GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs

TL;DR

GraphFL is a federated learning framework designed for semi-supervised node classification on graphs, effectively addressing data heterogeneity, new label domains, and unlabeled data utilization, with superior experimental performance.

Contribution

This paper introduces the first federated learning framework for semi-supervised node classification on graphs, incorporating meta-learning and self-training to handle non-IID data and new label domains.

Findings

GraphFL outperforms baseline federated learning methods.

Self-training enhances GraphFL's performance.

Framework effectively handles non-IID data and new label domains.

Abstract

Graph-based semi-supervised node classification (GraphSSC) has wide applications, ranging from networking and security to data mining and machine learning, etc. However, existing centralized GraphSSC methods are impractical to solve many real-world graph-based problems, as collecting the entire graph and labeling a reasonable number of labels is time-consuming and costly, and data privacy may be also violated. Federated learning (FL) is an emerging learning paradigm that enables collaborative learning among multiple clients, which can mitigate the issue of label scarcity and protect data privacy as well. Therefore, performing GraphSSC under the FL setting is a promising solution to solve real-world graph-based problems. However, existing FL methods 1) perform poorly when data across clients are non-IID, 2) cannot handle data with new label domains, and 3) cannot leverage unlabeled data, while all these issues naturally happen in real-world graph-based problems. To address the above issues, we propose the first FL framework, namely GraphFL, for semi-supervised node classification on graphs. Our framework is motivated by meta-learning methods. Specifically, we propose two GraphFL methods to respectively address the non-IID issue in graph data and handle the tasks with new label domains. Furthermore, we design a self-training method to leverage unlabeled graph data. We adopt representative graph neural networks as GraphSSC methods and evaluate GraphFL on multiple graph datasets. Experimental results demonstrate that GraphFL significantly outperforms the compared FL baseline and GraphFL with self-training can obtain better performance.