Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data
Federated Learning (FL) is a decentralized machine learning (ML) technique that allows a number of participants to train an ML model collaboratively without having to share their private local datasets with others. When participants are unmanned aerial vehicles (UAVs), UAV-enabled FL would experienc...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Vehicular Technology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10360280/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582311256784896 |
|---|---|
| author | Youssra Cheriguene Wael Jaafar Halim Yanikomeroglu Chaker Abdelaziz Kerrache |
| author_facet | Youssra Cheriguene Wael Jaafar Halim Yanikomeroglu Chaker Abdelaziz Kerrache |
| author_sort | Youssra Cheriguene |
| collection | DOAJ |
| description | Federated Learning (FL) is a decentralized machine learning (ML) technique that allows a number of participants to train an ML model collaboratively without having to share their private local datasets with others. When participants are unmanned aerial vehicles (UAVs), UAV-enabled FL would experience heterogeneity due to the majorly skewed (non-independent and identically distributed -IID) collected data. In addition, UAVs may demonstrate unintentional misbehavior in which the latter may fail to send updates to the FL server due, for instance, to UAVs' disconnectivity from the FL system caused by high mobility, unavailability, or battery depletion. Such challenges may significantly affect the convergence of the FL model. A recent way to tackle these challenges is client selection, based on customized criteria that consider UAV computing power and energy consumption. However, most existing client selection schemes neglected the participants' reliability. Indeed, FL can be targeted by poisoning attacks, in which malicious UAVs upload poisonous local models to the FL server, by either providing targeted false predictions for specifically chosen inputs or by compromising the global model's accuracy through tampering with the local model. Hence, we propose in this article a novel client selection scheme that enhances convergence by prioritizing fast UAVs with high-reliability scores, while eliminating malicious UAVs from training. Through experiments, we assess the effectiveness of our scheme in resisting different attack scenarios, in terms of convergence and achieved model accuracy. Finally, we demonstrate the performance superiority of the proposed approach compared to baseline methods. |
| format | Article |
| id | doaj-art-76e8597005c647759e645c6023e4b6d4 |
| institution | Kabale University |
| issn | 2644-1330 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Vehicular Technology |
| spelling | doaj-art-76e8597005c647759e645c6023e4b6d42025-01-30T00:04:22ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302024-01-01512514110.1109/OJVT.2023.334130410360280Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID DataYoussra Cheriguene0https://orcid.org/0000-0003-4506-3067Wael Jaafar1https://orcid.org/0000-0003-4378-9999Halim Yanikomeroglu2https://orcid.org/0000-0003-4776-9354Chaker Abdelaziz Kerrache3https://orcid.org/0000-0001-9990-519XLaboratoire d'Informatique et de Mathématiques, Université Amar Telidji de Laghouat, Laghouat, AlgeriaDepartment of Systems and Computer Engineering, Non-Terrestrial Network (NTN) Lab, Carleton University, Ottawa, ON, CanadaDepartment of Software and Information Technology Engineering, École de Technologie Supérieure, Montreal, QC, CanadaLaboratoire d'Informatique et de Mathématiques, Université Amar Telidji de Laghouat, Laghouat, AlgeriaFederated Learning (FL) is a decentralized machine learning (ML) technique that allows a number of participants to train an ML model collaboratively without having to share their private local datasets with others. When participants are unmanned aerial vehicles (UAVs), UAV-enabled FL would experience heterogeneity due to the majorly skewed (non-independent and identically distributed -IID) collected data. In addition, UAVs may demonstrate unintentional misbehavior in which the latter may fail to send updates to the FL server due, for instance, to UAVs' disconnectivity from the FL system caused by high mobility, unavailability, or battery depletion. Such challenges may significantly affect the convergence of the FL model. A recent way to tackle these challenges is client selection, based on customized criteria that consider UAV computing power and energy consumption. However, most existing client selection schemes neglected the participants' reliability. Indeed, FL can be targeted by poisoning attacks, in which malicious UAVs upload poisonous local models to the FL server, by either providing targeted false predictions for specifically chosen inputs or by compromising the global model's accuracy through tampering with the local model. Hence, we propose in this article a novel client selection scheme that enhances convergence by prioritizing fast UAVs with high-reliability scores, while eliminating malicious UAVs from training. Through experiments, we assess the effectiveness of our scheme in resisting different attack scenarios, in terms of convergence and achieved model accuracy. Finally, we demonstrate the performance superiority of the proposed approach compared to baseline methods.https://ieeexplore.ieee.org/document/10360280/Dropoutsedge computingfederated learningmodel poisoningstragglersUAV |
| spellingShingle | Youssra Cheriguene Wael Jaafar Halim Yanikomeroglu Chaker Abdelaziz Kerrache Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data IEEE Open Journal of Vehicular Technology Dropouts edge computing federated learning model poisoning stragglers UAV |
| title | Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data |
| title_full | Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data |
| title_fullStr | Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data |
| title_full_unstemmed | Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data |
| title_short | Towards Reliable Participation in UAV-Enabled Federated Edge Learning on Non-IID Data |
| title_sort | towards reliable participation in uav enabled federated edge learning on non iid data |
| topic | Dropouts edge computing federated learning model poisoning stragglers UAV |
| url | https://ieeexplore.ieee.org/document/10360280/ |
| work_keys_str_mv | AT youssracheriguene towardsreliableparticipationinuavenabledfederatededgelearningonnoniiddata AT waeljaafar towardsreliableparticipationinuavenabledfederatededgelearningonnoniiddata AT halimyanikomeroglu towardsreliableparticipationinuavenabledfederatededgelearningonnoniiddata AT chakerabdelazizkerrache towardsreliableparticipationinuavenabledfederatededgelearningonnoniiddata |