Research map / Federated learning and privacy / Differential privacy
FedAlign: Differentially Private Distribution Alignment for Non-IID Federated Learning
Peng Wu, Jiapeng Zhang, Yingjie Song, Xiong Xiao, Zhuo Tang
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 |
|---|---|---|---|
| use all global unsampled data for alignment instead of 40% (ablation) | FedAlign · CIFAR-10 (CNN) | test accuracy at 100 rounds: about 16% higher | Improved |
| align mean and variance (vs ignoring alignment of higher moments) (ablation) | FedAlign · CIFAR-10 (CNN) | test accuracy | Improved |
| additionally align skewness and kurtosis beyond mean and variance (ablation) | FedAlign · CIFAR-10 (CNN) | test accuracy | Improved |
| use FedAlign instead of FedRDN | FedAlign · CIFAR-10 (β=0.05) | test accuracy: 52.8 -> 54.9 | Improved |
| use FedAlign instead of FedAvg | FedAlign · CIFAR-10 (β=0.1) | test accuracy: 50.7 -> 54.3 | Improved |
| use FedAlign instead of Scaffold on MNIST | FedAlign · MNIST (β=0.1) | test accuracy: 99.12 -> 99.12 | No clear effect |
| use FedAlign instead of FedAvg on MNIST | FedAlign · MNIST (β=0.05) | test accuracy: 99.13 -> 99.26 | No clear effect |
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 3 of 4 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
- Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off (ICML 2025 · similarity 0.88)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.88)
- A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs (NeurIPS 2024 · similarity 0.88)
- FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024 · similarity 0.88)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.87)
- Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity (CVPR 2024 · similarity 0.87)
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.
