Private Read Update Write (PRUW) With Heterogeneous Databases

TL;DR

This paper proposes a privacy-preserving scheme for federated submodel learning that efficiently manages heterogeneous database storage constraints while ensuring data privacy during read and write operations.

Contribution

It introduces a novel PRUW scheme tailored for heterogeneous storage constraints, optimizing communication cost through submodel partitioning and encoding.

Findings

Achieves information-theoretic privacy of submodel indices and updates.

Reduces communication cost compared to existing methods.

Handles arbitrary storage constraints effectively.

Abstract

We investigate the problem of private read update write (PRUW) with heterogeneous storage constrained databases in federated submodel learning (FSL). In FSL a machine learning (ML) model is divided into multiple submodels based on different types of data used to train it. A given user downloads, updates and uploads the updates back to a single submodel of interest, based on the type of user's local data. With PRUW, the process of reading (downloading) and writing (uploading) is carried out such that information theoretic privacy of the updating submodel index and the values of updates is guaranteed. We consider the practical scenario where the submodels are stored in databases with arbitrary (heterogeneous) storage constraints, and provide a PRUW scheme with a storage mechanism that utilizes submodel partitioning and encoding to minimize the communication cost.