• LOGIN
    Login with username and password
Repository logo

BORIS Portal

Bern Open Repository and Information System

  • Publications
  • Theses
  • Research Data
  • Projects
  • Organizations
  • Researchers
  • More
  • Collections
  • Statistics
  • LOGIN
    Login with username and password
Repository logo
Unibern.ch
  1. Home
  2. Publications
  3. Resource-Aware Federated Transfer Learning with Adaptive Model Scaling and Channel Attention

Resource-Aware Federated Transfer Learning with Adaptive Model Scaling and Channel Attention

Details
Files
DOI
10.48620/94262
Abstract
The proliferation of heterogeneous edge devices creates opportunities for distributed intelligence but also introduces computational and communication challenges in Federated Learning (FL), with energy consumption emerging as a critical bottleneck for resource-constrained edge devices. Federated Transfer Learning (FTL) mitigates these issues by enabling cross-domain knowledge transfer, improving convergence, and reducing communication overhead. However, existing FTL approaches largely overlook device heterogeneity and resource constraints, leading to suboptimal efficiency and limited applicability in real-world edge environments. To address this gap, we present Resource-Aware Federated Transfer Learning (RA- FTL), a framework that adapts both model architecture and resource utilization to heterogeneous client capabilities. RA-FTL integrates two mechanisms: (1) capability-aware model scaling, which dynamically adjusts trainable parameters according to device profiles, and (2) adaptive channel attention, which sparsifies feature maps based on resource constraints. Experiments across diverse heterogeneous client settings show that the RA- FTL framework achieves 2–6× lower communication overhead, over 7% faster training, and up to 69% reduction in energy consumption compared to FTL and baseline FL methods, while maintaining competitive model performance.
Date Issued
2026-03
Publication Type
Conference Item
Subjects
Federated Learning
•
Transfer Learning
•
Energy- Efficient Machine Learning
•
Resource Heterogeneity.
Language(s)
en
Author(s)
Banik, Sabyasachi  
Institute of Computer Science  
Samikwa, Eric  
Institute of Computer Science  
Braun, Torsten  
Institute of Computer Science, Communication and Distributed Systems (CDS)  
Institute of Computer Science  
Additional Credits
Institute of Computer Science  
Institute of Computer Science, Communication and Distributed Systems (CDS)  
Publisher
IEEE
Title of Event
IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom PeRConAI Workshop)
Access(Rights)
restricted
Show full item
BORIS Portal
Bern Open Repository and Information System
Build: 0eaa7c [ 7.08. 11:06]
Explore
  • Projects
  • Funding
  • Publications
  • Research Data
  • Organizations
  • Researchers
  • Audiovisual Material
  • Software & other digital items
  • Events
More
  • About BORIS Portal
  • BORIS Portal & Open Science
  • Send Feedback
  • Cookie settings
  • Service Policy
Follow us on
  • Mastodon
  • YouTube
  • LinkedIn
UniBe logo
Repository logo COAR Notify