3
IRUS TotalDownloads
Altmetric
Model pruning enables efficient federated learning on edge devices
File | Description | Size | Format | |
---|---|---|---|---|
![]() | Accepted version | 6.84 MB | Adobe PDF | View/Open |
Title: | Model pruning enables efficient federated learning on edge devices |
Authors: | Jiang, Y Wang, S Valls, V Bong Jun, K Wei-Han, L Leung, K Tassiulas, L |
Item Type: | Journal Article |
Abstract: | Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers in a data center. To overcome this challenge, we propose PruneFL--a novel FL approach with adaptive and distributed parameter pruning, which adapts the model size during FL to reduce both communication and computation overhead and minimize the overall training time, while maintaining a similar accuracy as the original model. PruneFL includes initial pruning at a selected client and further pruning as part of the FL process. The model size is adapted during this process, which includes maximizing the approximate empirical risk reduction divided by the time of one FL round. Our experiments with various datasets on edge devices (e.g., Raspberry Pi) show that: 1) we significantly reduce the training time compared to conventional FL and various other pruning-based methods and 2) the pruned model with automatically determined size converges to an accuracy that is very similar to the original model, and it is also a lottery ticket of the original model. |
Issue Date: | 25-Apr-2022 |
Date of Acceptance: | 1-Apr-2022 |
URI: | http://hdl.handle.net/10044/1/96730 |
DOI: | 10.1109/TNNLS.2022.3166101 |
ISSN: | 1045-9227 |
Publisher: | Institute of Electrical and Electronics Engineers |
Start Page: | 1 |
End Page: | 13 |
Journal / Book Title: | IEEE Transactions on Neural Networks and Learning Systems |
Copyright Statement: | © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. |
Sponsor/Funder: | IBM United Kingdom Ltd |
Funder's Grant Number: | PO 4603 458 249 |
Keywords: | Science & Technology Technology Computer Science, Artificial Intelligence Computer Science, Hardware & Architecture Computer Science, Theory & Methods Engineering, Electrical & Electronic Computer Science Engineering Training Computational modeling Data models Adaptation models Collaborative work Servers Distributed databases Efficient training federated learning (FL) model pruning Artificial Intelligence & Image Processing |
Publication Status: | Published online |
Appears in Collections: | Computing Electrical and Electronic Engineering |