Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data
The increasing requirements for data protection and privacy have attracted a huge research interest on distributed artificial intelligence and specifically on federated learning, an emerging machine learning approach that allows the construction of a model between several participants who hold their...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023041324 |
| _version_ | 1797809113680314368 |
|---|---|
| author | Jose L. Salmeron Irina Arévalo Antonio Ruiz-Celma |
| author_facet | Jose L. Salmeron Irina Arévalo Antonio Ruiz-Celma |
| author_sort | Jose L. Salmeron |
| collection | DOAJ |
| description | The increasing requirements for data protection and privacy have attracted a huge research interest on distributed artificial intelligence and specifically on federated learning, an emerging machine learning approach that allows the construction of a model between several participants who hold their own private data. In the initial proposal of federated learning the architecture was centralised and the aggregation was done with federated averaging, meaning that a central server will orchestrate the federation using the most straightforward averaging strategy. This research is focused on testing different federated strategies in a peer-to-peer environment. The authors propose various aggregation strategies for federated learning, including weighted averaging aggregation, using different factors and strategies based on participant contribution. The strategies are tested with varying data sizes to identify the most robust ones. This research tests the strategies with several biomedical datasets and the results of the experiments show that the accuracy-based weighted average outperforms the classical federated averaging method. |
| first_indexed | 2024-03-13T06:48:48Z |
| format | Article |
| id | doaj.art-c9101e5cd63f45bab101f8692dd3e32b |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-13T06:48:48Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-c9101e5cd63f45bab101f8692dd3e32b2023-06-08T04:19:36ZengElsevierHeliyon2405-84402023-06-0196e16925Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical dataJose L. Salmeron0Irina Arévalo1Antonio Ruiz-Celma2CUNEF Universidad, Madrid, Spain; Universidad Autónoma de Chile, ChileUniversidad Pablo de Olavide, Seville, Spain; Corresponding author.Universidad de Extremadura, Badajoz, SpainThe increasing requirements for data protection and privacy have attracted a huge research interest on distributed artificial intelligence and specifically on federated learning, an emerging machine learning approach that allows the construction of a model between several participants who hold their own private data. In the initial proposal of federated learning the architecture was centralised and the aggregation was done with federated averaging, meaning that a central server will orchestrate the federation using the most straightforward averaging strategy. This research is focused on testing different federated strategies in a peer-to-peer environment. The authors propose various aggregation strategies for federated learning, including weighted averaging aggregation, using different factors and strategies based on participant contribution. The strategies are tested with varying data sizes to identify the most robust ones. This research tests the strategies with several biomedical datasets and the results of the experiments show that the accuracy-based weighted average outperforms the classical federated averaging method.http://www.sciencedirect.com/science/article/pii/S2405844023041324Federated learningPrivacy-preserving machine learning |
| spellingShingle | Jose L. Salmeron Irina Arévalo Antonio Ruiz-Celma Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data Heliyon Federated learning Privacy-preserving machine learning |
| title | Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data |
| title_full | Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data |
| title_fullStr | Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data |
| title_full_unstemmed | Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data |
| title_short | Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data |
| title_sort | benchmarking federated strategies in peer to peer federated learning for biomedical data |
| topic | Federated learning Privacy-preserving machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023041324 |
| work_keys_str_mv | AT joselsalmeron benchmarkingfederatedstrategiesinpeertopeerfederatedlearningforbiomedicaldata AT irinaarevalo benchmarkingfederatedstrategiesinpeertopeerfederatedlearningforbiomedicaldata AT antonioruizcelma benchmarkingfederatedstrategiesinpeertopeerfederatedlearningforbiomedicaldata |