FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Jiarui, Shen, Yunheng, Hou, Chengbin, Wang, Pengyu, Wang, Jinbao, Tang, Ke, Lv, Hairong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908579854811136
author Song, Jiarui
Shen, Yunheng
Hou, Chengbin
Wang, Pengyu
Wang, Jinbao
Tang, Ke
Lv, Hairong
author_facet Song, Jiarui
Shen, Yunheng
Hou, Chengbin
Wang, Pengyu
Wang, Jinbao
Tang, Ke
Lv, Hairong
contents Personalized Federated Learning (PFL) aims to address the statistical heterogeneity of data across clients by learning the personalized model for each client. Among various PFL approaches, the personalized aggregation-based approach conducts parameter aggregation in the server-side aggregation phase to generate personalized models, and focuses on learning appropriate collaborative relationships among clients for aggregation. However, the collaborative relationships vary in different scenarios and even at different stages of the FL process. To this end, we propose Personalized Federated Learning with Attentive Graph HyperNetworks (FedAGHN), which employs Attentive Graph HyperNetworks (AGHNs) to dynamically capture fine-grained collaborative relationships and generate client-specific personalized initial models. Specifically, AGHNs empower graphs to explicitly model the client-specific collaborative relationships, construct collaboration graphs, and introduce tunable attentive mechanism to derive the collaboration weights, so that the personalized initial models can be obtained by aggregating parameters over the collaboration graphs. Extensive experiments can demonstrate the superiority of FedAGHN. Moreover, a series of visualizations are presented to explore the effectiveness of collaboration graphs learned by FedAGHN.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16379
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks
Song, Jiarui
Shen, Yunheng
Hou, Chengbin
Wang, Pengyu
Wang, Jinbao
Tang, Ke
Lv, Hairong
Machine Learning
Artificial Intelligence
Personalized Federated Learning (PFL) aims to address the statistical heterogeneity of data across clients by learning the personalized model for each client. Among various PFL approaches, the personalized aggregation-based approach conducts parameter aggregation in the server-side aggregation phase to generate personalized models, and focuses on learning appropriate collaborative relationships among clients for aggregation. However, the collaborative relationships vary in different scenarios and even at different stages of the FL process. To this end, we propose Personalized Federated Learning with Attentive Graph HyperNetworks (FedAGHN), which employs Attentive Graph HyperNetworks (AGHNs) to dynamically capture fine-grained collaborative relationships and generate client-specific personalized initial models. Specifically, AGHNs empower graphs to explicitly model the client-specific collaborative relationships, construct collaboration graphs, and introduce tunable attentive mechanism to derive the collaboration weights, so that the personalized initial models can be obtained by aggregating parameters over the collaboration graphs. Extensive experiments can demonstrate the superiority of FedAGHN. Moreover, a series of visualizations are presented to explore the effectiveness of collaboration graphs learned by FedAGHN.
title FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.16379