AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Guiding Diffusion Models with Fine-Grained Conditions and Semantics-Preserving Sampling for One-Shot Federated Learning

Xiaojun Deng, Tianchi Liao, Zhiyuan Liu, Chuan Chen, Zibin Zheng

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models

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 Fine-Grained Condition Learning (intra-category clusters) (ablation)Prompts-only · DomainNet avgaccuracy: 64.00 -> 73.46Improved
add Fine-Grained Condition Learning (ablation)Prompts-only · PACS avgaccuracy: 70.90 -> 75.30Improved
add GMM of latent noises on top of C (ablation)Espresso · PACS avgaccuracy: 75.30 -> 79.86Improved
add Z-Sampling on top of C (ablation)Espresso · PACS avgaccuracy: 75.30 -> 80.13Improved
add both GMM and Z-Sampling to C (ablation)Espresso · DomainNet avgaccuracy: 73.46 -> 75.32Improved
add both GMM and Z-Sampling to C (ablation)Espresso · Common NICO++ avgaccuracy: 80.88 -> 82.16Improved
use Espresso over FedBiPEspresso · DomainNet quickdrawaccuracy: 70.18 -> 80.18Improved
use Espresso over FedBiPEspresso · DomainNet sketchaccuracy: 77.74 -> 71.96Hurt
use Espresso over FedDEOEspresso · PACS photoaccuracy: 92.05 -> 90.46Hurt
increase number of intra-category clusters J (ablation)Espresso · DomainNet and PACSaccuracyImproved
use 1 GMM component instead of 2 to 4 (ablation)Espresso · DomainNet/PACS/NICO++accuracyHurt

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