English
Related papers

Related papers: Federated Learning under Distributed Concept Drift

200 papers

Federated Learning (FL) has emerged as a pivotal framework for the development of effective global models (global FL) or personalized models (personalized FL) across clients with heterogeneous, non-iid data distribution. A key challenge in…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Seongyoon Kim , Minchan Jeong , Sungnyun Kim , Sungwoo Cho , Sumyeong Ahn , Se-Young Yun

Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields…

Machine Learning · Computer Science 2019-10-07 Felix Sattler , Klaus-Robert Müller , Wojciech Samek

Federated Learning (FL) is a privacy-preserving distributed learning approach that is rapidly developing in an era where privacy protection is increasingly valued. It is this rapid development trend, along with the continuous emergence of…

Machine Learning · Computer Science 2024-02-06 Lixu Wang , Yang Zhao , Jiahua Dong , Ating Yin , Qinbin Li , Xiao Wang , Dusit Niyato , Qi Zhu

As privacy concerns continue to grow, federated learning (FL) has gained significant attention as a promising privacy-preserving technology, leading to considerable advancements in recent years. Unlike traditional machine learning, which…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-05 Boyu Fan , Siyang Jiang , Xiang Su , Sasu Tarkoma , Pan Hui

In this paper, we show how the Federated Learning (FL) framework enables learning collectively from distributed data in connected robot teams. This framework typically works with clients collecting data locally, updating neural network…

Robotics · Computer Science 2020-10-20 Nathalie Majcherczyk , Nishan Srishankar , Carlo Pinciroli

Concept drift -- the change of the distribution over time -- poses significant challenges for learning systems and is of central interest for monitoring. Understanding drift is thus paramount, and drift localization -- determining which…

Machine Learning · Computer Science 2026-04-22 Fabian Hinder , Valerie Vaquet , Johannes Brinkrolf , Barbara Hammer

There are situations where data relevant to machine learning problems are distributed across multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons. Machine learning approaches that require data…

Machine Learning · Computer Science 2022-06-28 Dimitris Stripelis , Jose Luis Ambite

Federated Learning (FL) provides decentralised model training, which effectively tackles problems such as distributed data and privacy preservation. However, the generalisation of global models frequently faces challenges from data…

Machine Learning · Computer Science 2025-09-05 Ozgu Goksu , Nicolas Pugeault

Federated learning enables different parties to collaboratively build a global model under the orchestration of a server while keeping the training data on clients' devices. However, performance is affected when clients have heterogeneous…

Machine Learning · Computer Science 2022-06-20 Fabiola Espinoza Castellon , Aurelien Mayoue , Jacques-Henri Sublemontier , Cedric Gouy-Pailler

Federated Learning (FL) enables privacy-preserving multi-source information fusion (MSIF) but is challenged by client drift in highly heterogeneous data settings. Many existing drift-mitigation strategies rely on reference-based…

Machine Learning · Computer Science 2026-02-12 Jungwon Seo , Ferhat Ozgur Catak , Chunming Rong , Kibeom Hong , Minhoe Kim

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…

Machine Learning · Computer Science 2026-04-15 Li Shen , Yan Sun , Dacheng Tao

Federated Learning (FL) has emerged as a solution for distributed systems that allow clients to train models on their data and only share models instead of local data. Generative Models are designed to learn the distribution of a dataset…

Machine Learning · Computer Science 2024-05-28 Ashkan Vedadi Gargary , Emiliano De Cristofaro

Adapting to drifting data streams is a significant challenge in online learning. Concept drift must be detected for effective model adaptation to evolving data properties. Concept drift can impact the data distribution entirely or…

Machine Learning · Computer Science 2023-12-12 Gabriel J. Aguiar , Alberto Cano

Federated learning (FL) enables the collaboration of multiple deep learning models to learn from decentralized data archives (i.e., clients) without accessing data on clients. Although FL offers ample opportunities in knowledge discovery…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Barış Büyüktaş , Gencer Sumbul , Begüm Demir

In recent years, data are typically distributed in multiple organizations while the data security is becoming increasingly important. Federated Learning (FL), which enables multiple parties to collaboratively train a model without…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-03-13 Ji Liu , Xuehai Zhou , Lei Mo , Shilei Ji , Yuan Liao , Zheng Li , Qin Gu , Dejing Dou

Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. In practical FL applications, local data from each data silo reflect local usage patterns. Therefore, there exists heterogeneity of…

Machine Learning · Computer Science 2022-02-01 Shenglai Zeng , Zonghang Li , Hongfang Yu , Yihong He , Zenglin Xu , Dusit Niyato , Han Yu

In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift. We propose a different approach named virtual homogeneity learning (VHL)…

Machine Learning · Computer Science 2022-06-27 Zhenheng Tang , Yonggang Zhang , Shaohuai Shi , Xin He , Bo Han , Xiaowen Chu

Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE…

Signal Processing · Electrical Eng. & Systems 2024-04-24 Bingnan Xiao , Jingjing Zhang , Wei Ni , Xin Wang

Concept drift refers to a non stationary learning problem over time. The training and the application data often mismatch in real life problems. In this report we present a context of concept drift problem 1. We focus on the issues relevant…

Artificial Intelligence · Computer Science 2010-10-25 Indrė Žliobaitė

Federated Learning (FL) has been gaining significant traction across different ML tasks, ranging from vision to keyboard predictions. In large-scale deployments, client heterogeneity is a fact and constitutes a primary problem for fairness,…