Research map / Federated learning and privacy / Personalized and heterogeneous FL
DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing
Jiawei Shao, Yuchang Sun, Songze Li, Jun Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace FedAvg-style aggregation with DReS-FL | non-IID FL with dropout · MNIST | test accuracy (%): 96.17 -> 97.38 | Improved |
| replace FedAvg-style aggregation with DReS-FL | non-IID FL with dropout · Fashion-MNIST | test accuracy (%): 81.20 -> 86.60 | Improved |
| replace FedAvg-style aggregation with DReS-FL | non-IID FL with dropout · EMNIST | test accuracy (%): 71.50 -> 78.04 | Improved |
| replace FedAvg-style aggregation with DReS-FL | non-IID FL with dropout · CIFAR-10 | test accuracy (%): 89.54 -> 90.31 | Improved |
| replace FedAvg-style aggregation with DReS-FL | non-IID FL with dropout · CIFAR-100 | test accuracy (%): 67.71 -> 69.15 | Improved |
| replace FedAvg-style aggregation with DReS-FL | non-IID FL with dropout · SVHN | test accuracy (%): 83.82 -> 86.04 | Improved |
| weight client updates by known participation probability (FedAvg-IS) | FedAvg · Fashion-MNIST | test accuracy (%): 81.20 -> 85.94 | Improved |
| use SCAFFOLD control variates under non-IID and dropout | FedAvg · CIFAR-100 | test accuracy (%): 67.71 -> 29.97 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SCAFFOLD — SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (ICML 2020) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space (CVPR 2024 · similarity 0.86)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.86)
- DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing (ICML 2025 · similarity 0.85)
- Towards Trustworthy Federated Learning with Untrusted Participants (ICML 2025 · similarity 0.85)
- Concealing Sensitive Samples against Gradient Leakage in Federated Learning (AAAI 2024 · similarity 0.85)
- Federated Learning via Input-Output Collaborative Distillation (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
