Poster: Learning to Personalize in Federated Networks with Contribution-Aware Aggregation

  • Ke Xing
  • , Yanjie Dong*
  • , Xiaoyi Fan
  • , Xiping Hu*
  • *Corresponding author for this work

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

Abstract

Personalized Federated Learning (PFL) targets client-specific models under heterogeneous and limited data. However, conventional methods often use heuristic or data-size-based averaging and overlook the true contributions of client updates. We propose a contribution-oriented PFL framework that quantifies client contributions via gradient alignment and prediction discrepancy for informed aggregation. We further develop a parameter-wise personalization mechanism for adaptive local updates and a mask-aware momentum optimizer for stable training. Preliminary results on CIFAR10 validate its effectiveness.

Original languageEnglish
Title of host publicationACM MobiCom 2025 - Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking
PublisherAssociation for Computing Machinery, Inc
Pages1284-1286
Number of pages3
ISBN (Electronic)9798400711299
DOIs
Publication statusPublished - 21 Nov 2025
Event31st Annual International Conference on Mobile Computing and Networking, ACM MobiCom 2025 - Hong Kong, China
Duration: 4 Nov 20258 Nov 2025

Publication series

NameACM MobiCom 2025 - Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking

Conference

Conference31st Annual International Conference on Mobile Computing and Networking, ACM MobiCom 2025
Country/TerritoryChina
CityHong Kong
Period4/11/258/11/25

Fingerprint

Dive into the research topics of 'Poster: Learning to Personalize in Federated Networks with Contribution-Aware Aggregation'. Together they form a unique fingerprint.

Cite this