Privacy-Preserving Fully Distributed Gaussian Process Regression

TL;DR

This paper introduces a privacy-preserving distributed Gaussian process regression protocol using secure multi-party computation, ensuring data confidentiality while achieving comparable results to standard methods, and extends it to hyperparameter optimization.

Contribution

It presents a novel fully distributed GPR protocol with formal privacy guarantees and hyperparameter optimization, enhancing privacy and practicality in collaborative learning.

Findings

Protocol guarantees data privacy through formal security proofs.

Experimental results show accurate model convergence.

Method is practically applicable to real-world scenarios.

Abstract

Although distributed Gaussian process regression (GPR) enables multiple agents with separate datasets to jointly learn a model of the target function, its collaborative nature poses risks of private data leakage. To address this, we propose a privacy-preserving fully distributed GPR protocol based on secure multi-party computation (SMPC) that preserves the confidentiality of each agent's local dataset. Building upon a secure distributed average consensus algorithm, the protocol guarantees that each agent's local model practically converges to the same global model that would be obtained by the standard distributed GPR. Further, we adopt the paradigm of simulation based security to provide formal privacy guarantees, and extend the proposed protocol to enable kernel hyperparameter optimization, which is critical yet often overlooked in the literature. Experimental results demonstrate the effectiveness and practical applicability of the proposed method.