FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models

TL;DR

FedVS is a novel vertical federated learning framework that enhances robustness against straggling clients and ensures privacy of data and models through secret sharing, demonstrated across diverse datasets.

Contribution

The paper introduces FedVS, a new secret sharing-based approach that simultaneously mitigates stragglers and preserves privacy in split vertical federated learning.

Findings

FedVS effectively reduces training delays caused by stragglers.

FedVS guarantees information-theoretic privacy against colluding clients and curious servers.

Experimental results show FedVS outperforms baseline protocols across multiple datasets.

Abstract

In a vertical federated learning (VFL) system consisting of a central server and many distributed clients, the training data are vertically partitioned such that different features are privately stored on different clients. The problem of split VFL is to train a model split between the server and the clients. This paper aims to address two major challenges in split VFL: 1) performance degradation due to straggling clients during training; and 2) data and model privacy leakage from clients' uploaded data embeddings. We propose FedVS to simultaneously address these two challenges. The key idea of FedVS is to design secret sharing schemes for the local data and models, such that information-theoretical privacy against colluding clients and curious server is guaranteed, and the aggregation of all clients' embeddings is reconstructed losslessly, via decrypting computation shares from the non-straggling clients. Extensive experiments on various types of VFL datasets (including tabular, CV, and multi-view) demonstrate the universal advantages of FedVS in straggler mitigation and privacy protection over baseline protocols.