TY - GEN
T1 - Byzantine-tolerant federated Gaussian process regression for streaming data
AU - Zhang, Xu
AU - Yuan, Zhenyuan
AU - Zhu, Minghui
N1 - Funding Information:
This work was partially supported by NSF awards ECCS 1846706 and ECCS 2140175.
Publisher Copyright:
© 2022 Neural information processing systems foundation. All rights reserved.
PY - 2022
Y1 - 2022
N2 - In this paper, we consider Byzantine-tolerant federated learning for streaming data using Gaussian process regression (GPR). In particular, a cloud and a group of agents aim to collaboratively learn a latent function where some agents are subject to Byzantine attacks. We develop a Byzantine-tolerant federated GPR algorithm, which includes three modules: agent-based local GPR, cloud-based aggregated GPR and agent-based fused GPR. We derive the upper bounds on the prediction error between the mean from the cloud-based aggregated GPR and the target function provided that Byzantine agents are less than one quarter of all the agents. We also characterize the lower and upper bounds of the predictive variance. Experiments on a synthetic dataset and two real-world datasets are conducted to evaluate the proposed algorithm.
AB - In this paper, we consider Byzantine-tolerant federated learning for streaming data using Gaussian process regression (GPR). In particular, a cloud and a group of agents aim to collaboratively learn a latent function where some agents are subject to Byzantine attacks. We develop a Byzantine-tolerant federated GPR algorithm, which includes three modules: agent-based local GPR, cloud-based aggregated GPR and agent-based fused GPR. We derive the upper bounds on the prediction error between the mean from the cloud-based aggregated GPR and the target function provided that Byzantine agents are less than one quarter of all the agents. We also characterize the lower and upper bounds of the predictive variance. Experiments on a synthetic dataset and two real-world datasets are conducted to evaluate the proposed algorithm.
UR - http://www.scopus.com/inward/record.url?scp=85163204910&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85163204910&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85163204910
T3 - Advances in Neural Information Processing Systems
BT - Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
A2 - Koyejo, S.
A2 - Mohamed, S.
A2 - Agarwal, A.
A2 - Belgrave, D.
A2 - Cho, K.
A2 - Oh, A.
PB - Neural information processing systems foundation
T2 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
Y2 - 28 November 2022 through 9 December 2022
ER -