Federated Graph Learning -- A Position Paper

TL;DR

This paper introduces federated graph learning (FGL), categorizes its types based on data distribution, discusses formulations and applications, and highlights key challenges in privacy-sensitive scenarios.

Contribution

It provides a clear categorization of FGL types and discusses their formulations, applications, and challenges, clarifying an emerging research area.

Findings

Proposes four types of FGL based on data distribution.

Analyzes formulations and applications for each FGL type.

Identifies potential challenges in federated graph learning.

Abstract

Graph neural networks (GNN) have been successful in many fields, and derived various researches and applications in real industries. However, in some privacy sensitive scenarios (like finance, healthcare), training a GNN model centrally faces challenges due to the distributed data silos. Federated learning (FL) is a an emerging technique that can collaboratively train a shared model while keeping the data decentralized, which is a rational solution for distributed GNN training. We term it as federated graph learning (FGL). Although FGL has received increasing attention recently, the definition and challenges of FGL is still up in the air. In this position paper, we present a categorization to clarify it. Considering how graph data are distributed among clients, we propose four types of FGL: inter-graph FL, intra-graph FL and graph-structured FL, where intra-graph is further divided into horizontal and vertical FGL. For each type of FGL, we make a detailed discussion about the formulation and applications, and propose some potential challenges.