中文
相关论文

相关论文: Why Federated Optimization Fails to Achieve Perfec…

200 篇论文

Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private. With an increasing scale of clients and models, FL encounters two key challenges, client drift due…

机器学习 · 计算机科学 2025-01-20 Jianhui Sun , Xidong Wu , Heng Huang , Aidong Zhang

Minimax optimization has seen a surge in interest with the advent of modern applications such as GANs, and it is inherently more challenging than simple minimization. The difficulty is exacerbated by the training data residing at multiple…

机器学习 · 计算机科学 2023-02-10 Pranay Sharma , Rohan Panda , Gauri Joshi

Federated learning (FL) is a distributed machine learning paradigm where multiple clients conduct local training based on their private data, then the updated models are sent to a central server for global aggregation. The practical…

机器学习 · 计算机科学 2025-04-03 Harsh Vardhan , Xiaofan Yu , Tajana Rosing , Arya Mazumdar

Federated learning is a distributed machine learning paradigm in which a large number of clients coordinate with a central server to learn a model without sharing their own training data. Standard federated optimization methods such as…

Federated learning (FL) is an appealing paradigm that allows a group of machines (a.k.a. clients) to learn collectively while keeping their data local. However, due to the heterogeneity between the clients' data distributions, the model…

机器学习 · 计算机科学 2024-10-01 Youssef Allouah , Abdellah El Mrini , Rachid Guerraoui , Nirupam Gupta , Rafael Pinot

Federated learning enables the clients to collaboratively train a global model, which is aggregated from local models. Due to the heterogeneous data distributions over clients and data privacy in federated learning, it is difficult to train…

机器学习 · 计算机科学 2025-05-20 Wujun Zhou , Shu Ding , ZeLin Li , Wei Wang

Distributed learning algorithms aim to leverage distributed and diverse data stored at users' devices to learn a global phenomena by performing training amongst participating devices and periodically aggregating their local models'…

机器学习 · 计算机科学 2021-02-04 Naram Mhaisen , Alaa Awad , Amr Mohamed , Aiman Erbad , Mohsen Guizani

We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are distributed (unevenly) over an extremely large number of \nodes, but the goal remains to…

机器学习 · 计算机科学 2015-11-12 Jakub Konečný , Brendan McMahan , Daniel Ramage

Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space. For example, clients may differ in…

机器学习 · 计算机科学 2022-03-08 Yue Tan , Guodong Long , Lu Liu , Tianyi Zhou , Qinghua Lu , Jing Jiang , Chengqi Zhang

Data heterogeneity is a significant challenge in modern federated learning (FL) as it creates variance in local model updates, causing the aggregated global model to shift away from the true global optimum. Partial client participation in…

机器学习 · 计算机科学 2025-12-24 Mrinmay Sen , Subhrajit Nag

Federated learning has evolved to improve a single global model under data heterogeneity (as a curse) or to develop multiple personalized models using data heterogeneity (as a blessing). However, little research has considered both…

机器学习 · 计算机科学 2022-03-17 Jaehoon Oh , Sangmook Kim , Se-Young Yun

The federated learning (FL) framework trains a machine learning model using decentralized data stored at edge client devices by periodically aggregating locally trained models. Popular optimization algorithms of FL use vanilla (stochastic)…

机器学习 · 计算机科学 2021-06-07 Jianyu Wang , Zheng Xu , Zachary Garrett , Zachary Charles , Luyang Liu , Gauri Joshi

Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics and lead to objective inconsistency, where the global model…

机器学习 · 计算机科学 2026-02-24 Shudi Weng , Chao Ren , Ming Xiao , Mikael Skoglund

The heterogeneity of hardware and data is a well-known and studied problem in the community of Federated Learning (FL) as running under heterogeneous settings. Recently, custom-size client models trained with Knowledge Distillation (KD) has…

机器学习 · 计算机科学 2022-11-15 Hongrui Shi , Valentin Radu , Po Yang

Federated Learning (FL) enables mobile edge devices, functioning as clients, to collaboratively train a decentralized model while ensuring local data privacy. However, the efficiency of FL in wireless networks is limited not only by…

分布式、并行与集群计算 · 计算机科学 2026-01-01 Yanbing Yang , Huiling Zhu , Wenchi Cheng , Jingqing Wang , Changrun Chen , Jiangzhou Wang

Federated learning (FL) enables multiple clients to train a model while keeping their data private collaboratively. Previous studies have shown that data heterogeneity between clients leads to drifts across client updates. However, there…

机器学习 · 计算机科学 2023-10-02 Tailin Zhou , Jun Zhang , Danny H. K. Tsang

Federated learning is a distributed machine learning approach where multiple clients collaboratively train a model without sharing their local data, which contributes to preserving privacy. A challenge in federated learning is managing…

机器学习 · 计算机科学 2025-03-04 Rickard Brännvall

Federated Learning (FL) suffers from severe performance degradation due to the data heterogeneity among clients. Existing works reveal that the fundamental reason is that data heterogeneity can cause client drift where the local model…

机器学习 · 计算机科学 2025-01-22 Haoran Xu , Jiaze Li , Wanyi Wu , Hao Ren

The performance of Federated Learning (FL) hinges on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global…

计算机视觉与模式识别 · 计算机科学 2024-05-01 Yuan Wang , Huazhu Fu , Renuga Kanagavelu , Qingsong Wei , Yong Liu , Rick Siow Mong Goh

Federated learning (FL) facilitates collaborative model training among multiple clients while preserving data privacy, often resulting in enhanced performance compared to models trained by individual clients. However, factors such as…

机器学习 · 计算机科学 2025-03-13 Yunjie Fang , Sheng Wu , Tao Yang , Xiaofeng Wu , Bo Hu
‹ 上一页 1 2 3 10 下一页 ›