Communication-Computation Efficient Secure Aggregation for Federated Learning

TL;DR

This paper introduces a low-complexity, communication-efficient secure aggregation scheme for federated learning that maintains privacy and reliability while significantly reducing resource consumption.

Contribution

It proposes a novel sparse graph topology for secret sharing in federated learning, reducing resource use by 70-80% compared to existing methods.

Findings

Achieves similar privacy and reliability as traditional methods

Reduces communication and computational resources by 70-80%

Provides theoretical guarantees using Erdős-Rényi graph model

Abstract

Federated learning has been spotlighted as a way to train neural networks using distributed data with no need for individual nodes to share data. Unfortunately, it has also been shown that adversaries may be able to extract local data contents off model parameters transmitted during federated learning. A recent solution based on the secure aggregation primitive enabled privacy-preserving federated learning, but at the expense of significant extra communication/computational resources. In this paper, we propose a low-complexity scheme that provides data privacy using substantially reduced communication/computational resources relative to the existing secure solution. The key idea behind the suggested scheme is to design the topology of secret-sharing nodes as a sparse random graph instead of the complete graph corresponding to the existing solution. We first obtain the necessary and sufficient condition on the graph to guarantee both reliability and privacy. We then suggest using the Erd\H{o}s-R\'enyi graph in particular and provide theoretical guarantees on the reliability/privacy of the proposed scheme. Through extensive real-world experiments, we demonstrate that our scheme, using only $20 \sim 30\%$ of the resources required in the conventional scheme, maintains virtually the same levels of reliability and data privacy in practical federated learning systems.