FedQOGD: Federated Quantized Online Gradient Descent with Distributed Time-Series Data
- Authors
- Park, Jonghwan; Kwon, Dohyeok; Hong, Songnam
- Issue Date
- Apr-2022
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- distributed learning; Federated learning; online learning; regret analysis
- Citation
- IEEE Wireless Communications and Networking Conference, WCNC, v.2022-April, pp.536 - 541
- Indexed
- SCOPUS
- Journal Title
- IEEE Wireless Communications and Networking Conference, WCNC
- Volume
- 2022-April
- Start Page
- 536
- End Page
- 541
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/138739
- DOI
- 10.1109/WCNC51071.2022.9771579
- ISSN
- 1525-3511
- Abstract
- We investigate an online federated learning (in short, OFL), in which many edge nodes receive their own time-series data and train a sequence of global models under the orchestration of a central server while keeping data localized. In this framework, we propose a communication efficient federated quantized online gradient descent (FedQOGD) by means of a stochastic quantization and partial node participation. We theoretically prove that FedQOGD over T time slots can achieve an optimal sublinear regret bound {mathcal{O}(sqrt T ) for any quantization level (e.g., 1-level quantization), even when every node can participate in a learning process sporadically. Our analysis reveals that FedQOGD yields the same asymptotic performance as the centralized counterpart (i.e., all local data are gathered at the central server) while having a low-communication overhead and preserving an edge-node privacy. Finally, we verify the effectiveness of our algorithm via experiments with a real-world MNIST dataset on online classification task.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/138739)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.