AdaptPSOFL: Adaptive Particle Swarm Optimization-Based Layer Offloading Framework for Federated Learning

Rachit Verma, Shajulin Benedict

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Following the rising privacy requirement enforced by regulations such as the European General Data Protection Regulation and the HIPAA, the centralized training of machine learning models has become difficult. Federated learning has come under extensive adoption because it allows clients to train a local model on a local dataset and then send the model to a server for aggregation. This aspect allows clients to preserve the privacy of their local data, while also allowing the training of a global model. A new area of study that is emerging is the possibility of offloading the training of the local model between a client and a server to influence the training time of the model. Studies such as FedAdapt use a reinforcement learning agent to decide the optimal split between a client and a server. In our study, we determine the optimal split between a client and server by formulating an optimization problem that simultaneously minimizes the CPU utilization and the round execution time while considering the number of layers placed on the client as decision variables. We apply particle swarm optimization to approach the optimization problem. Based on our experiments, we observed that our scheme outperforms FedAdapt and classic federated learning on the combined objectives by 36.60% and 36.73% on average respectively.

Original languageEnglish
Title of host publication4th International Conference on Image Processing and Capsule Networks - ICIPCN 2023
EditorsSubarna Shakya, João Manuel R.S. Tavares, Antonio Fernández-Caballero, George Papakostas
PublisherSpringer Science and Business Media Deutschland GmbH
Pages597-610
Number of pages14
ISBN (Print)9789819970926
DOIs
StatePublished - 2023
Externally publishedYes
Event4th International Conference on Image Processing and Capsule Networks, ICIPCN 2023 - Bangkok, Thailand
Duration: 10 Aug 202311 Aug 2023

Publication series

NameLecture Notes in Networks and Systems
Volume798 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference4th International Conference on Image Processing and Capsule Networks, ICIPCN 2023
Country/TerritoryThailand
CityBangkok
Period10/08/2311/08/23

Keywords

  • Edge computing
  • Federated learning
  • Particle swarm optimization
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'AdaptPSOFL: Adaptive Particle Swarm Optimization-Based Layer Offloading Framework for Federated Learning'. Together they form a unique fingerprint.

Cite this