mlsanityData to 14 Oct 2026

The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communications

arXiv 2510.17901 ↗First posted 19 Oct 2025cs.LG cs.AI cs.DCcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 19 Oct 2025.

Builds on

25 of 40 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  5. 2023A Comprehensive Overview of Large Language Modelscited by 648
  6. 2021A Field Guide to Federated Optimizationcited by 315
  7. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  8. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  9. 2022ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!cited by 134
  10. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  11. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 96
  12. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
13 more
  1. 2021Neural ODE control for classification, approximation and transportcited by 57
  2. 2022BlindFL: Vertical Federated Machine Learning without Peeking into Your Datacited by 36
  3. 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
  4. 2021FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Datacited by 31
  5. 2019Deep neural networks, generic universal interpolation, and controlled ODEscited by 28
  6. 2020Hybrid Differentially Private Federated Learning on Vertically Partitioned Datacited by 22
  7. 2020Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theorycited by 18
  8. 2022Vertical Federated Learning: A Structured Literature Reviewcited by 17
  9. 2023FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Modelscited by 17
  10. 2020Large-time asymptotics in deep learningcited by 14
  11. 2023Blind Federated Learning via Over-the-Air q-QAMcited by 8
  12. 2024Blind Federated Learning without initial modelcited by 2
  13. 2020Control on the Manifolds of Mappings with a View to the Deep Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Federated Learning for Pediatric Pneumonia Detection: Enabling Collaborative Diagnosis Without Sharing Patient Datacited by 0
  2. 2026Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifierscited by 0
  3. 2026Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approachcited by 0