Generalized Category Discovery in Federated Graph Learning

TL;DR

This paper introduces GCD-FGL, a novel federated graph learning framework for discovering new categories across decentralized graph data, addressing structural biases and semantic inconsistencies.

Contribution

It proposes a comprehensive approach combining client-side semantic alignment and server-side prototype alignment to improve generalized category discovery in federated graph learning.

Findings

GCD-FGL outperforms state-of-the-art methods on five real-world datasets.

Achieves an average HRScore gain of +4.86 over baselines.

Effectively mitigates neighborhood absorption and semantic inconsistency issues.

Abstract

Federated Graph Learning (FGL) enables collaborative learning over distributed graph data, yet existing approaches largely rely on a closed-world assumption, limiting their applicability in dynamic environments where novel categories continuously emerge. To bridge this gap, we target the practical scenario of Federated Graph Generalized Category Discovery (FGGCD), aiming to collaboratively discover novel categories across decentralized graph clients while retaining knowledge of known categories. We observe that FGGCD introduces two fundamental challenges: (1) the Neighborhood Absorption Effect, where structural fragmentation leads to biased neighborhood aggregation, causing novel nodes to be misclassified as known categories; and (2) Global Semantic Inconsistency, where the aforementioned local biases propagate to the server and are amplified by heterogeneous subgraph distributions, hindering cross-client knowledge integration. To address these issues, we propose GCD-FGL, an FGL framework for GCD that integrates a client-side Topology-Reliable Semantic Alignment and Discovery process to mitigate the neighborhood absorption effect, and a server-side Hierarchical Prototype Alignment strategy to resolve global semantic inconsistency. Extensive experiments on five real-world graph datasets demonstrate that GCD-FGL consistently outperforms state-of-the-art baselines, achieving an average absolute gain of +4.86 in HRScore.