Cargando…
New Generation Federated Learning
With the development of the Internet of things (IoT), federated learning (FL) has received increasing attention as a distributed machine learning (ML) framework that does not require data exchange. However, current FL frameworks follow an idealized setup in which the task size is fixed and the stora...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9654996/ https://www.ncbi.nlm.nih.gov/pubmed/36366172 http://dx.doi.org/10.3390/s22218475 |
_version_ | 1784829076275462144 |
---|---|
author | Li, Boyuan Chen, Shengbo Peng, Zihao |
author_facet | Li, Boyuan Chen, Shengbo Peng, Zihao |
author_sort | Li, Boyuan |
collection | PubMed |
description | With the development of the Internet of things (IoT), federated learning (FL) has received increasing attention as a distributed machine learning (ML) framework that does not require data exchange. However, current FL frameworks follow an idealized setup in which the task size is fixed and the storage space is unlimited, which is impossible in the real world. In fact, new classes of these participating clients always emerge over time, and some samples are overwritten or discarded due to storage limitations. We urgently need a new framework to adapt to the dynamic task sequences and strict storage constraints in the real world. Continuous learning or incremental learning is the ultimate goal of deep learning, and we introduce incremental learning into FL to describe a new federated learning framework. New generation federated learning (NGFL) is probably the most desirable framework for FL, in which, in addition to the basic task of training the server, each client needs to learn its private tasks, which arrive continuously independent of communication with the server. We give a rigorous mathematical representation of this framework, detail several major challenges faced under this framework, and address the main challenges of combining incremental learning with federated learning (aggregation of heterogeneous output layers and the task transformation mutual knowledge problem), and show the lower and upper baselines of the framework. |
format | Online Article Text |
id | pubmed-9654996 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96549962022-11-15 New Generation Federated Learning Li, Boyuan Chen, Shengbo Peng, Zihao Sensors (Basel) Article With the development of the Internet of things (IoT), federated learning (FL) has received increasing attention as a distributed machine learning (ML) framework that does not require data exchange. However, current FL frameworks follow an idealized setup in which the task size is fixed and the storage space is unlimited, which is impossible in the real world. In fact, new classes of these participating clients always emerge over time, and some samples are overwritten or discarded due to storage limitations. We urgently need a new framework to adapt to the dynamic task sequences and strict storage constraints in the real world. Continuous learning or incremental learning is the ultimate goal of deep learning, and we introduce incremental learning into FL to describe a new federated learning framework. New generation federated learning (NGFL) is probably the most desirable framework for FL, in which, in addition to the basic task of training the server, each client needs to learn its private tasks, which arrive continuously independent of communication with the server. We give a rigorous mathematical representation of this framework, detail several major challenges faced under this framework, and address the main challenges of combining incremental learning with federated learning (aggregation of heterogeneous output layers and the task transformation mutual knowledge problem), and show the lower and upper baselines of the framework. MDPI 2022-11-03 /pmc/articles/PMC9654996/ /pubmed/36366172 http://dx.doi.org/10.3390/s22218475 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Li, Boyuan Chen, Shengbo Peng, Zihao New Generation Federated Learning |
title | New Generation Federated Learning |
title_full | New Generation Federated Learning |
title_fullStr | New Generation Federated Learning |
title_full_unstemmed | New Generation Federated Learning |
title_short | New Generation Federated Learning |
title_sort | new generation federated learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9654996/ https://www.ncbi.nlm.nih.gov/pubmed/36366172 http://dx.doi.org/10.3390/s22218475 |
work_keys_str_mv | AT liboyuan newgenerationfederatedlearning AT chenshengbo newgenerationfederatedlearning AT pengzihao newgenerationfederatedlearning |