Calibrating Privacy Budgets for Locally Private Graph Neural Networks - Citegraph

Paper Info

Title
Calibrating Privacy Budgets for Locally Private Graph Neural Networks

Abstract
Graph neural networks have shown excellent performance in learning graph representations. In many cases, the graph structured data are crowd-sourced and may contain sensitive information, thus causing privacy issues. Therefore, privacy-preserving graph neural networks have spurred increasing interest nowadays. A promising approach for privacy-preserving graph neural networks is to apply local diff...

Year	DOI	Venue
2021	10.1109/NaNA53684.2021.00012	2021 International Conference on Networking and Network Applications (NaNA)
Keywords	DocType	ISBN
Privacy,Differential privacy,Graph neural networks,Calibration,Task analysis	Conference	978-1-6654-4158-2
Citations	PageRank	References
0	0.34	0
Authors
6

Authors (6 rows)

Cited by (0 rows)

References (0 rows)

Name	Order	Citations	PageRank
Wentao Du	1	0	0.34
Xinyu Ma	2	0	0.34
Wenxiang Dong	3	0	0.34
Dong Zhang	4	0	0.34
Chi Zhang	5	0	0.34
Qibin Sun	6	0	0.34

1