Federated Graph Learning -- A Position Paper
This work tackles privacy-preserving distributed graph learning for industries like finance and healthcare, but it is incremental as it primarily provides a categorization without new methods or results.
The paper addresses the challenge of training graph neural networks (GNNs) in privacy-sensitive scenarios with distributed data by proposing federated graph learning (FGL) as a solution, and it categorizes FGL into four types based on graph data distribution to clarify definitions and challenges.
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.