Research map / Federated learning and privacy / Personalized and heterogeneous FL
Co-Boosting++: Coupled Optimization of Data and Ensemble for One-Shot Federated Learning
Xun Yang, Rong Dai, Yonggang Zhang, Ang Li, Tongliang Liu, Bo Han
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 hard sample generation loss (GHS) (ablation) | Co-Boosting baseline · CIFAR-10 (Dir 0.05) | accuracy: 39.72 -> 42.85 | Improved |
| add on-the-fly diverse hard samples (DHS) (ablation) | Co-Boosting baseline · CIFAR-10 (Dir 0.05) | accuracy: 39.72 -> 43.75 | Improved |
| add ensemble enhancement by reweighting (EE) (ablation) | Co-Boosting baseline · CIFAR-10 (Dir 0.05) | accuracy: 39.72 -> 41.45 | Improved |
| add ensemble enhancement to GHS+DHS (ablation) | Co-Boosting · CIFAR-10 (Dir 0.05) | accuracy: 44.36 -> 47.20 | Improved |
| add hard sample generation loss (GHS) to DHS+EE (ablation) | Co-Boosting · SVHN (Dir 0.05) | accuracy: 63.42 -> 65.40 | Improved |
| add DHS to GHS+EE (ablation) | Co-Boosting · SVHN (Dir 0.05) | accuracy: 64.40 -> 65.40 | Improved |
| add all three components (GHS, DHS, EE) (ablation) | Co-Boosting baseline · SVHN (Dir 0.05) | accuracy: 58.46 -> 65.40 | Improved |
| learn ensemble weights on hard synthetic samples instead of averaging | FedENS · CIFAR-10 (Dir 0.1) | ensemble accuracy: 49.99 -> 59.86 | Improved |
| use Co-Boosting instead of DENSE | DENSE · MNIST (Dir 0.05) | accuracy: 81.06 -> 93.93 | Improved |
| use Co-Boosting instead of FedDF with real validation data | FedDF · MNIST (Dir 0.3) | accuracy: 97.66 -> 97.25 | No clear effect |
| use Co-Boosting instead of DENSE | DENSE · MNIST-M domain SYN (CNN server) | accuracy: 79.90 -> 78.67 | Hurt |
| use Co-Boosting instead of DENSE as client count grows to 50 | DENSE · CIFAR-10 (50 clients) | accuracy: 28.51 -> 42.29 | Improved |
Later papers that compared with this method
1 later accepted paper reports Co-Boosting as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics (ICLR 2026 · better on 3 of 3 shared results)
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.
- DENSE — DENSE: Data-Free One-Shot Federated Learning (NeurIPS 2022) · better on 17 of 17 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
- Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting (ICLR 2024 · similarity 0.98)
- Revisiting Ensembling in One-Shot Federated Learning (NeurIPS 2024 · similarity 0.86)
- One-shot Federated Learning via Synthetic Distiller-Distillate Communication (NeurIPS 2024 · similarity 0.86)
- FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion (NeurIPS 2024 · similarity 0.86)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 2024 · similarity 0.85)
- FedBEns: One-Shot Federated Learning based on Bayesian Ensemble (ICML 2025 · 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.
