Federated Continual Graph Learning

TL;DR

This paper introduces FCGL, a federated learning framework for evolving graph data that tackles local forgetting and global expertise conflicts, enhancing GNN performance while respecting privacy constraints.

Contribution

It proposes POWER, a novel framework combining experience node preservation and pseudo-prototype reconstruction to improve federated continual graph learning.

Findings

POWER outperforms existing federated CGL baselines.

The approach effectively mitigates local graph forgetting.

The method reduces global expertise conflict in federated settings.

Abstract

Managing evolving graph data presents substantial challenges in storage and privacy, and training graph neural networks (GNNs) on such data often leads to catastrophic forgetting, impairing performance on earlier tasks. Despite existing continual graph learning (CGL) methods mitigating this to some extent, they rely on centralized architectures and ignore the potential of distributed graph databases to leverage collective intelligence. To this end, we propose Federated Continual Graph Learning (FCGL) to adapt GNNs across multiple evolving graphs under storage and privacy constraints. Our empirical study highlights two core challenges: local graph forgetting (LGF), where clients lose prior knowledge when adapting to new tasks, and global expertise conflict (GEC), where the global GNN exhibits sub-optimal performance in both adapting to new tasks and retaining old ones, arising from inconsistent client expertise during server-side parameter aggregation. To address these, we introduce POWER, a framework that preserves experience nodes with maximum local-global coverage locally to mitigate LGF, and leverages pseudo-prototype reconstruction with trajectory-aware knowledge transfer to resolve GEC. Experiments on various graph datasets demonstrate POWER's superiority over federated adaptations of CGL baselines and vision-centric federated continual learning approaches.