Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devices

arXiv:2303.00492v3 Announce Type: replace
Abstract: Graph neural networks (GNN) have been widely deployed in real-world networked applications and systems due to their capability to handle graph-structured data. However, the growing awareness of data privacy severely challenges the traditional centralized model training paradigm, where a server holds all the graph information. Federated learning is an emerging collaborative computing paradigm that allows model training without data centralization. Existing federated GNN studies mainly focus on systems where clients hold distinctive graphs or sub-graphs. …

abstract applications arxiv capability challenges cs.dc cs.lg data data privacy decentralized devices federated learning gnn graph graph learning graph neural networks information networks neural networks paradigm privacy server structured data systems training type world