Cooperative Network Learning for Large-Scale and Decentralized Graphs

TL;DR

This paper introduces a Cooperative Network Learning framework that enables secure, privacy-preserving, and collaborative graph learning across decentralized data sources using homomorphic encryption and secure communication.

Contribution

The paper presents a novel CNL framework that unifies local and global graph perspectives for decentralized GNN training without a central coordinator, ensuring security and fairness.

Findings

Outperforms state-of-the-art GNNs on multiple tasks

Provides a secure and privacy-preserving collaborative learning environment

Enhances the effectiveness of decentralized graph analysis

Abstract

Graph research, the systematic study of interconnected data points represented as graphs, plays a vital role in capturing intricate relationships within networked systems. However, in the real world, as graphs scale up, concerns about data security among different data-owning agencies arise, hindering information sharing and, ultimately, the utilization of graph data. Therefore, establishing a mutual trust mechanism among graph agencies is crucial for unlocking the full potential of graphs. Here, we introduce a Cooperative Network Learning (CNL) framework to ensure secure graph computing for various graph tasks. Essentially, this CNL framework unifies the local and global perspectives of GNN computing with distributed data for an agency by virtually connecting all participating agencies as a global graph without a fixed central coordinator. Inter-agency computing is protected by various technologies inherent in our framework, including homomorphic encryption and secure transmission. Moreover, each agency has a fair right to design or employ various graph learning models from its local or global perspective. Thus, CNL can collaboratively train GNN models based on decentralized graphs inferred from local and global graphs. Experiments on contagion dynamics prediction and traditional graph tasks (i.e., node classification and link prediction) demonstrate that our CNL architecture outperforms state-of-the-art GNNs developed at individual sites, revealing that CNL can provide a reliable, fair, secure, privacy-preserving, and global perspective to build effective and personalized models for network applications. We hope this framework will address privacy concerns in graph-related research and integrate decentralized graph data structures to benefit the network research community in cooperation and innovation.