Reliable Imputed-Sample Assisted Vertical Federated Learning

TL;DR

This paper introduces RISA, a framework that improves vertical federated learning by selecting reliable imputed non-overlapping samples using evidence theory, significantly enhancing model accuracy especially with limited overlapping data.

Contribution

The paper proposes a novel RISA framework that leverages evidence theory to select high-quality imputed samples, boosting VFL performance with minimal overlapping data.

Findings

48% accuracy gain on CIFAR-10 with 1% overlapping samples

Effective utilization of non-overlapping samples improves VFL accuracy

Significant performance gains demonstrated on two datasets

Abstract

Vertical Federated Learning (VFL) is a well-known FL variant that enables multiple parties to collaboratively train a model without sharing their raw data. Existing VFL approaches focus on overlapping samples among different parties, while their performance is constrained by the limited number of these samples, leaving numerous non-overlapping samples unexplored. Some previous work has explored techniques for imputing missing values in samples, but often without adequate attention to the quality of the imputed samples. To address this issue, we propose a Reliable Imputed-Sample Assisted (RISA) VFL framework to effectively exploit non-overlapping samples by selecting reliable imputed samples for training VFL models. Specifically, after imputing non-overlapping samples, we introduce evidence theory to estimate the uncertainty of imputed samples, and only samples with low uncertainty are selected. In this way, high-quality non-overlapping samples are utilized to improve VFL model. Experiments on two widely used datasets demonstrate the significant performance gains achieved by the RISA, especially with the limited overlapping samples, e.g., a 48% accuracy gain on CIFAR-10 with only 1% overlapping samples.