Reliable Imputed-Sample Assisted Vertical Federated Learning

2025-01-11

AI Summary

In vertical federated learning (VFL), sparse sample intersections lead to underutilization of non-overlapping samples, while existing missing-data imputation methods neglect imputation quality. Method: This paper proposes a novel training paradigm leveraging high-fidelity imputed samples, featuring (i) the first reliability assessment mechanism for imputed samples grounded in Dempster–Shafer evidence theory, enabling adaptive selection of low-uncertainty samples; and (ii) a privacy-preserving VFL collaborative modeling framework integrating multiple imputation, allowing trustworthy cross-silo imputation without raw data sharing. Results: On CIFAR-10 with only 1% sample overlap, our method achieves a 48% accuracy gain over baseline VFL approaches, demonstrating superior generalization under ultra-sparse intersection settings and systematically unlocking the utility of non-overlapping samples.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Vertical Federated Learning
• Non-shared Samples Utilization
• Missing Data Imputation Quality

Innovation

• RISA Framework
• Vertical Federated Learning (VFL)
• Quality Imputation Samples