Against Multifaceted Graph Heterogeneity via Asymmetric Federated Prompt Learning

TL;DR

This paper introduces FedGPL, a novel federated graph learning framework that effectively addresses multifaceted graph heterogeneity through asymmetric prompt-based knowledge transfer, improving accuracy and efficiency.

Contribution

The paper proposes a split federated framework with hierarchical transfer and adaptive graph structure generation to handle diverse graph heterogeneity in federated learning.

Findings

FedGPL outperforms state-of-the-art baselines in accuracy on large-scale datasets.

The framework enhances data utility by distinguishing key subgraphs.

Theoretical analysis confirms the effectiveness of the proposed algorithms.

Abstract

Federated Graph Learning (FGL) aims to collaboratively and privately optimize graph models on divergent data for different tasks. A critical challenge in FGL is to enable effective yet efficient federated optimization against multifaceted graph heterogeneity to enhance mutual performance. However, existing FGL works primarily address graph data heterogeneity and perform incapable of graph task heterogeneity. To address the challenge, we propose a Federated Graph Prompt Learning (FedGPL) framework to efficiently enable prompt-based asymmetric graph knowledge transfer between multifaceted heterogeneous federated participants. Generally, we establish a split federated framework to preserve universal and domain-specific graph knowledge, respectively. Moreover, we develop two algorithms to eliminate task and data heterogeneity for advanced federated knowledge preservation. First, a Hierarchical Directed Transfer Aggregator (HiDTA) delivers cross-task beneficial knowledge that is hierarchically distilled according to the directional transferability. Second, a Virtual Prompt Graph (VPG) adaptively generates graph structures to enhance data utility by distinguishing dominant subgraphs and neutralizing redundant ones. We conduct theoretical analyses and extensive experiments to demonstrate the significant accuracy and efficiency effectiveness of FedGPL against multifaceted graph heterogeneity compared to state-of-the-art baselines on large-scale federated graph datasets.