paper-with-me

Papers

Geometric Prior-Guided Federated Prompt Calibration

2025-12-08 · Fei Luo, Ziwei Zhao, Mingxuan Wang, Duoyang Li, Zhe Qian, Jiayi Tuo, Chenyue Zhou, Yanbiao Ma arxiv

Federated Prompt Learning (FPL) offers a parameter-efficient solution for collaboratively training large models, but its performance is severely hindered by data heterogeneity, which causes locally trained prompts to become biased. Existing methods, focusing on aggregation or regularization, fail to address this root cause of local training bias. To this end, we propose Geometry-Guided Text Prompt Calibration (GGTPC), a novel framework that directly corrects this bias by providing clients with a global geometric prior. This prior, representing the shape of the global data distribution derived from the covariance matrix, is reconstructed on the server in a privacy-preserving manner. Clients then use a novel Geometry-Prior Calibration Layer (GPCL) to align their local feature distributions with this global prior during training. Extensive experiments show GGTPC's effectiveness. On the label-skewed CIFAR-100 dataset ($β$=0.1), it outperforms the state-of-the-art by 2.15\%. Under extreme skew ($β$=0.01), it improves upon the baseline by 9.17\%. Furthermore, as a plug-and-play module on the domain-skewed Office-Home dataset, it boosts FedAvg's performance by 4.60\%. These results demonstrate that GGTPC effectively mitigates data heterogeneity by correcting the fundamental local training bias, serving as a versatile module to enhance various FL algorithms.

📄 PDF Abstract BibTeX arXiv:2512.07208

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2025-08-19 · Yanbiao Ma, Wei Dai, Bowei Liu, Jiayi Chen 외 arxiv

Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for the causing of this gap e.g. sampling bi…

Federated Learning

How (Mis)calibrated is Your Federated CLIP and What To Do About It?

2025-12-03 · Mainak Singha, Masih Aminbeidokhti, Paolo Casari, Gianni Franchi 외 arxiv

While vision-language models like CLIP have been extensively studied, their calibration, crucial for reliable predictions, has received limited attention. Although a few prior works have examined CLIP calibration in offl…

Federated Learning

Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation

2026-02-21 · Shile Li, Markus Karmann, Onay Urfalioglu arxiv

We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification. Unlike prior post-training or block-wise reconstruction methods, we jointly opt…

Image Classification

FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler

2024-05-24 · Hongyi Peng, Han Yu, Xiaoli Tang, Xiaoxiao Li

Federated learning (FL) enables collaborative machine learning across distributed data owners, but data heterogeneity poses a challenge for model calibration. While prior work focused on improving accuracy for non-iid da…

Federated Learning

Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes

2026-05-28 · Chenxi Tao, Seung-Kyum Choi arxiv

Industrial visual sim-to-real is often described as transferring from synthetic images to real images, but industrial deployment usually involves a broader mismatch between available evidence and required decisions. A sy…

Pose Estimation