mlsanityData to 7 Oct 2026

FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection

arXiv 2003.10637 ↗First posted 24 Mar 2020cs.LG cs.CR stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

As massive data are produced from small gadgets, federated learning on mobile devices has become an emerging trend. In the federated setting, Stochastic Gradient Descent (SGD) has been widely used in federated learning for various machine learning models. To prevent privacy leakages from gradients that are calculated on users' sensitive data, local differential privacy (LDP) has been considered as a privacy guarantee in federated SGD recently. However, the existing solutions have a dimension dependency problem: the injected noise is substantially proportional to the dimension d. In this work, we propose a two-stage framework FedSel for federated SGD under LDP to relieve this problem. Our key idea is that not all dimensions are equally important so that we privately select Top-k dimensions according to their contributions in each iteration of federated SGD. Specifically, we propose three private dimension selection mechanisms and adapt the gradient accumulation technique to stabilize the learning process with noisy updates. We also theoretically analyze privacy, accuracy and time complexity of FedSel, which outperforms the state-of-the-art solutions. Experiments on real-world and synthetic datasets verify the effectiveness and efficiency of our framework.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 6; 2023: 4; 2024: 3; 2025: 4; 2026: 2.

35 papers.

Sort:

  1. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
  2. 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 38
  3. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
  4. 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 32
  5. 2021Stronger Privacy for Federated Collaborative Filtering with Implicit Feedbackcited by 26
  6. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  7. 2021Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learningcited by 17
  8. 2021Transparent Contribution Evaluation for Secure Federated Learning on Blockchaincited by 16
  9. 2022DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decodercited by 14
  10. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  11. 2021FL-Market: Trading Private Models in Federated Learningcited by 9
  12. 2021Efficient and Reliable Overlay Networks for Decentralized Federated Learningcited by 9
23 more
  1. 2021Improving Differentially Private SGD via Randomly Sparsified Gradientscited by 8
  2. 2021Constrained Differentially Private Federated Learning for Low-bandwidth Devicescited by 6
  3. 2021Wireless Federated Learning with Limited Communication and Differential Privacycited by 6
  4. 2021FLSys: Toward an Open Ecosystem for Federated Learning Mobile Appscited by 6
  5. 2021Task-aware Privacy Preservation for Multi-dimensional Datacited by 5
  6. 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacycited by 5
  7. 2023Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacycited by 5
  8. 2022OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsificationcited by 4
  9. 2022FedPerm: Private and Robust Federated Learning by Parameter Permutationcited by 3
  10. 2023FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learningcited by 3
  11. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  12. 2021On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Timescited by 2
  13. 2021Lightweight Transformer in Federated Setting for Human Activity Recognitioncited by 2
  14. 2021Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacycited by 1
  15. 2024Beyond Statistical Estimation: Differentially Private Individual Computation via Shufflingcited by 1
  16. 2025AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networkscited by 1
  17. 2021Understanding the Interplay between Privacy and Robustness in Federated Learningcited by 0
  18. 2022sqSGD: Locally Private and Communication Efficient Federated Learningcited by 0
  19. 2025FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learningcited by 0
  20. 2025Progressive Size-Adaptive Federated Learning: A Comprehensive Framework for Heterogeneous Multi-Modal Data Systemscited by 0
  21. 2025Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learningcited by 0
  22. 2026Classification Under Local Differential Privacy with Model Reversal and Model Averagingcited by 0
  23. 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregationcited by 0