Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Scalable Federated Learning over Passive Optical Networks

Not Accessible

Your library or personal account may give you access

Abstract

Two-step aggregation is introduced to facilitate scalable federated learning (SFL) over passive optical networks (PONs). Results reveal that the SFL keeps the required PON upstream bandwidth constant regardless of the number of involved clients, while bringing ~10% learning accuracy improvement.

© 2021 The Author(s)

PDF Article
More Like This
High-Precision Edge-Cloud Collaboration with Federated Learning in Edge Optical Network

Chao Li, Hui Yang, Quiyan Yao, Zhengjie Sun, and Jie Zhang
W6A.11 Optical Fiber Communication Conference (OFC) 2021

Federated Transfer Learning-based Data Security Assurance in Edge Optical Networks for IoT Applications

Qiuyan Yao, Hui Yang, Bowen Bao, Zhengjie Sun, Chao Li, Jie Zhang, and Shanguo Huang
W2C.3 Asia Communications and Photonics Conference (ACP) 2021

Multi-Agent Federated Reinforcement Learning for Privacy-enhanced Service Provision in Multi-domain Optical Network

Haiyu Liu, Rentao Gu, Zhekang Li, and Yuefeng Ji
T1C.3 Asia Communications and Photonics Conference (ACP) 2021

Poster Presentation

Media 1: PDF (1357 KB)     
Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All Rights Reserved