Federated Learning over Coupled Graphs

• Published in: IEEE transactions on parallel and distributed systems Vol. 34; no. 4; pp. 1 - 14
• Main Authors: Lei, Runze, Wang, Pinghui, Zhao, Junzhou, Lan, Lin, Tao, Jing, Deng, Chao, Feng, Junlan, Wang, Xidian, Guan, Xiaohong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Communication networks; Data models; Data privacy; Distributed databases; distributed graph processing; Federated learning; Graph neural networks; Graphs; Optimization; privacy preservation; Task analysis; Training
• ISSN: 1045-9219; 1558-2183
• DOI: 10.1109/TPDS.2023.3240527

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 <inline-formula><tex-math notation="LaTeX">14.7\%</tex-math></inline-formula>.