Research map / Federated learning and privacy / Personalized and heterogeneous FL
DENSE: Data-Free One-Shot Federated Learning
Jie Zhang, Chen Chen, Bo Li, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chunhua Shen, Chao Wu
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 |
|---|---|---|---|
| add BN loss and boundary-support loss to CE generator loss (ablation) | DENSE generator · CIFAR10 | accuracy (%): 53.12 -> 62.19 | Improved |
| add BN loss and boundary-support loss to CE generator loss (ablation) | DENSE generator · SVHN | accuracy (%): 73.11 -> 80.03 | Improved |
| add BN loss and boundary-support loss to CE generator loss (ablation) | DENSE generator · CIFAR100 | accuracy (%): 36.47 -> 42.07 | Improved |
| add BN regularization loss to generator (ablation) | DENSE · CIFAR10 | accuracy (%): 61.05 -> 62.19 | Improved |
| add BN regularization loss to generator (ablation) | DENSE · CIFAR100 | accuracy (%): 39.89 -> 42.07 | Improved |
| add boundary support (divergence) loss to generator (ablation) | DENSE · CIFAR10 | accuracy (%): 59.18 -> 62.19 | Improved |
| add boundary support (divergence) loss to generator (ablation) | DENSE · SVHN | accuracy (%): 77.59 -> 80.03 | Improved |
| use LDAM in clients' local training | DENSE · CIFAR10 alpha=0.1 | accuracy (%): 50.26 -> 57.24 | Improved |
| use LDAM in clients' local training | DENSE · SVHN alpha=0.5 | accuracy (%): 80.03 -> 81.77 | Improved |
| add more communication rounds (1 to 5) | DENSE · CIFAR10 alpha=0.5 | accuracy (%): 63.89 -> 76.01 | Improved |
| distill ensemble with synthetic data instead of FedAvg parameter averaging | DENSE · CIFAR10 alpha=0.3 | accuracy (%): 27.72 -> 59.76 | Improved |
| increase number of clients from 5 to 100 | DENSE · CIFAR10 | accuracy (%): 62.19 -> 43.28 | Hurt |
Later papers that compared with this method
9 later accepted papers report DENSE as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.
- Co-Boosting++: Coupled Optimization of Data and Ensemble for One-Shot Federated Learning (TPAMI 2026 · better on 17 of 17 shared results)
- The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics (ICLR 2026 · better on 3 of 3 shared results)
- Privacy-Preserving Model Transcription With Differentially Private Synthetic Distillation (TPAMI 2026 · better on 2 of 2 shared results)
- FedBEns: One-Shot Federated Learning based on Bayesian Ensemble (ICML 2025 · better on 2 of 2 shared results)
- Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework (ICML 2025 · better on 1 of 1 shared result)
- FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion (NeurIPS 2024 · better on 7 of 7 shared results)
- One-shot Federated Learning via Synthetic Distiller-Distillate Communication (NeurIPS 2024 · better on 4 of 4 shared results)
- FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation (NeurIPS 2024 · better on 4 of 4 shared results)
1 more not listed.
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
- One-shot Federated Learning via Synthetic Distiller-Distillate Communication (NeurIPS 2024 · similarity 0.91)
- One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models (ICML 2025 · similarity 0.89)
- Revisiting Ensembling in One-Shot Federated Learning (NeurIPS 2024 · similarity 0.89)
- FedBEns: One-Shot Federated Learning based on Bayesian Ensemble (ICML 2025 · similarity 0.88)
- FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion (NeurIPS 2024 · similarity 0.88)
- Capture Global Feature Statistics for One-Shot Federated Learning (AAAI 2025 · 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.
