International revenue share fraud prediction on the 5G edge using federated learning
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/1822/87093 |
Resumo: | Edge computing and multi-access edge computing (MEC) are two recent paradigms of distributed computing that are growing due to the rise of the fifth-generation (5G) of broadband cellular networks. The development of edge computing and MEC architectures involves the hosting of applications close to the end-users, allowing: an improved privacy, given that critical data is not shared with other systems; a reduced communication latency; an improved application speed; and a more efficient energy use. However, many applications are challenged by edge computing and MEC. In the case of machine learning (ML) applications, there can be privacy rules that do not allow data to be shared among distinct edges. Additionally, the devices used to train ML models might present lower computational capabilities than traditional computers. In this work, we present a Federated ML architecture that uses decentralized data and light ML training techniques to fit ML models on the 5G Edge. Our system consists of edge nodes that train models using local data and a centralized node that aggregates the results. As a case study, an international revenue share fraud task is addressed by considering two real-world datasets obtained from a commercial provider of Telecom analytics solutions. We test our architecture using two iterations of a Federated ML method, then compare it with a centralized ML model that is currently adopted by the provider. The results show that the Federated Learning decentralized approach produces an excellent level of class discrimination and that the main models maintain the performance across two rounds of decentralized training and even surpass the existing centralized model. After validating the results with the Telecom provider, we have built a prototype technological architecture that can be deployed in a real-world MEC scenario. |
id |
RCAP_45bcc38a41ebc82f7e12445908672a2b |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/87093 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
International revenue share fraud prediction on the 5G edge using federated learning5G networksEdge computingFederated learningMachine learningMulti-access edge computingCiências Naturais::Ciências da Computação e da InformaçãoScience & TechnologyEdge computing and multi-access edge computing (MEC) are two recent paradigms of distributed computing that are growing due to the rise of the fifth-generation (5G) of broadband cellular networks. The development of edge computing and MEC architectures involves the hosting of applications close to the end-users, allowing: an improved privacy, given that critical data is not shared with other systems; a reduced communication latency; an improved application speed; and a more efficient energy use. However, many applications are challenged by edge computing and MEC. In the case of machine learning (ML) applications, there can be privacy rules that do not allow data to be shared among distinct edges. Additionally, the devices used to train ML models might present lower computational capabilities than traditional computers. In this work, we present a Federated ML architecture that uses decentralized data and light ML training techniques to fit ML models on the 5G Edge. Our system consists of edge nodes that train models using local data and a centralized node that aggregates the results. As a case study, an international revenue share fraud task is addressed by considering two real-world datasets obtained from a commercial provider of Telecom analytics solutions. We test our architecture using two iterations of a Federated ML method, then compare it with a centralized ML model that is currently adopted by the provider. The results show that the Federated Learning decentralized approach produces an excellent level of class discrimination and that the main models maintain the performance across two rounds of decentralized training and even surpass the existing centralized model. After validating the results with the Telecom provider, we have built a prototype technological architecture that can be deployed in a real-world MEC scenario.This work was executed under the project Opti-Edge: 5G Digital Services Optimization at the Edge, Individual Project, NUP: POCI-01-0247-FEDER-045220, co-funded by the Incentive System for Research and Technological Development, from the Thematic Operational Program Competitiveness of the national framework program - Portugal2020. We wish to thank the anonymous reviewers for their helpful comments.SpringerUniversidade do MinhoFerreira, Luís Fernando FariaSilva, LeopoldoMorais, FranciscoMartins, Carlos ManuelPires, Pedro MiguelRodrigues, HelenaCortez, PauloPilastri, Andre20232023-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/87093engFerreira, L., Silva, L., Morais, F., Martins, C. M., Pires, P. M., Rodrigues, H., … Pilastri, A. (2023, March 31). International revenue share fraud prediction on the 5G edge using federated learning. Computing. Springer Science and Business Media LLC. http://doi.org/10.1007/s00607-023-01174-w0010-485X1436-505710.1007/s00607-023-01174-whttps://link.springer.com/article/10.1007/s00607-023-01174-winfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-10-28T01:19:46Zoai:repositorium.sdum.uminho.pt:1822/87093Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:26:00.880064Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
