mlsanityData to 7 Oct 2026

Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing

arXiv 2305.01387 ↗First posted 2 May 2023cs.DC cs.CR cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a collaborative learning paradigm for decentralized private data from mobile terminals (MTs). However, it suffers from issues in terms of communication, resource of MTs, and privacy. Existing privacy-preserving FL methods usually adopt the instance-level differential privacy (DP), which provides a rigorous privacy guarantee but with several bottlenecks: severe performance degradation, transmission overhead, and resource constraints of edge devices such as MTs. To overcome these drawbacks, we propose Fed-LTP, an efficient and privacy-enhanced FL framework with underlineLottery underlineTicket underlineHypothesis (LTH) and zero-concentrated DunderlineP (zCDP). It generates a pruned global model on the server side and conducts sparse-to-sparse training from scratch with zCDP on the client side. On the server side, two pruning schemes are proposed: (i) the weight-based pruning (LTH) determines the pruned global model structure; (ii) the iterative pruning further shrinks the size of the pruned model's parameters. Meanwhile, the performance of Fed-LTP is also boosted via model validation based on the Laplace mechanism. On the client side, we use sparse-to-sparse training to solve the resource-constraints issue and provide tighter privacy analysis to reduce the privacy budget. We evaluate the effectiveness of Fed-LTP on several real-world datasets in both independent and identically distributed (IID) and non-IID settings. The results clearly confirm the superiority of Fed-LTP over state-of-the-art (SOTA) methods in communication, computation, and memory efficiencies while realizing a better utility-privacy trade-off.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 38 of its 54 references that are in the map. First posted on arXiv 2 May 2023.

Builds on

38 of 54 references.

References · 38

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  8. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  9. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  10. 2018LEAF: A Benchmark for Federated Settingscited by 780
  11. 2017Renyi Differential Privacycited by 643
  12. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 627
26 more
  1. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  2. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  3. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  4. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  5. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  6. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
  7. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  8. 2018Scalable Private Learning with PATEcited by 266
  9. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 219
  10. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  11. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 157
  12. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  13. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  14. 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 63
  15. 2020LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasetscited by 60
  16. 2020Federated Model Distillation with Noise-Free Differential Privacycited by 40
  17. 2022Private Adaptive Optimization with Side Informationcited by 38
  18. 2022Differentially Private Federated Learning with Local Regularization and Sparsificationcited by 35
  19. 2023Make Landscape Flatter in Differentially Private Federated Learningcited by 33
  20. 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 32
  21. 2022Achieving Personalized Federated Learning with Sparse Local Modelscited by 30
  22. 2020Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimizationcited by 25
  23. 2019Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaborationcited by 15
  24. 2021Communication-Efficient and Personalized Federated Lottery Ticket Learningcited by 10
  25. 2020Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learningcited by 5
  26. 2020The Differentially Private Lottery Ticket Mechanismcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2024A Survey of Lottery Ticket Hypothesiscited by 23
  2. 2023PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learningcited by 3
  3. 2024Heterogeneous Federated Learning with Splited Language Modelcited by 1
  4. 2025FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initializationcited by 1
  5. 2026CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstructioncited by 1