中文
相关论文

相关论文: Initialization Matters: Unraveling the Impact of P…

200 篇论文

An oft-cited challenge of federated learning is the presence of heterogeneity. \emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \emph{System heterogeneity} refers to the…

机器学习 · 计算机科学 2022-10-18 John Nguyen , Jianyu Wang , Kshitiz Malik , Maziar Sanjabi , Michael Rabbat

An oft-cited challenge of federated learning is the presence of heterogeneity. \emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \emph{System heterogeneity} refers to…

机器学习 · 计算机科学 2023-03-28 John Nguyen , Jianyu Wang , Kshitiz Malik , Maziar Sanjabi , Michael Rabbat

Pre-training is prevalent in nowadays deep learning to improve the learned model's performance. However, in the literature on federated learning (FL), neural networks are mostly initialized with random weights. These attract our interest in…

机器学习 · 计算机科学 2023-03-24 Hong-You Chen , Cheng-Hao Tu , Ziwei Li , Han-Wei Shen , Wei-Lun Chao

Advancement in the field of machine learning is unavoidable, but something of major concern is preserving the privacy of the users whose data is being used for training these machine learning algorithms. Federated learning(FL) has emerged…

机器学习 · 计算机科学 2023-11-07 Ishmeet Kaur , Adwaita Janardhan Jadhav

Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a number of participants without sharing data. Recent works have begun to consider the effects of using pre-trained models as an initialization point…

机器学习 · 计算机科学 2023-11-07 Gwen Legate , Nicolas Bernier , Lucas Caccia , Edouard Oyallon , Eugene Belilovsky

Federated learning (FL) refers to the learning paradigm that trains machine learning models directly in the decentralized systems consisting of smart edge devices without transmitting the raw data, which avoids the heavy communication costs…

机器学习 · 计算机科学 2020-12-17 Xin Yao , Lifeng Sun

Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the training data localised on each node. This approach avoids…

机器学习 · 计算机科学 2025-05-23 Arash Badie-Modiri , Chiara Boldrini , Lorenzo Valerio , János Kertész , Márton Karsai

Federated Learning (FL) is a privacy-protected machine learning paradigm that allows model to be trained directly at the edge without uploading data. One of the biggest challenges faced by FL in practical applications is the heterogeneity…

机器学习 · 计算机科学 2021-08-20 Zirui Zhu , Ziyi Ye

Federated Learning (FL) enables large-scale distributed training of machine learning models, while still allowing individual nodes to maintain data locally. However, executing FL at scale comes with inherent practical challenges: 1)…

机器学习 · 计算机科学 2025-05-23 Hossein Zakerinia , Shayan Talaei , Giorgi Nadiradze , Dan Alistarh

Federated learning (FL) is a distributed paradigm that coordinates massive local clients to collaboratively train a global model via stage-wise local training processes on the heterogeneous dataset. Previous works have implicitly studied…

机器学习 · 计算机科学 2026-04-15 Li Shen , Yan Sun , Dacheng Tao

Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data heterogeneity, which can result in performance degradation. In…

机器学习 · 计算机科学 2023-11-23 Seongyoon Kim , Gihun Lee , Jaehoon Oh , Se-Young Yun

Federated learning (FL) is an emerging paradigm in machine learning, where a shared model is collaboratively learned using data from multiple devices to mitigate the risk of data leakage. While recent studies posit that Vision Transformer…

计算机视觉与模式识别 · 计算机科学 2023-10-09 Peiran Xu , Zeyu Wang , Jieru Mei , Liangqiong Qu , Alan Yuille , Cihang Xie , Yuyin Zhou

Federated learning (FL) trains a shared model from updates contributed by distributed clients, often implicitly assuming that contributing clients are representative of the target population. In practice, this representativeness assumption…

机器学习 · 计算机科学 2026-04-30 Gota Morishita

Federated learning (FL) enables decentralized clients to train a model collaboratively without sharing local data. A key distinction between FL and centralized learning is that clients' data are non-independent and identically distributed,…

机器学习 · 计算机科学 2025-08-19 Like Jian , Dong Liu

Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nature, making…

机器学习 · 计算机科学 2022-04-15 Matias Mendieta , Taojiannan Yang , Pu Wang , Minwoo Lee , Zhengming Ding , Chen Chen

Meta federated learning (FL) is a personalized variant of FL, where multiple agents collaborate on training an initial shared model without exchanging raw data samples. The initial model should be trained in a way that current or new agents…

机器学习 · 计算机科学 2025-05-14 Mohammad Vahid Jamali , Hamid Saber , Jung Hyun Bae

Federated Learning (FL) is a distributed machine learning strategy, developed for settings where training data is owned by distributed devices and cannot be shared. FL circumvents this constraint by carrying out model training in…

机器学习 · 计算机科学 2025-01-24 Maria Hartmann , Grégoire Danoy , Pascal Bouvry

As methods to create discrimination-aware models develop, they focus on centralized ML, leaving federated learning (FL) unexplored. FL is a rising approach for collaborative ML, in which an aggregator orchestrates multiple parties to train…

机器学习 · 计算机科学 2020-12-07 Annie Abay , Yi Zhou , Nathalie Baracaldo , Shashank Rajamoni , Ebube Chuba , Heiko Ludwig

With an increasing number of smart devices like internet of things (IoT) devices deployed in the field, offloadingtraining of neural networks (NNs) to a central server becomes more and more infeasible. Recent efforts toimprove users'…

机器学习 · 计算机科学 2023-07-19 Kilian Pfeiffer , Martin Rapp , Ramin Khalili , Jörg Henkel

Federated learning (FL) enables distributed training while preserving data privacy, but stragglers-slow or incapable clients-can significantly slow down the total training time and degrade performance. To mitigate the impact of stragglers,…

机器学习 · 计算机科学 2024-09-11 Honggu Kang , Seohyeon Cha , Jinwoo Shin , Jongmyeong Lee , Joonhyuk Kang
‹ 上一页 1 2 3 10 下一页 ›