中文
相关论文

相关论文: Fine-tuning Global Model via Data-Free Knowledge D…

200 篇论文

Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving. However, one major challenge is the data heterogeneity issue, which refers to the biased labeling preferences at…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Huan Wang , Haoran Li , Huaming Chen , Jun Yan , Jiahua Shi , Jun Shen

Federated Learning (FL) is a distributed learning paradigm that enables a large number of resource-limited nodes to collaboratively train a model without data sharing. The non-independent-and-identically-distributed (non-i.i.d.) data…

机器学习 · 计算机科学 2022-02-04 Hongda Wu , Ping Wang

In federated learning, the heterogeneity of client data has a great impact on the performance of model training. Many heterogeneity issues in this process are raised by non-independently and identically distributed (non-IID) data. To…

机器学习 · 计算机科学 2026-03-25 Xiufang Shi , Wei Zhang , Yuheng Li , Mincheng Wu , Zhenyu Wen , Shibo He , Tejal Shah , Rajiv Ranjan

As people pay more and more attention to privacy protection, Federated Learning (FL), as a promising distributed machine learning paradigm, is receiving more and more attention. However, due to the biased distribution of data on devices in…

机器学习 · 计算机科学 2023-02-27 Yuquan Zhang , Yongquan Zhang

The growing interest in intelligent services and privacy protection for mobile devices has given rise to the widespread application of federated learning in Multi-access Edge Computing (MEC). Diverse user behaviors call for personalized…

机器学习 · 计算机科学 2025-02-28 Zhiyuan Wu , Sheng Sun , Yuwei Wang , Min Liu , Quyang Pan , Xuefeng Jiang , Bo Gao

Federated Learning (FL) is a recent development in distributed machine learning that collaboratively trains models without training data leaving client devices, preserving data privacy. In real-world FL, the training set is distributed over…

机器学习 · 计算机科学 2022-10-07 Jed Mills , Jia Hu , Geyong Min , Rui Jin , Siwei Zheng , Jin Wang

Federated learning (FL) is a machine learning paradigm that facilitates massively distributed model training with end-user data on edge devices directed by a central server. However, the large number of heterogeneous clients in FL…

机器学习 · 计算机科学 2025-04-23 Qifan Yan , Andrew Liu , Shiqi He , Mathias Lécuyer , Ivan Beschastnikh

Most current federated learning frameworks are modeled as static processes, ignoring the dynamic characteristics of the learning system. Under the limited communication budget of the central server, the flexible model architecture of a…

机器学习 · 计算机科学 2025-03-11 Yiting Zheng , Bohan Lin , Jinqian Chen , Jihua Zhu

In this paper, we introduce DistDD, a novel approach within the federated learning framework that reduces the need for repetitive communication by distilling data directly on clients' devices. Unlike traditional federated learning that…

机器学习 · 计算机科学 2024-10-14 Peiran Wang , Haohan Wang

Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. Data heterogeneity is a critical challenge in realistic FL settings, as it causes significant performance…

机器学习 · 计算机科学 2023-11-15 Yuwei Wang , Runhan Li , Hao Tan , Xuefeng Jiang , Sheng Sun , Min Liu , Bo Gao , Zhiyuan Wu

Recently, foundation models have exhibited remarkable advancements in multi-modal learning. These models, equipped with millions (or billions) of parameters, typically require a substantial amount of data for finetuning. However, collecting…

机器学习 · 计算机科学 2023-08-25 Haokun Chen , Yao Zhang , Denis Krompass , Jindong Gu , Volker Tresp

Federated Learning (FL) suffers significant performance degradation in real-world deployments characterized by moderate to extreme statistical heterogeneity (non-IID client data). While global aggregation strategies promote broad…

机器学习 · 计算机科学 2026-03-11 Prakash Kumbhakar , Shrey Srivastava , Haroon R Lone

Classic Machine Learning techniques require training on data available in a single data lake. However, aggregating data from different owners is not always convenient for different reasons, including security, privacy and secrecy. Data…

机器学习 · 计算机科学 2023-04-03 Bruno Casella , Roberto Esposito , Carlo Cavazzoni , Marco Aldinucci

Federated learning (FL) has emerged as a promising privacy-preserving distributed machine learning framework recently. It aims at collaboratively learning a shared global model by performing distributed training locally on edge devices and…

密码学与安全 · 计算机科学 2023-04-26 Jingcai Guo , Song Guo , Jie Zhang , Ziming Liu

Federated Learning (FL) has emerged as a promising decentralized learning (DL) approach that enables the use of distributed data without compromising user privacy. However, FL poses several key challenges. First, it is frequently assumed…

机器学习 · 计算机科学 2025-09-29 Zahid Iqbal

Federated Learning (FL) is a decentralized approach for collaborative model training on edge devices. This distributed method of model training offers advantages in privacy, security, regulatory compliance, and cost-efficiency. Our emphasis…

机器学习 · 计算机科学 2024-10-24 Charuka Herath , Xiaolan Liu , Sangarapillai Lambotharan , Yogachandran Rahulamathavan

Federated Learning (FL) is a pioneering approach in distributed machine learning, enabling collaborative model training across multiple clients while retaining data privacy. However, the inherent heterogeneity due to imbalanced resource…

机器学习 · 计算机科学 2024-11-18 Suraj Racha , Shubh Gupta , Humaira Firdowse , Aastik Solanki , Ganesh Ramakrishnan , Kshitij S. Jadhav

We consider a real-world scenario in which a newly-established pilot project needs to make inferences for newly-collected data with the help of other parties under privacy protection policies. Current federated learning (FL) paradigms are…

机器学习 · 计算机科学 2023-05-09 Xin-Chun Li , Yang Yang , De-Chuan Zhan

In the last years, Federated learning (FL) has become a popular solution to train machine learning models in domains with high privacy concerns. However, FL scalability and performance face significant challenges in real-world deployments…

机器学习 · 计算机科学 2026-03-11 Davide Domini , Gianluca Aguzzi , Lukas Esterle , Mirko Viroli

In heterogeneous scenarios where the data distribution amongst the Federated Learning (FL) participants is Non-Independent and Identically distributed (Non-IID), FL suffers from the well known problem of data heterogeneity. This leads the…

机器学习 · 计算机科学 2024-07-09 Fatima Abacha , Sin G. Teo , Lucas C. Cordeiro , Mustafa A. Mustafa