@inproceedings{f19c9f80bbe543b79538f0409ded1231,
title = "Poster: Learning to Personalize in Federated Networks with Contribution-Aware Aggregation",
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.",
author = "Ke Xing and Yanjie Dong and Xiaoyi Fan and Xiping Hu",
note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; 31st Annual International Conference on Mobile Computing and Networking, ACM MobiCom 2025 ; Conference date: 04-11-2025 Through 08-11-2025",
year = "2025",
month = nov,
day = "21",
doi = "10.1145/3680207.3765661",
language = "English",
series = "ACM MobiCom 2025 - Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking",
publisher = "Association for Computing Machinery, Inc",
pages = "1284--1286",
booktitle = "ACM MobiCom 2025 - Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking",
}