Accelerating distributed online meta-learning via multi-agent collaboration under limited communication

Sen Lin, Mehmet Dedeoglu, Junshan Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Online meta-learning is emerging as an enabling technique for achieving edge intelligence in the IoT ecosystem. Nevertheless, to learn a good meta-model for within-task fast adaptation, a single agent alone has to learn over many tasks, and this is the so-called 'cold-start' problem. Observing that in a multi-agent network the learning tasks across different agents often share some model similarity, we ask the following fundamental question: "Is it possible to accelerate the online meta-learning across agents via limited communication and if yes how much benefit can be achieved?"To answer this question, we propose a multi-agent online meta-learning framework and cast it as an equivalent two-level nested online convex optimization (OCO) problem. By characterizing the upper bound of the agent-task-averaged regret, we show that the performance of multi-agent online meta-learning depends heavily on how much an agent can benefit from the distributed network-level OCO for meta-model updates via limited communication, which however is not well understood. To tackle this challenge, we devise a distributed online gradient descent algorithm with gradient tracking where each agent tracks the global gradient using only one communication step with its neighbors per iteration, and it results in an average regret O(T/N) per agent, indicating that a factor of 1/N speedup over the optimal single-agent regret O(T) after T iterations, where N is the number of agents. Building on this sharp performance speedup, we next develop a multi-agent online meta-learning algorithm and show that it can achieve the optimal task-average regret at a faster rate of O(1 N/T) via limited communication, compared to single-agent online meta-learning. Extensive experiments corroborate the theoretic results.

Original languageEnglish (US)
Title of host publicationMobiHoc 2021 - Proceedings of the 2021 22nd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing
PublisherAssociation for Computing Machinery
Pages261-270
Number of pages10
ISBN (Electronic)9781450385589
DOIs
StatePublished - Jul 26 2021
Externally publishedYes
Event22nd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, MobiHoc 2021 - Shanghai, China
Duration: Jul 26 2021Jul 29 2021

Publication series

NameProceedings of the International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc)

Conference

Conference22nd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, MobiHoc 2021
Country/TerritoryChina
CityShanghai
Period7/26/217/29/21

Keywords

  • Distributed online convex optimization
  • Gradient tracking
  • Multi-agent network
  • Online meta-learning

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Networks and Communications
  • Software

Fingerprint

Dive into the research topics of 'Accelerating distributed online meta-learning via multi-agent collaboration under limited communication'. Together they form a unique fingerprint.

Cite this