AI Paper Atlas

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

FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning

Huan Wang, Haoran Li, Huaming Chen, Jun Yan, Jiahua Shi, Jun Shen

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 4 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 TDCL (ablation)baseline · CIFAR10 (NID1/NID2 average)accuracy: 80.41 -> 82.81Improved
add NDCR (ablation)baseline · CIFAR10 (NID1/NID2 average)accuracy: 80.41 -> 82.40Improved
add NDCR to TDCL (ablation)TDCL · CIFAR10 (NID1/NID2 average)accuracy: 82.81 -> 84.29Improved
add TDCL (ablation)baseline · CIFAR10-LT (NID1_0.2, rho average)accuracy: 60.46 -> 61.31Improved
add NDCR (ablation)baseline · CIFAR10-LT (NID1_0.2, rho average)accuracy: 60.46 -> 61.50Improved
add NDCR to TDCL (ablation)TDCL · CIFAR10-LT (NID1_0.2, rho average)accuracy: 61.31 -> 62.25Improved
use fused multi-layer diffusion features instead of best single layer (L=2) (ablation)FedDifRC · CIFAR10 NID1_0.05accuracy: 82.60 -> 83.14Improved
use fused multi-layer diffusion features instead of best single layer (L=3) (ablation)FedDifRC · CIFAR10 NID1_0.2accuracy: 87.81 -> 88.27Improved
use fused multi-layer diffusion features instead of best single layer (L=2) (ablation)FedDifRC · CIFAR10 NID1_0.5accuracy: 89.03 -> 89.31Improved
use fused multi-layer diffusion features instead of best single layer (L=2) (ablation)FedDifRC · CIFAR10 NID2accuracy: 75.73 -> 76.45Improved
use only layer L=1 features instead of fused features (ablation)FedDifRC · CIFAR10 NID1_0.05accuracy: 83.14 -> 80.21Hurt
align raw Stable Diffusion features with L2 loss added to FedRCL instead of FedDifRC designFedRCL · CIFAR10 NID1_0.05accuracy: 82.30 -> 80.95Hurt

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