mlsanityData to 7 Oct 2026

FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models

arXiv 2304.13407 ↗First posted 26 Apr 2023cs.LG cs.CR cs.ITcited by 17

Not on the map. Why?

Abstract (arXiv)

In a vertical federated learning (VFL) system consisting of a central server and many distributed clients, the training data are vertically partitioned such that different features are privately stored on different clients. The problem of split VFL is to train a model split between the server and the clients. This paper aims to address two major challenges in split VFL: 1) performance degradation due to straggling clients during training; and 2) data and model privacy leakage from clients' uploaded data embeddings. We propose FedVS to simultaneously address these two challenges. The key idea of FedVS is to design secret sharing schemes for the local data and models, such that information-theoretical privacy against colluding clients and curious server is guaranteed, and the aggregation of all clients' embeddings is reconstructed losslessly, via decrypting computation shares from the non-straggling clients. Extensive experiments on various types of VFL datasets (including tabular, CV, and multi-view) demonstrate the universal advantages of FedVS in straggler mitigation and privacy protection over baseline protocols.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 50 of its 72 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

50 of 72 references.

References · 50

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  5. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  6. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  7. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  8. 2019Asynchronous Federated Optimizationcited by 264
  9. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  10. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  11. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
  12. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 174
38 more
  1. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  2. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  3. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  4. 2019Secure Federated Matrix Factorizationcited by 102
  5. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  6. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 89
  7. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  8. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  9. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  10. 2014On the Computational Efficiency of Training Neural Networkscited by 71
  11. 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
  12. 2020FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tierscited by 64
  13. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  14. 2020Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneitycited by 56
  15. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  16. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
  17. 2019Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinatorcited by 51
  18. 2020Multi-Participant Multi-Class Vertical Federated Learningcited by 47
  19. 2020SplitNN-driven Vertical Partitioningcited by 42
  20. 2021Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updatingcited by 37
  21. 2020Coded Computing for Low-Latency Federated Learning over Wireless Edge Networkscited by 32
  22. 2022Privacy-Preserving Aggregation in Federated Learning: A Surveycited by 25
  23. 2020Hybrid Differentially Private Federated Learning on Vertically Partitioned Datacited by 22
  24. 2020Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noisecited by 21
  25. 2021CodedPaddedFL and CodedSecAgg: Straggler Mitigation and Secure Aggregation in Federated Learningcited by 20
  26. 2022Flexible Vertical Federated Learning with Heterogeneous Partiescited by 20
  27. 2020Communication-Computation Efficient Secure Aggregation for Federated Learningcited by 18
  28. 2022SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learningcited by 18
  29. 2022Efficient Dropout-resilient Aggregation for Privacy-preserving Machine Learningcited by 18
  30. 2022DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharingcited by 17
  31. 2020Coded Federated Learningcited by 14
  32. 2022SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guaranteescited by 14
  33. 2021Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradientscited by 13
  34. 2022Stochastic Coded Federated Learning with Convergence and Privacy Guaranteescited by 10
  35. 2019Achieving Differential Privacy in Vertically Partitioned Multiparty Learningcited by 8
  36. 2022Secure Forward Aggregation for Vertical Federated Neural Networkscited by 6
  37. 2022Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Designcited by 6
  38. 2021Ladder Polynomial Neural Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 5; 2026: 3.

17 papers.

Sort:

  1. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  2. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
  3. 2023FLTracer: Accurate Poisoning Attack Provenance in Federated Learningcited by 4
  4. 2024Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splittingcited by 4
  5. 2024URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learningcited by 3
  6. 2025The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communicationscited by 3
  7. 2023Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environmentscited by 2
  8. 2024Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Needcited by 2
  9. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  10. 2024Decoupled Vertical Federated Learning for Practical Training on Vertically Partitioned Datacited by 1
  11. 2025OPUS-VFL: Incentivizing Optimal Privacy-Utility Tradeoffs in Vertical Federated Learningcited by 1
  12. 2023EASTER: Embedding Aggregation-based Heterogeneous Models Training in Vertical Federated Learningcited by 0
5 more
  1. 2025PBM-VFL: Vertical Federated Learning with Feature and Sample Privacycited by 0
  2. 2025An Empirical Study of the Impact of Federated Learning on Machine Learning Model Accuracycited by 0
  3. 2026Learning Unknown Interdependencies for Decentralized Root Cause Analysis in Nonlinear Dynamical Systemscited by 0
  4. 2026LEA: Label Enumeration Attack in Vertical Federated Learningcited by 0
  5. 2026LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projectionscited by 0