The Sherpa.ai Blind Vertical Federated Learning paradigm to minimize the number of communications

Acero A, Jimenez-Gutierrez DM, Pighin D, Zuazua Iriondo E, Del Rio J, Uribe-Etxebarria X (2025)

Publication Language: English

Publication Status: Submitted

Publication Type: Unpublished / Preprint

Future Publication Type: Journal article

Publication year: 2025

URI: https://doi.org/10.48550/arXiv.2510.17901

DOI: 10.48550/arXiv.2510.17901

Open Access Link: https://doi.org/10.48550/arXiv.2510.17901

Abstract

Federated Learning (FL) enables collaborative decentralized training across multiple parties (nodes) while keeping raw data private. There are two main paradigms in FL: Horizontal FL (HFL), where all participant nodes share the same feature space but hold different samples, and Vertical FL (VFL), where participants hold complementary features for the same samples. While HFL is widely adopted, VFL is employed in domains where nodes hold complementary features about the same samples. Still, VFL presents a significant limitation: the vast number of communications required during training. This compromises privacy and security, and can lead to high energy consumption, and in some cases, make model training unfeasible due to the high number of communications. In this paper, we introduce Sherpa.ai Blind Vertical Federated Learning (SBVFL), a novel paradigm that leverages a distributed training mechanism enhanced for privacy and security. Decoupling the vast majority of node updates from the server dramatically reduces node-server communication. Experiments show that SBVFL reduces communication by ∼99% compared to standard VFL while maintaining accuracy and robustness. Therefore, SBVFL enables practical, privacy-preserving VFL across sensitive domains, including healthcare, finance, manufacturing, aerospace, cybersecurity, and the defense industry.

Authors with CRIS profile

Enrique Zuazua Iriondo Lehrstuhl für Dynamics, Control, Machine Learning and Numerics (Alexander von Humboldt-Professur)

Involved external institutions

Università degli studi "La Sapienza" IT Italy (IT) Polytechnic University of Catalonia / Universitat Politècnica de Catalunya · BarcelonaTech (UPC) / Universidad Politécnica de Cataluña ES Spain (ES) Apple Inc US United States (USA) (US)

How to cite

APA:

Acero, A., Jimenez-Gutierrez, D.M., Pighin, D., Zuazua Iriondo, E., Del Rio, J., & Uribe-Etxebarria, X. (2025). The Sherpa.ai Blind Vertical Federated Learning paradigm to minimize the number of communications. (Unpublished, Submitted).

MLA:

Acero, Alex, et al. The Sherpa.ai Blind Vertical Federated Learning paradigm to minimize the number of communications. Unpublished, Submitted. 2025.

BibTeX: Download