Knowledge-Driven Federated Graph Learning on Model Heterogeneity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Zhengyu, Zeng, Guang, Lai, Huilin, Su, Daohan, Jia, Jishuo, Zhu, Yinlin, Li, Xunkai, Li, Rong-Hua, Wang, Guoren, Zhou, Chenghu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912795834974208
author Wu, Zhengyu
Zeng, Guang
Lai, Huilin
Su, Daohan
Jia, Jishuo
Zhu, Yinlin
Li, Xunkai
Li, Rong-Hua
Wang, Guoren
Zhou, Chenghu
author_facet Wu, Zhengyu
Zeng, Guang
Lai, Huilin
Su, Daohan
Jia, Jishuo
Zhu, Yinlin
Li, Xunkai
Li, Rong-Hua
Wang, Guoren
Zhou, Chenghu
contents Federated graph learning (FGL) has emerged as a promising paradigm for collaborative graph representation learning, enabling multiple parties to jointly train models while preserving data privacy. However, most existing approaches assume homogeneous client models and largely overlook the challenge of model-centric heterogeneous FGL (MHtFGL), which frequently arises in practice when organizations employ graph neural networks (GNNs) of different scales and architectures.Such architectural diversity not only undermines smooth server-side aggregation, which presupposes a unified representation space shared across clients' updates, but also further complicates the transfer and integration of structural knowledge across clients. To address this issue, we propose the Federated Graph Knowledge Collaboration (FedGKC) framework. FedGKC introduces a lightweight Copilot Model on each client to facilitate knowledge exchange while local architectures are heterogeneous across clients, and employs two complementary mechanisms: Client-side Self-Mutual Knowledge Distillation, which transfers effective knowledge between local and copilot models through bidirectional distillation with multi-view perturbation; and Server-side Knowledge-Aware Model Aggregation, which dynamically assigns aggregation weights based on knowledge provided by clients. Extensive experiments on eight benchmark datasets demonstrate that FedGKC achieves an average accuracy gain of 3.88% over baselines in MHtFGL scenarios, while maintaining excellent performance in homogeneous settings.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12624
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge-Driven Federated Graph Learning on Model Heterogeneity
Wu, Zhengyu
Zeng, Guang
Lai, Huilin
Su, Daohan
Jia, Jishuo
Zhu, Yinlin
Li, Xunkai
Li, Rong-Hua
Wang, Guoren
Zhou, Chenghu
Machine Learning
Distributed, Parallel, and Cluster Computing
Federated graph learning (FGL) has emerged as a promising paradigm for collaborative graph representation learning, enabling multiple parties to jointly train models while preserving data privacy. However, most existing approaches assume homogeneous client models and largely overlook the challenge of model-centric heterogeneous FGL (MHtFGL), which frequently arises in practice when organizations employ graph neural networks (GNNs) of different scales and architectures.Such architectural diversity not only undermines smooth server-side aggregation, which presupposes a unified representation space shared across clients' updates, but also further complicates the transfer and integration of structural knowledge across clients. To address this issue, we propose the Federated Graph Knowledge Collaboration (FedGKC) framework. FedGKC introduces a lightweight Copilot Model on each client to facilitate knowledge exchange while local architectures are heterogeneous across clients, and employs two complementary mechanisms: Client-side Self-Mutual Knowledge Distillation, which transfers effective knowledge between local and copilot models through bidirectional distillation with multi-view perturbation; and Server-side Knowledge-Aware Model Aggregation, which dynamically assigns aggregation weights based on knowledge provided by clients. Extensive experiments on eight benchmark datasets demonstrate that FedGKC achieves an average accuracy gain of 3.88% over baselines in MHtFGL scenarios, while maintaining excellent performance in homogeneous settings.
title Knowledge-Driven Federated Graph Learning on Model Heterogeneity
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2501.12624