mlsanityData to 7 Oct 2026

Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization

arXiv 2008.01558 ↗First posted 1 Aug 2020cs.LG cs.CR stat.MLcited by 25

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarantee. Existing DP mechanisms would introduce random noise with magnitude proportional to the model size, which can be quite large in deep neural networks. In this paper, we propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee. Since sparsification would increase the number of communication rounds required to achieve a certain target accuracy, which is unfavorable for DP guarantee, we further introduce acceleration techniques to help reduce the privacy cost. We rigorously analyze the convergence of our approach and utilize Renyi DP to tightly account the end-to-end DP guarantee. Extensive experiments on benchmark datasets validate that our approach outperforms previous differentially-private FL approaches in both privacy guarantee and communication efficiency.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 7; 2023: 9; 2024: 6; 2025: 2.

25 papers.

Sort:

  1. 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
  2. 2022Differentially Private Federated Learning with Local Regularization and Sparsificationcited by 35
  3. 2023Make Landscape Flatter in Differentially Private Federated Learningcited by 33
  4. 2024Advances and Open Challenges in Federated Foundation Modelscited by 33
  5. 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 32
  6. 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
  7. 2023Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimationcited by 22
  8. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  9. 2022Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networkingcited by 18
  10. 2022FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregationcited by 16
  11. 2022Federated Progressive Sparsification (Purge, Merge, Tune)+cited by 8
  12. 2023Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacycited by 8
13 more
  1. 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacycited by 5
  2. 2023Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacycited by 5
  3. 2023Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computingcited by 5
  4. 2024Improved Communication-Privacy Trade-offs in L2 Mean Estimation under Streaming Differential Privacycited by 4
  5. 2024Federated Learning under Partially Class-Disjoint Data via Manifold Reshapingcited by 4
  6. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  7. 2023PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advancecited by 2
  8. 2022FedCAT: Towards Accurate Federated Learning via Device Concatenationcited by 1
  9. 2023Unlocking the Potential of Federated Learning for Deeper Modelscited by 1
  10. 2024Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimizationcited by 1
  11. 2025Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacycited by 1
  12. 2024Online Client Scheduling and Resource Allocation for Efficient Federated Edge Learningcited by 0
  13. 2025Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networkscited by 0