与（联合）学习过程的每个客户端对量化模型有不同的要求（在值和精度方面）时，我们通过针对全局训练模型引入本地客户端目标的惩罚项来制定量化个性化框架，以鼓励协作。我们开发了一个交替的近端梯度更新来解决这个量化的个性化问题，我们分析了它的收敛性。在数值上，我们表明，优化的量化水平提高了性能，我们验证QuPeL优于FedAvg和本地培训的客户端在异构环境中。
英文摘要：
Traditionally, federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. Two natural challenges that FL algorithms face are heterogeneity in data across clients and collaboration of clients with {\em diverse resources}. In this work, we introduce a \textit{quantized} and \textit{personalized} FL algorithm QuPeL that facilitates collective training with heterogeneous clients while respecting resource diversity. For personalization, we allow clients to learn \textit{compressed personalized models} with different quantization parameters depending on their resources. Towards this, first we propose an algorithm for learning quantized models through a relaxed optimization problem, where quantization values are also optimized over. When each client participating in the (federated) learning process has different requirements of the quantized model (both in value and precision), we formulate a quantized personalization framework by introducing a penalty term for local client objectives against a globally trained model to encourage collaboration. We develop an alternating proximal gradient update for solving this quantized personalization problem, and we analyze its convergence properties. Numerically, we show that optimizing over the quantization levels increases the performance and we validate that QuPeL outperforms both FedAvg and local training of clients in a heterogeneous setting.
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。
