Secure Federated Submodel Learning

TL;DR

This paper introduces a secure federated submodel learning framework that enhances efficiency and privacy by allowing clients to download and update only relevant submodels, protecting private data through differential privacy and secure protocols.

Contribution

It proposes a novel federated submodel learning scheme with privacy-preserving features, including randomized response, secure aggregation, and differential privacy, suitable for large-scale deep learning tasks.

Findings

Demonstrates feasibility and scalability on real-world Taobao data

Achieves good model accuracy and convergence

Reduces communication, computation, and storage overheads

Abstract

Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient for resource-constrained clients and large-scale deep learning tasks. We thus propose a new framework, called federated submodel learning, where clients download only the needed parts of the full model, namely submodels, and then upload the submodel updates. Nevertheless, the "position" of a client's truly required submodel corresponds to her private data, and its disclosure to the cloud server during interactions inevitably breaks the tenet of federated learning. To integrate efficiency and privacy, we have designed a secure federated submodel learning scheme coupled with a private set union protocol as a cornerstone. Our secure scheme features the properties of randomized response, secure aggregation, and Bloom filter, and endows each client with a customized plausible deniability, in terms of local differential privacy, against the position of her desired submodel, thus protecting her private data. We further instantiated our scheme with the e-commerce recommendation scenario in Alibaba, implemented a prototype system, and extensively evaluated its performance over 30-day Taobao user data. The analysis and evaluation results demonstrate the feasibility and scalability of our scheme from model accuracy and convergency, practical communication, computation, and storage overheads, as well as manifest its remarkable advantages over the conventional federated learning framework.