中文
相关论文

相关论文: Cost-Free Personalization via Information-Geometri…

200 篇论文

Federated learning (FL) is a widely used and impactful distributed optimization framework that achieves consensus through averaging locally trained models. While effective, this approach may not align well with Bayesian inference, where the…

机器学习 · 计算机科学 2025-10-01 Nour Jamoussi , Giuseppe Serra , Photios A. Stavrou , Marios Kountouris

Conventional federated learning (FL) frameworks often suffer from training degradation due to data uncertainty and heterogeneity across local clients. Probabilistic approaches such as Bayesian neural networks (BNNs) can mitigate this issue…

机器学习 · 计算机科学 2026-03-20 Ratun Rahman , Dinh C. Nguyen

To support real-world decision-making, it is crucial for models to be well-calibrated, i.e., to assign reliable confidence estimates to their predictions. Uncertainty quantification is particularly important in personalized federated…

机器学习 · 计算机科学 2024-10-21 Boning Zhang , Dongzhu Liu , Osvaldo Simeone , Guanchu Wang , Dimitrios Pezaros , Guangxu Zhu

Bayesian personalized federated learning (BPFL) addresses challenges in existing personalized FL (PFL). BPFL aims to quantify the uncertainty and heterogeneity within and across clients towards uncertainty representations by addressing the…

机器学习 · 计算机科学 2023-10-04 Hui Chen , Hengyu Liu , Longbing Cao , Tiancheng Zhang

Personalized Bayesian federated learning (PBFL) handles non-i.i.d. client data and quantifies uncertainty by combining personalization with Bayesian inference. However, existing PBFL methods face two limitations: restrictive parametric…

机器学习 · 计算机科学 2025-10-14 Ting Wei , Biao Mei , Junliang Lyu , Renquan Zhang , Feng Zhou , Yifan Sun

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables collaborative model training across multiple distributed clients without disclosing their raw data. Personalized federated learning (pFL) has gained…

机器学习 · 计算机科学 2025-08-28 Tiandi Ye , Wenyan Liu , Kai Yao , Lichun Li , Shangchao Su , Cen Chen , Xiang Li , Shan Yin , Ming Gao

Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients. To address these challenges, this paper proposes a novel personalized federated learning method via Bayesian…

机器学习 · 计算机科学 2022-06-17 Xu Zhang , Yinchuan Li , Wenpeng Li , Kaiyang Guo , Yunfeng Shao

Federated Learning (FL) has emerged as a promising method to collaboratively learn from decentralized and heterogeneous data available at different clients without the requirement of data ever leaving the clients. Recent works on FL have…

机器学习 · 计算机科学 2024-11-28 Shivam Pal , Aishwarya Gupta , Saqib Sarwar , Piyush Rai

Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization…

机器学习 · 计算机科学 2023-10-17 Jianqing Zhang , Yang Hua , Hao Wang , Tao Song , Zhengui Xue , Ruhui Ma , Jian Cao , Haibing Guan

Federated learning (FL for simplification) is a distributed machine learning technique that utilizes global servers and collaborative clients to achieve privacy-preserving global model training without direct data sharing. However,…

机器学习 · 计算机科学 2022-11-28 Mingjia Shi , Yuhao Zhou , Qing Ye , Jiancheng Lv

Federated Learning (FL) is a distributed learning scheme to train a shared model across clients. One common and fundamental challenge in FL is that the sets of data across clients could be non-identically distributed and have different…

机器学习 · 计算机科学 2023-05-23 Junyi Zhu , Xingchen Ma , Matthew B. Blaschko

Federated learning (FL) can help promote data privacy by training a shared model in a de-centralized manner on the physical devices of clients. In the presence of highly heterogeneous distributions of local data, personalized FL strategy…

机器学习 · 统计学 2022-10-12 Zhe Liu , Yue Hui , Fuchun Peng

Personalized Federated Learning (PFL) enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new PFL approach in which each agent optimizes a weighted combination of all agents'…

机器学习 · 计算机科学 2026-03-04 Jean-Baptiste Fermanian , Batiste Le Bars , Aurélien Bellet

Federated Learning (FL) aims to infer a shared model from private and decentralized data stored by multiple clients. Personalized FL (PFL) enhances the model's fit for each client by adapting the global model to the clients. A significant…

机器学习 · 计算机科学 2025-03-27 Mahrokh Ghoddousi Boroujeni , Andreas Krause , Giancarlo Ferrari Trecate

Investigation of the degree of personalization in federated learning algorithms has shown that only maximizing the performance of the global model will confine the capacity of the local models to personalize. In this paper, we advocate an…

机器学习 · 计算机科学 2020-11-09 Yuyang Deng , Mohammad Mahdi Kamani , Mehrdad Mahdavi

Traditional Federated Learning (FL) methods encounter significant challenges when dealing with heterogeneous data and providing personalized solutions for non-IID scenarios. Personalized Federated Learning (PFL) approaches aim to address…

机器学习 · 计算机科学 2025-11-11 Yasaman Saadati , Mohammad Rostami , M. Hadi Amini

Federated Learning provides a privacy-preserving paradigm for distributed learning, but suffers from statistical heterogeneity across clients. Personalized Federated Learning (PFL) mitigates this issue by considering client-specific models.…

机器学习 · 统计学 2026-02-17 Ala Emrani , Amir Najafi , Abolfazl Motahari

Bayesian Federated Learning (BFL) enables uncertainty quantification and robust adaptation in distributed learning. In contrast to the frequentist approach, it estimates the posterior distribution of a global model, offering insights into…

机器学习 · 计算机科学 2025-04-23 Usevalad Milasheuski , Luca Barbieri , Sanaz Kianoush , Monica Nicoli , Stefano Savazzi

Personalization aims to characterize individual preferences and is widely applied across many fields. However, conventional personalized methods operate in a centralized manner, potentially exposing raw data when pooling individual…

机器学习 · 计算机科学 2025-08-06 Hao Di , Yi Yang , Haishan Ye , Xiangyu Chang

Federated learning (FL) is a distributed learning framework that leverages commonalities between distributed client datasets to train a global model. Under heterogeneous clients, however, FL can fail to produce stable training results.…

机器学习 · 计算机科学 2024-11-04 Connor J. Mclaughlin , Lili Su
‹ 上一页 1 2 3 10 下一页 ›