FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningPrivacy PreservingVertical Federated LearningSimilar Papers 제목 키워드 기반
Straggler-Resilient Differentially-Private Decentralized Learning
We consider the straggler problem in decentralized learning over a logical ring while preserving user data privacy. Especially, we extend the recently proposed framework of differential privacy (DP) amplification by dece…
image-classificationImage ClassificationregressionA Vertical Federated Learning Framework for Horizontally Partitioned Labels
Vertical federated learning is a collaborative machine learning framework to train deep leaning models on vertically partitioned data with privacy-preservation. It attracts much attention both from academia and industry.…
Federated LearningVertical Federated LearningFedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution
Video Super-Resolution (VSR) reconstructs high-resolution videos from low-resolution inputs to restore fine details and improve visual clarity. While deep learning-based VSR methods achieve impressive results, their cent…
Federated LearningFederated Learning (Video Super-Resolution)Super-ResolutionVideo Super-ResolutionSecure Vertical Federated Learning Under Unreliable Connectivity
Most work in privacy-preserving federated learning (FL) has focused on horizontally partitioned datasets where clients hold the same features and train complete client-level models independently. However, individual data…
Federated LearningPrivacy PreservingVertical Federated LearningFLOSS: Federated Learning with Opt-Out and Straggler Support
Previous work on data privacy in federated learning systems focuses on privacy-preserving operations for data from users who have agreed to share their data for training. However, modern data privacy agreements also empo…
Federated Learning