Distributed Online Learning With Multiple Kernels
- Authors
- Hong, Songnam; Chae, Jeongmin
- Issue Date
- Mar-2023
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Decentralized federated learning; distributed online learning; multiple kernel learning (MKL); online learning
- Citation
- IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, v.34, no.3, pp.1263 - 1277
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
- Volume
- 34
- Number
- 3
- Start Page
- 1263
- End Page
- 1277
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/185441
- DOI
- 10.1109/TNNLS.2021.3105146
- ISSN
- 2162-237X
- Abstract
- We consider the problem of learning a nonlinear function over a network of learners in a fully decentralized fashion Online learning is additionally assumed where every learner receives continuous streaming data locally This learning model is called a fully distributed online learning or a fully decentralized online federated learning). For this model, we propose a novel learning framework with multiple kernels, which is named DOMKL. The proposed DOMKL is devised by harnessing the principles of an online alternating direction method of multipliers and a distributed Hedge algorithm. We theoretically prove that DOMKL over T time slots can achieve an optimal sublinear regret O(√T), implying that every learner in the network can learn a common function having a diminishing gap from the best function in hindsight. Our analysis also reveals that DOMKL yields the same asymptotic performance as the state-of-the-art centralized approach while keeping local data at edge learners. Via numerical tests with real datasets, we demonstrate the effectiveness of the proposed DOMKL on various online regression and time-series prediction tasks.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.