Hierarchical Federated Learning Architectures for the Metaverse
GU Cheng, LI Baochun
[Introduction] In the context of edge computing environments in general and the metaverse in particular, federated learning (FL) has emerged as a distributed machine learning paradigm that allows multiple users to collaborate on training a shared machine learning model locally, eliminating the need for uploading raw data to a central server. It is perhaps the only training paradigm that preserves the privacy of user data, which is essential for computing environments as personal as the metaverse. However, the original FL architecture proposed is not scalable to a large number of user devices in the metaverse community. To mitigate this problem, hierarchical federated learning (HFL) has been introduced as a general distributed learning paradigm, and has since then inspired and led to a number of research works. In this paper, we present several types of HFL architectures, with a special focus on the three-layer client-edge-cloud HFL architecture, which is most pertinent to the metaverse due to its delay-sensitive nature. We also examine works that take advantage of the natural layered organization of three-layer client-edge-cloud HFL to tackle some of the most challenging problems in FL within the metaverse. Finally, we outline some future research directions of HFL in the metaverse.
Waveguide Bragg Grating for Fault Localization in PON
HU Jin, LIU Xu, ZHU Songlin, ZHUANG Yudi, WU Yuejun, XIA Xiang, HE Zuyuan
[Introduction] Femtosecond laser direct inscription is a technique especially useful for prototyping purposes due to its distinctive advantages such as high fabrication accuracy, true 3D processing flexibility, and no need for mold or photomask. In this paper, we demonstrate the design and fabrication of a planar lightwave circuit (PLC) power splitter encoded with waveguide Bragg gratings (WBG) using a femtosecond laser inscription technique for passive optical network (PON) fault localization application. Both the reflected wavelengths and intervals of WBGs can be conveniently tuned. In the experiment, we succeeded in directly inscribing WBGs in 1×4 PLC splitter chips with a wavelength interval of about 4 nm and an adjustable reflectivity of up to 70% in the C-band. The proposed method is suitable for the prototyping of a PLC splitter encoded with WBG for PON fault localization applications.