期刊
IEEE INTERNET OF THINGS JOURNAL
卷 10, 期 11, 页码 9622-9633出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2023.3234977
关键词
Internet of Things; Servers; Training; Data models; Performance evaluation; Adaptation models; Generators; Adversarial learning; domain generalization (DG); federated learning (FL); Internet of Things (IoT)
Federated learning is a distributed machine learning technique that enables IoT devices to train an ML model jointly using a centralized server. Local data of IoT devices is protected as it never leaves the devices. To address the poor generalization performance of models trained over multisource domains, we propose federated adversarial domain generalization (FedADG) to enhance FL with domain generalization capability.
Federated learning (FL) is a distributed machine learning (ML) technique that allows numerous Internet of Things (IoT) devices to jointly train an ML model using a centralized server for help. Local data never leaves each IoT device in FL, so the local data of IoT devices are protected. In FL, distributed IoT devices usually collect their local data independently, so the data set of each IoT device may naturally form a distinct source domain. In real-world applications, the model trained over multisource domains may have poor generalization performance on unseen target domains. To address this issue, we propose federated adversarial domain generalization (FedADG) to equip FL with domain generalization capability. FedADG employs the federated adversarial learning approach to measure and align the distributions among different source domains via matching each distribution to a reference distribution. The reference distribution is adaptively generated (by accommodating all source domains) to minimize the domain shift distance during alignment. Therefore, the learned feature representation tends to be universal, and, thus, it has good generalization performance over the unseen target domains while protecting local data privacy. Intensive experiments on various data sets demonstrate that FedADG has comparable performance with the state-of-the-art.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据