Can I read Deep Efficient Private Neighbor Generation for Subgraph Federated Learning on EtoBox?

Deep Efficient Private Neighbor Generation for Subgraph Federated Learning by Zhang, Ke; Sun, Lichao; Ding, Bolin; Yiu, Siu Ming; Yang, Carl is a scholarly article available to read on EtoBox.

What is Deep Efficient Private Neighbor Generation for Subgraph Federated Learning about?

Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications. Without harming data privacy, it is natural to consider the subgraph federated learning (subgraph FL) scenario, where each local client holds a subgraph of the entire global graph, to obtain globally generalized graph mining models. To overcome the unique challenge of incomplete information propagation on local subgraphs due to missing cross-subgraph neighbors, previous works resort to the augmentation of local neighborhoods through the joint FL of missing neighbor generators and GNNs. Yet their technical designs have profound limitations regarding the utility, efficiency, and privacy goals of FL. In this work, we propose FedDEP to comprehensively tackle these challenges in subgraph FL. FedDEP consists of a series of novel technical designs: (1) Deep neighbor generation through leveraging the GNN embeddings of potential missing neighbors; (2) Efficient pseudo-FL for neighbor generation through embedding prototyping; and (3) Privacy protection through noise-less edge-local-differential-privacy. We analyze the correctness and efficiency of FedDEP

Author

Zhang, Ke; Sun, Lichao; Ding, Bolin; Yiu, Siu Ming; Yang, Carl

Published

2024

Language

EN