Home > Research > Publications & Outputs > Federated learning with adaptive local aggregat...

Research

Associated organisational unit

Electronic data

Links

Text available via DOI:

View graph of relations

Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles

Research output: Contribution to Journal/Magazine › Journal article › peer-review

E-pub ahead of print

Standard

Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles. / Cheng, Yong; Hu, Yuhao; Liu, Wei et al.
In: Information Sciences, Vol. 710, 122100, 31.08.2025.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Cheng, Y, Hu, Y, Liu, W & Bilal, M 2025, 'Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles', Information Sciences, vol. 710, 122100. https://doi.org/10.1016/j.ins.2025.122100

APA

Cheng, Y., Hu, Y., Liu, W., & Bilal, M. (2025). Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles. Information Sciences, 710, Article 122100. Advance online publication. https://doi.org/10.1016/j.ins.2025.122100

Vancouver

Cheng Y, Hu Y, Liu W, Bilal M. Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles. Information Sciences. 2025 Aug 31;710:122100. Epub 2025 Mar 20. doi: 10.1016/j.ins.2025.122100

Author

Cheng, Yong ; Hu, Yuhao ; Liu, Wei et al. / Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles. In: Information Sciences. 2025 ; Vol. 710.

Bibtex

@article{744eb6b5e0d641bebf40d766d1c9f90e,
title = "Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles",
abstract = "Deep learning (DL) models have great potential to be used for recommender systems (RS) in the Internet of Vehicles (IoV) due to their excellent data processing and learning abilities. To alleviate the problem of privacy leakage in centralized training of DL models, federated learning (FL) is engaged for its advantage of just uploading gradients or parameters of models without raw data sharing. However, the ubiquitous data heterogeneity in IoV brings a big challenge to the stable global convergence of FL. In addition, existing FL schemes with high convergence latency cannot realize the timely personalized content recommendation in IoV. In this paper, a FL scheme with adaptive local aggregation for privacy-aware RS in IoV, named FLRS, is proposed. At first, we analyze the data distribution on each vehicle locally from two aspects: label distribution and feature distribution. After receiving vehicle data distribution information, the edge server selects aggregation collaborators for each vehicle according to the distribution similarity of labels and features. In the model updating stage, the local model on each vehicle is adaptively aggregated with those from its collaborators and then the local training process begins. At last, the performance of FLRS is evaluated through simulation experiments.",
author = "Yong Cheng and Yuhao Hu and Wei Liu and Muhammad Bilal",
year = "2025",
month = mar,
day = "20",
doi = "10.1016/j.ins.2025.122100",
language = "English",
volume = "710",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

RIS

TY - JOUR

T1 - Federated learning with adaptive local aggregation for privacy-aware recommender systems in Internet of Vehicles

AU - Cheng, Yong

AU - Hu, Yuhao

AU - Liu, Wei

AU - Bilal, Muhammad

PY - 2025/3/20

Y1 - 2025/3/20

N2 - Deep learning (DL) models have great potential to be used for recommender systems (RS) in the Internet of Vehicles (IoV) due to their excellent data processing and learning abilities. To alleviate the problem of privacy leakage in centralized training of DL models, federated learning (FL) is engaged for its advantage of just uploading gradients or parameters of models without raw data sharing. However, the ubiquitous data heterogeneity in IoV brings a big challenge to the stable global convergence of FL. In addition, existing FL schemes with high convergence latency cannot realize the timely personalized content recommendation in IoV. In this paper, a FL scheme with adaptive local aggregation for privacy-aware RS in IoV, named FLRS, is proposed. At first, we analyze the data distribution on each vehicle locally from two aspects: label distribution and feature distribution. After receiving vehicle data distribution information, the edge server selects aggregation collaborators for each vehicle according to the distribution similarity of labels and features. In the model updating stage, the local model on each vehicle is adaptively aggregated with those from its collaborators and then the local training process begins. At last, the performance of FLRS is evaluated through simulation experiments.

AB - Deep learning (DL) models have great potential to be used for recommender systems (RS) in the Internet of Vehicles (IoV) due to their excellent data processing and learning abilities. To alleviate the problem of privacy leakage in centralized training of DL models, federated learning (FL) is engaged for its advantage of just uploading gradients or parameters of models without raw data sharing. However, the ubiquitous data heterogeneity in IoV brings a big challenge to the stable global convergence of FL. In addition, existing FL schemes with high convergence latency cannot realize the timely personalized content recommendation in IoV. In this paper, a FL scheme with adaptive local aggregation for privacy-aware RS in IoV, named FLRS, is proposed. At first, we analyze the data distribution on each vehicle locally from two aspects: label distribution and feature distribution. After receiving vehicle data distribution information, the edge server selects aggregation collaborators for each vehicle according to the distribution similarity of labels and features. In the model updating stage, the local model on each vehicle is adaptively aggregated with those from its collaborators and then the local training process begins. At last, the performance of FLRS is evaluated through simulation experiments.

U2 - 10.1016/j.ins.2025.122100

DO - 10.1016/j.ins.2025.122100

M3 - Journal article

VL - 710

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

M1 - 122100

ER -