Personalized Online Federated Learning for IoT/CPS: Challenges and Future Directions
Personalized Online Federated Learning for IoT/CPS: Challenges and Future Directions
复制标题
DOI：
10.1109/iotm.001.2200178
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Vinay Chakravarthi Gogineni;Stefan Werner;François Gauthier;Yih-Fang Huang;A. Kuh
中科院分区：
文献类型：
--
作者：
Vinay Chakravarthi Gogineni;Stefan Werner;François Gauthier;Yih-Fang Huang;A. Kuh
近年来，由于其隐私能力，联邦学习（FL）已成为分发学习的强大范式。通过使用FL，Edge设备网络可以做出智能决策，而无需将其数据公开给他人。尽管它取得了成功，但传统的FL并不非常适合许多实用应用，例如涉及涉及图像Internet（IoT）或网络物理系统（CPS）的应用程序，其中数据访问可能是间歇性的，而Edge设备为半度 - 与设备特异性动态行为特征无关。这些设备在这里被称为半独立设备，因为它们需要根据自己的数据和设备特性做出决策，通常与其他设备以及从网络中其他设备获得的信息无关。此外，随着新信息的可用，传统佛罗里达州必须重复整个学习过程，并且可能无法为参与者提供及时和量身定制的解决方案。另一方面，个性化的在线FL保留了合作和隐私的方面，同时从间歇性数据实时学习。它进一步使设备能够学习对设备定制的模型及其执行的特定任务。鉴于这些原因，个性化的在线 - FL是学习依赖于异质数据流的应用程序的理想选择，而本地优化是有益的。在这项工作中，我们希望引起人们对这个新的学习范式的关注，其中提供了一些可以从中受益的应用程序，并强调了研究社区在开发成功的个性化在线FL方面面临的主要挑战。
In recent years, federated learning (FL) has emerged as a powerful paradigm for distributed learning thanks to its privacy-preserving capabilities. With the use of FL, a network of edge devices can make intelligent decisions without exposing their data to others. Despite its success, the traditional FL is not well suited to many practical applications such as those that involve the internet-of-things (IoT) or cyber-physical systems (CPS), where data access can be intermittent, and edge devices are semi-independent with device-specific dynamic behavior characteristics. Those devices are referred to here as semi-independent devices since they need to make decisions based on their own data and device characteristics, often independent of other devices and the information obtained from other devices in the network. Additionally, as new information becomes available, traditional FL must repeat the entire learning process and may not be able to provide timely and tailored solutions to participants. Personalized online FL, on the other hand, retains the collaborative and privacy-preserving aspects while learning in real time from intermittent data. It further enables devices to learn models customized to the device and the specific tasks it performs. In light of these reasons, personalized Online-FL is ideal for applications where the learning relies on heterogeneous data streams, and local optimization is beneficial. In this work, we want to bring attention to this new learning paradigm, present a few of the applications that could benefit from it, and highlight the principal challenges the research community faces in developing successful personalized Online-FL.