Preserving Differential Privacy Between Features in Distributed Estimation
This addresses privacy concerns for data owners in distributed machine learning settings, though it is incremental as it extends existing differential privacy concepts to a specific distributed case.
The paper tackles the problem of preserving privacy in distributed, vertically-partitioned datasets for statistical estimation, proposing PriDE, a scalable framework that ensures differential privacy with bounded estimation error compared to non-private, non-distributed optimal estimates, as confirmed empirically on real-world and synthetic datasets.
Privacy is crucial in many applications of machine learning. Legal, ethical and societal issues restrict the sharing of sensitive data making it difficult to learn from datasets that are partitioned between many parties. One important instance of such a distributed setting arises when information about each record in the dataset is held by different data owners (the design matrix is "vertically-partitioned"). In this setting few approaches exist for private data sharing for the purposes of statistical estimation and the classical setup of differential privacy with a "trusted curator" preparing the data does not apply. We work with the notion of $(ε,δ)$-distributed differential privacy which extends single-party differential privacy to the distributed, vertically-partitioned case. We propose PriDE, a scalable framework for distributed estimation where each party communicates perturbed random projections of their locally held features ensuring $(ε,δ)$-distributed differential privacy is preserved. For $\ell_2$-penalized supervised learning problems PriDE has bounded estimation error compared with the optimal estimates obtained without privacy constraints in the non-distributed setting. We confirm this empirically on real world and synthetic datasets.