中文
相关论文

相关论文: Cumulative Utility Parity for Fair Federated Learn…

200 篇论文

Federated Learning (FL) is an emerging paradigm in machine learning without exposing clients' raw data. In practical scenarios with numerous clients, encouraging fair and efficient client participation in federated learning is of utmost…

机器学习 · 计算机科学 2024-01-30 Simin Javaherian , Sanjeev Panta , Shelby Williams , Md Sirajul Islam , Li Chen

Federated Learning (FL) is a decentralized machine learning approach where local models are trained on distributed clients, allowing privacy-preserving collaboration by sharing model updates instead of raw data. However, the added…

分布式、并行与集群计算 · 计算机科学 2023-08-17 Pratik Agrawal , Philipp Wiesner , Odej Kao

Federated Learning (FL) algorithms implicitly assume that clients passively comply with server-side orchestration by sharing local model updates upon server request. However, this overlooks an important aspect in real-world cross-silo…

机器学习 · 计算机科学 2026-05-19 M Yashwanth , Arunabh Singh , Ashok Nayak , Sai Kiran Bulusu , Anirban Chakraborty

Federated Learning (FL) is a decentralized machine learning framework that enables collaborative model training while respecting data privacy. In various applications, non-uniform availability or participation of users is unavoidable due to…

机器学习 · 计算机科学 2023-09-26 Periklis Theodoropoulos , Konstantinos E. Nikolakakis , Dionysis Kalogerias

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minmax group fairness in paradigms where different participating entities may only…

机器学习 · 计算机科学 2021-10-08 Afroditi Papadaki , Natalia Martinez , Martin Bertran , Guillermo Sapiro , Miguel Rodrigues

Federated learning (FL) enables multiple data owners (a.k.a. FL clients) to collaboratively train machine learning models without disclosing sensitive private data. Existing FL research mostly focuses on the monopoly scenario in which a…

机器学习 · 计算机科学 2024-02-09 Yuxin Shi , Han Yu

Federated Learning (FL) enables collaborative training while preserving privacy, yet it introduces a critical challenge: the "illusion of fairness''. A global model, usually evaluated on the server, appears fair on average while keeping…

机器学习 · 计算机科学 2026-05-12 Xenia Heilmann , Luca Corbucci , Mattia Cerrato , Anna Monreale

Federated Learning (FL) enables data owners to train a shared global model without sharing their private data. Unfortunately, FL is susceptible to an intrinsic fairness issue: due to heterogeneity in clients' data distributions, the final…

机器学习 · 计算机科学 2022-08-18 Hamid Mozaffari , Amir Houmansadr

With the emerging application of Federated Learning (FL) in finance, hiring and healthcare, FL models are regulated to be fair, preventing disparities with respect to legally protected attributes such as race or gender. Two concepts of…

机器学习 · 计算机科学 2025-04-02 Yuying Duan , Gelei Xu , Yiyu Shi , Michael Lemmon

Federated learning involves training statistical models over remote devices such as mobile phones while keeping data localized. Training in heterogeneous and potentially massive networks introduces opportunities for privacy-preserving data…

机器学习 · 计算机科学 2022-01-21 Afra Mashhadi , Alex Kyllo , Reza M. Parizi

Federated learning is a prominent distributed learning paradigm that incorporates collaboration among diverse clients, promotes data locality, and thus ensures privacy. These clients have their own technological, cultural, and other biases…

机器学习 · 计算机科学 2024-11-04 Antesh Upadhyay , Abolfazl Hashemi

Federated Learning (FL) enables collaborative model training across distributed devices while preserving data privacy. Nonetheless, the heterogeneity of edge devices often leads to inconsistent performance of the globally trained models,…

机器学习 · 计算机科学 2025-05-13 Lin Wang , Zhichao Wang , Ye Shi , Sai Praneeth Karimireddy , Xiaoying Tang

Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. However, heterogeneous data distributions over different…

机器学习 · 计算机科学 2022-05-27 Yaqi Sun , Shijing Si , Jianzong Wang , Yuhan Dong , Zhitao Zhu , Jing Xiao

Federated learning (FL) is a distributed learning technique that trains a shared model over distributed data in a privacy-preserving manner. Unfortunately, FL's performance degrades when there is (i) variability in client characteristics in…

机器学习 · 计算机科学 2021-10-28 Muhammad Tahir Munir , Muhammad Mustansar Saeed , Mahad Ali , Zafar Ayyub Qazi , Ihsan Ayyub Qazi

Federated learning (FL) has enabled multiple data owners (a.k.a. FL clients) to train machine learning models collaboratively without revealing private data. Since the FL server can only engage a limited number of clients in each training…

机器学习 · 计算机科学 2023-07-21 Yuxin Shi , Zelei Liu , Zhuan Shi , Han Yu

Federated Learning enables collaborative model training across decentralized data sources without data transfer. Averaging-based FL is limited by the presence of non-IID data, which negatively impacts convergence speed and final model…

机器学习 · 计算机科学 2026-05-22 Adda Akram Bendoukha , Heber Hwang Arcolezi , Nesrine Kaaniche , Aymen Boudguiga

Federated Learning (FL) enables multiple clients to train machine learning models collaboratively without sharing the raw training data. However, for a given FL task, how to select a group of appropriate clients fairly becomes a challenging…

分布式、并行与集群计算 · 计算机科学 2023-12-27 Meiying Zhang , Huan Zhao , Sheldon Ebron , Ruitao Xie , Kan Yang

Federated Learning (FL) has gained significant attention as it facilitates collaborative machine learning among multiple clients without centralizing their data on a server. FL ensures the privacy of participating clients by locally storing…

机器学习 · 计算机科学 2025-01-07 Huiqiang Chen , Tianqing Zhu , Wanlei Zhou , Wei Zhao

Federated Learning is an emerging distributed collaborative learning paradigm used by many of applications nowadays. The effectiveness of federated learning relies on clients' collective efforts and their willingness to contribute local…

计算机科学与博弈论 · 计算机科学 2022-05-24 Shuyu Kong , You Li , Hai Zhou

Federated Learning (FL) is a novel privacy-protection distributed machine learning paradigm that guarantees user privacy and prevents the risk of data leakage due to the advantage of the client's local training. Researchers have struggled…

机器学习 · 计算机科学 2023-12-01 Kangkang Sun , Xiaojin Zhang , Xi Lin , Gaolei Li , Jing Wang , Jianhua Li