DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing

TL;DR

This paper introduces DReS-FL, a federated learning framework resilient to client dropouts and non-IID data, using secret data sharing and polynomial neural networks to enhance privacy and robustness.

Contribution

The paper proposes a novel dropout-resilient secure federated learning framework using Lagrange coding and polynomial neural networks, addressing non-IID data and client dropout challenges.

Findings

DReS-FL improves training performance over baseline methods.

The framework provides strong privacy guarantees.

Experimental results confirm robustness to client dropout.

Abstract

Federated learning (FL) strives to enable collaborative training of machine learning models without centrally collecting clients' private data. Different from centralized training, the local datasets across clients in FL are non-independent and identically distributed (non-IID). In addition, the data-owning clients may drop out of the training process arbitrarily. These characteristics will significantly degrade the training performance. This paper proposes a Dropout-Resilient Secure Federated Learning (DReS-FL) framework based on Lagrange coded computing (LCC) to tackle both the non-IID and dropout problems. The key idea is to utilize Lagrange coding to secretly share the private datasets among clients so that each client receives an encoded version of the global dataset, and the local gradient computation over this dataset is unbiased. To correctly decode the gradient at the server, the gradient function has to be a polynomial in a finite field, and thus we construct polynomial integer neural networks (PINNs) to enable our framework. Theoretical analysis shows that DReS-FL is resilient to client dropouts and provides privacy protection for the local datasets. Furthermore, we experimentally demonstrate that DReS-FL consistently leads to significant performance gains over baseline methods.