Federated Learning over Coupled Graphs

TL;DR

This paper introduces FedCog, a federated learning framework designed for coupled graph data, addressing privacy and topological challenges, and demonstrating significant improvements in node classification accuracy.

Contribution

The paper presents a novel federated learning framework for coupled graphs, with theoretical correctness and security proofs, and superior performance over traditional methods.

Findings

FedCog outperforms traditional FL methods on graph data.

Achieves up to 14.7% improvement in node classification accuracy.

Successfully handles distributed coupled graphs in real-world applications.

Abstract

Graphs are widely used to represent the relations among entities. When one owns the complete data, an entire graph can be easily built, therefore performing analysis on the graph is straightforward. However, in many scenarios, it is impractical to centralize the data due to data privacy concerns. An organization or party only keeps a part of the whole graph data, i.e., graph data is isolated from different parties. Recently, Federated Learning (FL) has been proposed to solve the data isolation issue, mainly for Euclidean data. It is still a challenge to apply FL on graph data because graphs contain topological information which is notorious for its non-IID nature and is hard to partition. In this work, we propose a novel FL framework for graph data, FedCog, to efficiently handle coupled graphs that are a kind of distributed graph data, but widely exist in a variety of real-world applications such as mobile carriers' communication networks and banks' transaction networks. We theoretically prove the correctness and security of FedCog. Experimental results demonstrate that our method FedCog significantly outperforms traditional FL methods on graphs. Remarkably, our FedCog improves the accuracy of node classification tasks by up to 14.7%.