Knowledge-Driven Federated Graph Learning on Model Heterogeneity

TL;DR

This paper introduces FedGKC, a framework for federated graph learning that effectively handles model heterogeneity by using a copilot model and knowledge distillation, improving accuracy across diverse client architectures.

Contribution

The paper proposes a novel federated graph learning framework with a copilot model and knowledge-aware aggregation to address client model heterogeneity in GNN-based federated learning.

Findings

Achieves 3.88% average accuracy improvement over baselines in heterogeneous scenarios.

Maintains strong performance in homogeneous settings.

Demonstrates effectiveness across eight benchmark datasets.

Abstract

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.