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.
View on arXiv@article{irureta2025_2410.17648,
title={ Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Need },
author={ Jon Irureta and Jon Imaz and Aizea Lojo and Javier Fernandez-Marques and Marco González and Iñigo Perona },
journal={arXiv preprint arXiv:2410.17648},
year={ 2025 }
}