International revenue share fraud prediction on the 5G edge using federated learning |
title |
International revenue share fraud prediction on the 5G edge using federated learning |
spellingShingle |
International revenue share fraud prediction on the 5G edge using federated learning Ferreira, Luís Fernando Faria 5G networks Edge computing Federated learning Machine learning Multi-access edge computing Ciências Naturais::Ciências da Computação e da Informação Science & Technology |
title_short |
International revenue share fraud prediction on the 5G edge using federated learning |
title_full |
International revenue share fraud prediction on the 5G edge using federated learning |
title_fullStr |
International revenue share fraud prediction on the 5G edge using federated learning |
title_full_unstemmed |
International revenue share fraud prediction on the 5G edge using federated learning |
title_sort |
International revenue share fraud prediction on the 5G edge using federated learning |
author |
Ferreira, Luís Fernando Faria |
author_facet |
Ferreira, Luís Fernando Faria Silva, Leopoldo Morais, Francisco Martins, Carlos Manuel Pires, Pedro Miguel Rodrigues, Helena Cortez, Paulo Pilastri, Andre |
author_role |
author |
author2 |
Silva, Leopoldo Morais, Francisco Martins, Carlos Manuel Pires, Pedro Miguel Rodrigues, Helena Cortez, Paulo Pilastri, Andre |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Ferreira, Luís Fernando Faria Silva, Leopoldo Morais, Francisco Martins, Carlos Manuel Pires, Pedro Miguel Rodrigues, Helena Cortez, Paulo Pilastri, Andre |
dc.subject.por.fl_str_mv |
5G networks Edge computing Federated learning Machine learning Multi-access edge computing Ciências Naturais::Ciências da Computação e da Informação Science & Technology |
topic |
5G networks Edge computing Federated learning Machine learning Multi-access edge computing Ciências Naturais::Ciências da Computação e da Informação Science & Technology |
description |
Edge computing and multi-access edge computing (MEC) are two recent paradigms of distributed computing that are growing due to the rise of the fifth-generation (5G) of broadband cellular networks. The development of edge computing and MEC architectures involves the hosting of applications close to the end-users, allowing: an improved privacy, given that critical data is not shared with other systems; a reduced communication latency; an improved application speed; and a more efficient energy use. However, many applications are challenged by edge computing and MEC. In the case of machine learning (ML) applications, there can be privacy rules that do not allow data to be shared among distinct edges. Additionally, the devices used to train ML models might present lower computational capabilities than traditional computers. In this work, we present a Federated ML architecture that uses decentralized data and light ML training techniques to fit ML models on the 5G Edge. Our system consists of edge nodes that train models using local data and a centralized node that aggregates the results. As a case study, an international revenue share fraud task is addressed by considering two real-world datasets obtained from a commercial provider of Telecom analytics solutions. We test our architecture using two iterations of a Federated ML method, then compare it with a centralized ML model that is currently adopted by the provider. The results show that the Federated Learning decentralized approach produces an excellent level of class discrimination and that the main models maintain the performance across two rounds of decentralized training and even surpass the existing centralized model. After validating the results with the Telecom provider, we have built a prototype technological architecture that can be deployed in a real-world MEC scenario. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023 2023-01-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/1822/87093 |
url |
https://hdl.handle.net/1822/87093 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Ferreira, L., Silva, L., Morais, F., Martins, C. M., Pires, P. M., Rodrigues, H., … Pilastri, A. (2023, March 31). International revenue share fraud prediction on the 5G edge using federated learning. Computing. Springer Science and Business Media LLC. http://doi.org/10.1007/s00607-023-01174-w 0010-485X 1436-5057 10.1007/s00607-023-01174-w https://link.springer.com/article/10.1007/s00607-023-01174-w |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Springer |
publisher.none.fl_str_mv |
Springer |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134141791338496 |