Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedUSD: Unbiased Synthetic Data for Federated Learning
Weiying Xie, Chenhe Hao, Haozhi Shi, Jitao Ma, Daixun Li, Jiazhe Li, Hengyi Wang, Leyuan Fang, Yunsong Li
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 FedUSD instead of FedAF | aggregation-free FL, ConvNet · CIFAR-10 (alpha=0.1) | Top-1 accuracy (%): 67.38 -> 74.73 | Improved |
| use FedUSD instead of FedAF | ConvNet · CIFAR-100 (alpha=0.01) | Top-1 accuracy (%): 34.53 -> 44.58 | Improved |
| use FedUSD instead of FedAF | ConvNet · SVHN (alpha=0.1) | Top-1 accuracy (%): 84.32 -> 89.96 | Improved |
| use FedUSD instead of FedAF | ViT-Tiny-16 · CIFAR-10 (alpha=0.1) | Top-1 accuracy (%): 47.81 -> 57.07 | Improved |
| add SEA module to baseline (ablation) | FedUSD baseline, ConvNet · CIFAR-10 (alpha=0.1) | Top-1 accuracy (%): 62.15 -> 72.50 | Improved |
| add USD loss to baseline (ablation) | FedUSD baseline, ConvNet · CIFAR-10 (alpha=0.1) | Top-1 accuracy (%): 62.15 -> 69.61 | Improved |
| add USD loss to baseline with SEA (full FedUSD) (ablation) | FedUSD, ConvNet · CIFAR-10 (alpha=0.1) | Top-1 accuracy (%): 72.50 -> 74.73 | Improved |
| add USD loss and SEA to baseline (ablation) | FedUSD, ConvNet · CIFAR-100 (alpha=0.01) | Top-1 accuracy (%): 28.61 -> 44.58 | Improved |
| increase IPC from 1 to 10 (ablation) | FedUSD, ConvNet · CIFAR-10 (alpha=0.1) | Top-1 accuracy (%): 48.14 -> 74.73 | Improved |
| increase IPC from 10 to 50 (ablation) | FedUSD, ConvNet · CIFAR-10 (alpha=0.1) | Top-1 accuracy (%): 74.73 -> 81.14 | Improved |
| use FedUSD instead of FedAvg for communication | ConvNet, alpha=0.01 · CIFAR-10 | communication cost: 256.0MB -> 35.2MB | Improved |
| use FedUSD instead of FedDM for communication | ConvNet, alpha=0.01 · CIFAR-10 | communication cost: 35.2MB -> 35.2MB | 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.
- FedDM — FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning (CVPR 2023) · better on 12 of 12 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
- Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization (ICLR 2025 · similarity 0.86)
- Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning (NeurIPS 2025 · similarity 0.86)
- FedUV: Uniformity and Variance for Heterogeneous Federated Learning (CVPR 2024 · similarity 0.86)
- Fake It Till Make It: Federated Learning with Consensus-Oriented Generation (ICLR 2024 · similarity 0.86)
- An Aggregation-Free Federated Learning for Tackling Data Heterogeneity (CVPR 2024 · similarity 0.86)
- FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation (NeurIPS 2024 · similarity 0.86)
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.
