Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios

TL;DR

This paper introduces a flexible, unified vertical federated learning framework based on deep latent variable models that handles arbitrary data alignment, labeling scenarios, and missing data mechanisms, outperforming existing methods.

Contribution

It proposes the first VFL framework capable of jointly managing arbitrary data alignment, unlabeled data, and multi-party collaboration, addressing key limitations of prior approaches.

Findings

Outperforms all baselines in 160 out of 168 configurations.

Achieves an average performance gap of 9.6 percentage points over competitors.

Supports diverse missingness mechanisms in training and testing scenarios.

Abstract

Federated learning (FL) has attracted significant attention for enabling collaborative learning without exposing private data. Among the primary variants of FL, vertical federated learning (VFL) addresses feature-partitioned data held by multiple institutions, each holding complementary information for the same set of users. However, existing VFL methods often impose restrictive assumptions such as a small number of participating parties, fully aligned data, or only using labeled data. In this work, we reinterpret alignment gaps in VFL as missing data problems and propose a unified framework that accommodates both training and inference under arbitrary alignment and labeling scenarios, while supporting diverse missingness mechanisms. In the experiments on 168 configurations spanning four benchmark datasets, six training-time missingness patterns, and seven testing-time missingness patterns, our method outperforms all baselines in 160 cases with an average gap of 9.6 percentage points over the next-best competitors. To the best of our knowledge, this is the first VFL framework to jointly handle arbitrary data alignment, unlabeled data, and multi-party collaboration all at once.