Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Need

2024/10/23 by Jon Irureta, Jon Imaz, Irureta, Jon +8
Computer Science · #Advanced Graph Neural Networks #Cooperative Communication and Network Coding #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2410.17648

openalex publication_date 2024/10/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Existing Vertical FL (VFL) methods often struggle with realistic and unaligned data partitions, and incur into high communication costs and significant operational complexity. This work introduces a novel approach to VFL, Active Participant Centric VFL (APC-VFL), that excels in scenarios when data samples among participants are partially aligned at training. Among its strengths, APC-VFL only requires a single communication step with the active participant. This is made possible through a local and unsupervised representation learning stage at each participant followed by a knowledge distillation step in the active participant. Compared to other VFL methods such as SplitNN or VFedTrans, APC-VFL consistently outperforms them across three popular VFL datasets in terms of F1, accuracy and communication costs as the ratio of aligned data is reduced.

Related

• VFL-RPS: Relevant Participant Selection in Vertical Federated Learning
• Vertical Federated Learning Hybrid Local Pre-training
• Vertical Federated Learning: A Structured Literature Review
• Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples
• TreeCSS: An Efficient Framework for Vertical Federated Learning