AI Paper Atlas

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

Calibrating Biased Distribution in VFM-Derived Latent Space via Cross-Domain Geometric Consistency

Yanbiao Ma, Wei Dai, Bowei Liu, Jiayi Chen, Wenke Huang, Guancheng Wan, Zhiwu Lu, Junchi Yan

TPAMI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated medical and multimodal learning · 0 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 GGEUR distribution calibrationFedAvg (CLIP+MLP) · CIFAR-100 label skew beta=0.1accuracy: 68.22 -> 77.70Improved
add GGEUR distribution calibrationFedAvg (CLIP+MLP) · CIFAR-100 label skew beta=0.01accuracy: 58.71 -> 75.72Improved
add GGEUR distribution calibrationFedAvg (CLIP+MLP) · CIFAR-100 label skew beta=0.5accuracy: 81.41 -> 83.31Improved
add GGEUR distribution calibrationFedAvg (CLIP+MLP) · Tiny-ImageNet label skew beta=0.01accuracy: 53.03 -> 64.27Improved
add GGEUR distribution calibrationFedAvg (CLIP+MLP) · CIFAR-10 label skew beta=0.01accuracy: 90.87 -> 94.39Improved
add GGEUR Step 1 (local augmentation) to FedAvg (ablation)FedAvg (CLIP+MLP) · Digitsaverage accuracy: 76.60 -> 80.18Improved
add GGEUR Step 2 on top of Step 1 (ablation)FedAvg (CLIP+MLP) · Digitsaverage accuracy: 80.18 -> 82.36Improved
add GGEUR Step 2 on top of Step 1 (ablation)MOON (CLIP+MLP) · Digitsaverage accuracy: 67.50 -> 78.13Improved
add GGEUR Step 1 to MOON (ablation)MOON (CLIP+MLP) · Digitsaverage accuracy: 60.07 -> 67.50Improved
add GGEURMOON (CLIP+MLP) · DigitsSTD across domains: 15.14 -> 16.08Mixed
add GGEURMOON (CLIP+MLP) · Office-Home-LDSaverage accuracy: 76.83 -> 78.08Improved
add GGEURFedOPT (CLIP+MLP) · Office-Home-LDSaverage accuracy: 65.59 -> 84.20Improved

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