ADMM Based Privacy-Preserving Decentralized Optimization
By Chunlei Zhang, Muaz Ahmad, Yongqiang Wang. 2017
197 citations recorded by the source corpus.
Privacy preservation is addressed for decentralized optimization, where <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> agents cooperatively minimize the sum of <inline-formula> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> convex functions private to these individual agents. In most existing decentralized optimization approaches, participating agents exchange and disclose states explicitly, which may not be desirable when the states contain sensitive information of individual agents. The problem is more acute when adversaries exist which try to steal information from other participating agents. To address this issue, we propose a privacy-preserving decentralized optimization approach based on alternating direction method of multipliers (ADMM) and partially homomorphic cryptography. To the best of our knowledge, this is the first time that cryptographic techniques are incorporated in a fully decentralized setting to enable privacy preservation in decentralized optimization in the absence of any third party or aggregator. To facilitate the incorporation of encryption in a fully decentralized manner, we introduce a new ADMM, which allows time-varying penalty matrices and rigorously prove that it has a convergence rate of <inline-formula> <tex-math notation="LaTeX">$O(1/t)$ </tex-math></inline-formula>. Numerical and experimental results confirm the effectiveness and low-computational complexity of the proposed approach.
Subfields: Artificial Intelligence, Computational Mechanics, Electrical and Electronic Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computational Mechanics
In Electrical and Electronic Engineering
Citations in the corpus
- Learning Privately over Distributed Features: An ADMM Sharing Approach (2019, methodology): “Recently, DP has been applied to ADMM algorithms to solve multi-party machine learning problems Zhang et al. (2018); Zhang and Zhu (2016a); Zhang et al. (2019); Zhang and Zhu (2017).”
- DP-ADMM: ADMM-Based Distributed Learning With Differential Privacy (2018, unknown): “A recent work [33] uses partially homomorphic cryptography in ADMM-based distributed learning to preserve data privacy but the proposed approach cannot protect the information leakage of the private user data from the final learned models.”