paper-with-me

홈 › Papers

Heterogeneous Federated Learning: State-of-the-art and Research Challenges

2023-07-20 · Mang Ye, Xiuwen Fang, Bo Du, Pong C. Yuen, DaCheng Tao

Federated learning (FL) has drawn increasing attention owing to its potential use in large-scale industrial applications. Existing federated learning works mainly focus on model homogeneous settings. However, practical federated learning typically faces the heterogeneity of data distributions, model architectures, network environments, and hardware devices among participant clients. Heterogeneous Federated Learning (HFL) is much more challenging, and corresponding solutions are diverse and complex. Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential. In this survey, we firstly summarize the various research challenges in HFL from five aspects: statistical heterogeneity, model heterogeneity, communication heterogeneity, device heterogeneity, and additional challenges. In addition, recent advances in HFL are reviewed and a new taxonomy of existing HFL methods is proposed with an in-depth analysis of their pros and cons. We classify existing methods from three different levels according to the HFL procedure: data-level, model-level, and server-level. Finally, several critical and promising future research directions in HFL are discussed, which may facilitate further developments in this field. A periodically updated collection on HFL is available at https://github.com/marswhu/HFL_Survey.

📄 PDF Abstract BibTeX arXiv:2307.10616

Code (2)

marswhu/hfl_survey 공식 구현
wenkehuang/marsfl pytorch

Tasks

Federated LearningSurvey

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Advances in Robust Federated Learning: Heterogeneity Considerations

2024-05-16 · Chuan Chen, Tianchi Liao, Xiaojun Deng, Zihou Wu 외

In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and collaboratively train models across multiple clients with different data distributions, model structures, task objectives, co…

DiversityFederated LearningPrivacy Preserving

Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Setting

2021-09-15 · Wei Zhu, Jiebo Luo, Andrew White

Chemistry research has both high material and computational costs to conduct experiments. Institutions thus consider chemical data to be valuable and there have been few efforts to construct large public datasets for mac…

Federated Learning

Federated Large Language Models: Current Progress and Future Directions

2024-09-24 · Yuhang Yao, Jianyi Zhang, Junda Wu, Chengkai Huang 외

Large language models are rapidly gaining popularity and have been widely adopted in real-world applications. While the quality of training data is essential, privacy concerns arise during data collection. Federated lear…

Federated LearningPrompt Learning

Universal EHR Federated Learning Framework

2022-11-14 · Junu Kim, Kyunghoon Hur, Seongjun Yang, Edward Choi

Federated learning (FL) is the most practical multi-source learning method for electronic healthcare records (EHR). Despite its guarantee of privacy protection, the wide application of FL is restricted by two large chall…

Federated Learning

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

2021-06-10 · CVPR 2022 1 · Liangqiong Qu, Yuyin Zhou, Paul Pu Liang, Yingda Xia 외

Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there …

Federated Learning