Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. Federated Learning under Covariate Shifts with Generalization Guarantees
 
research article

Federated Learning under Covariate Shifts with Generalization Guarantees

Ramezani-Kebrya, Ali
•
Liu, Fanghui  
•
Pethick, Thomas Michaelsen  
Show more
2023
Transactions on Machine Learning Research

This paper addresses intra-client and inter-client covariate shifts in federated learning (FL) with a focus on the overall generalization performance. To handle covariate shifts, we formulate a new global model training paradigm and propose Federated Importance- Weighted Empirical Risk Minimization (FTW-ERM) along with improving density ratio matching methods without requiring perfect knowledge of the supremum over true ratios. We also propose the communication-efficient variant FITW-ERM with the same level of privacy guarantees as those of classical ERM in FL. We theoretically show that FTW-ERM achieves smaller generalization error than classical ERM under certain settings. Experimental results demonstrate the superiority of FTW-ERM over existing FL baselines in challenging imbalanced federated settings in terms of data distribution shifts across clients.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

FTWERMCameraReady.pdf

Type

Postprint

Version

http://purl.org/coar/version/c_ab4af688f83e57aa

Access type

openaccess

License Condition

CC BY

Size

1.39 MB

Format

Adobe PDF

Checksum (MD5)

659880ee94e3881cbf6da3f420d101ac

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés