mlsanityData to 7 Oct 2026

Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation

arXiv 2602.15996 ↗First posted 17 Feb 2026math.OC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The objective of Vertical Federated Learning (VFL) is to collectively train a model using features available on different devices while sharing the same users. This paper focuses on the saddle point reformulation of the VFL problem via the classical Lagrangian function. We first demonstrate how this formulation can be solved using deterministic methods. More importantly, we explore various stochastic modifications to adapt to practical scenarios, such as employing compression techniques for efficient information transmission, enabling partial participation for asynchronous communication, and utilizing coordinate selection for faster local computation. We show that the saddle point reformulation plays a key role and opens up possibilities to use mentioned extension that seem to be impossible in the standard minimization formulation. Convergence estimates are provided for each algorithm, demonstrating their effectiveness in addressing the VFL problem. Additionally, alternative reformulations are investigated, and numerical experiments are conducted to validate performance and effectiveness of the proposed approach.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 70 references that are in the map. First posted on arXiv 17 Feb 2026.

Builds on

36 of 70 references.

References · 36

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2014SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectivescited by 401
  6. 2019Error Feedback Fixes SignSGD and other Gradient Compression Schemescited by 306
  7. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  8. 2019PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimizationcited by 234
  9. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  10. 2019A Survey on Distributed Machine Learningcited by 187
  11. 2013Minimizing Finite Sums with the Stochastic Average Gradientcited by 164
  12. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
24 more
  1. 2020On Biased Compression for Distributed Learningcited by 140
  2. 2021EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedbackcited by 131
  3. 2020Optimal Client Sampling for Federated Learningcited by 123
  4. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  5. 2019Natural Compression for Distributed Deep Learningcited by 88
  6. 2016CoCoA: A General Framework for Communication-Efficient Distributed Optimizationcited by 69
  7. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  8. 2021Stochastic Variance Reduction for Variational Inequality Methodscited by 46
  9. 2020Error Compensated Distributed SGD Can Be Acceleratedcited by 45
  10. 2020Communication-Efficient Federated Learning via Optimal Client Samplingcited by 39
  11. 2020When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Controlcited by 32
  12. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  13. 2019On Lower Iteration Complexity Bounds for the Saddle Point Problemscited by 28
  14. 2022Vertical Federated Learning: A Structured Literature Reviewcited by 17
  15. 2013On Optimal Probabilities in Stochastic Coordinate Descent Methodscited by 14
  16. 2014Coordinate Descent with Arbitrary Sampling I: Algorithms and Complexitycited by 14
  17. 2019Learning Privately over Distributed Features: An ADMM Sharing Approachcited by 14
  18. 2021Failure Prediction in Production Line Based on Federated Learning: An Empirical Studycited by 11
  19. 2022Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMMcited by 10
  20. 2021An Optimal Algorithm for Strongly Convex Minimization under Affine Constraintscited by 8
  21. 2021Efficient Batch Homomorphic Encryption for Vertically Federated XGBoostcited by 6
  22. 2023On a Unified and Simplified Proof for the Ergodic Convergence Rates of PPM, PDHG and ADMMcited by 5
  23. 2014Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Noisy Matrix Decompositioncited by 2
  24. 2024Accelerated Methods with Compression for Horizontal and Vertical Federated Learningcited by 1

Built on by

Not cited yet.