联邦学习的个性化解耦：一种可解释视角
Personalization Disentanglement for Federated Learning: An explainable perspective
AI总结：
本文提出FedDVA框架，通过双编码器将潜在表示显式解耦为共享知识与客户端个性化两部分，以可解释方式改进个性化联邦学习，并可兼容现有FL方法，实验证明其显著优于普通方法。
摘要：
个性化联邦学习（PFL）通过平衡跨客户端的知识共享与每个客户端的模型个性化，联合训练多种本地模型。本文通过将潜在表示显式解耦为两部分来解决PFL问题，以分别捕获共享知识和客户端特定的个性化信息，从而带来更可靠、更有效的PFL。该解耦由一种新颖的联邦双变分自编码器（Federated Dual Variational Autoencoder，FedDVA）实现，它采用两个编码器来推断这两类表示。FedDVA能够更好地理解PFL中全局知识共享与本地个性化之间的权衡。此外，它可以与现有FL方法集成，并将它们转化为适用于异构下游任务的个性化模型。大量实验验证了解耦带来的优势，并表明使用解耦表示训练的模型显著优于那些普通方法。
英文摘要：
Personalized federated learning (PFL) jointly trains a variety of local models through balancing between knowledge sharing across clients and model personalization per client. This paper addresses PFL via explicit disentangling latent representations into two parts to capture the shared knowledge and client-specific personalization, which leads to more reliable and effective PFL. The disentanglement is achieved by a novel Federated Dual Variational Autoencoder (FedDVA), which employs two encoders to infer the two types of representations. FedDVA can produce a better understanding of the trade-off between global knowledge sharing and local personalization in PFL. Moreover, it can be integrated with existing FL methods and turn them into personalized models for heterogeneous downstream tasks. Extensive experiments validate the advantages caused by disentanglement and show that models trained with disentangled representations substantially outperform those vanilla methods.
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。
