AI Paper Atlas

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

TPAMI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 28 citations (OpenAlex)

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 changedWhereMeasuredEffect
add hard sample generation loss (GHS) (ablation)Co-Boosting baseline · CIFAR-10 (Dir 0.05)accuracy: 39.72 -> 42.85Improved
add on-the-fly diverse hard samples (DHS) (ablation)Co-Boosting baseline · CIFAR-10 (Dir 0.05)accuracy: 39.72 -> 43.75Improved
add ensemble enhancement by reweighting (EE) (ablation)Co-Boosting baseline · CIFAR-10 (Dir 0.05)accuracy: 39.72 -> 41.45Improved
add ensemble enhancement to GHS+DHS (ablation)Co-Boosting · CIFAR-10 (Dir 0.05)accuracy: 44.36 -> 47.20Improved
add hard sample generation loss (GHS) to DHS+EE (ablation)Co-Boosting · SVHN (Dir 0.05)accuracy: 63.42 -> 65.40Improved
add DHS to GHS+EE (ablation)Co-Boosting · SVHN (Dir 0.05)accuracy: 64.40 -> 65.40Improved
add all three components (GHS, DHS, EE) (ablation)Co-Boosting baseline · SVHN (Dir 0.05)accuracy: 58.46 -> 65.40Improved
learn ensemble weights on hard synthetic samples instead of averagingFedENS · CIFAR-10 (Dir 0.1)ensemble accuracy: 49.99 -> 59.86Improved
use Co-Boosting instead of DENSEDENSE · MNIST (Dir 0.05)accuracy: 81.06 -> 93.93Improved
use Co-Boosting instead of FedDF with real validation dataFedDF · MNIST (Dir 0.3)accuracy: 97.66 -> 97.25No clear effect
use Co-Boosting instead of DENSEDENSE · MNIST-M domain SYN (CNN server)accuracy: 79.90 -> 78.67Hurt
use Co-Boosting instead of DENSE as client count grows to 50DENSE · CIFAR-10 (50 clients)accuracy: 28.51 -> 42.29Improved

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.

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy