Journal of Applied Science and Engineering

Published by Tamkang University Press

ESCI jase impact factor scopus logo open access rate of Scopus journal

A Federated Learning-Driven Method for Privacy-Preserving Vocational Learner Profiling and Practical Training Path Recommendation

 2026

 Volume 35

Guo Feng Zhao, Liang Guo

Henan University of Industry Technology, Nanyang, 473000, China

Received: July 21, 2026
Accepted: August 23, 2026
Publication Date: September 16, 2026

上傳圖片

Federated privacy-preserving training process of FL-PTR

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: BibTeX | http://dx.doi.org/10.6180/jase.202612_35.046

Download PDF

In vocational education cloud platforms, online training systems, and school-enterprise collaborative training scenarios, vocational learner behavior data are typically distributed across schools, platforms, and training bases, and centralized profiling and pathrecommendation methods that rely on aggregating raw data risk privacy leakage, data silos, and limited scalability. This study proposes FL-PTR, a federated learning-driven method for privacy-preserving vocational learner profiling and practical training path recommendation, enabling cross-client collaborative profile modeling and personalized path recommendation without uploading raw behavior data. FL-PTR comprises a data acquisition layer, local profiling layer, privacy protection layer, federated collaboration layer, path recommendation layer, and feedback update layer; each client locally encodes behavior sequences and uploads protected updates via gradient pruning, differential privacy noise, and secure aggregation, while the server computes trust-aware aggregation weights from client contribution, stability, anomaly risk, and reputation. In a heavily non-IID scenario, FL-PTR achieves an NDCG@10 of 0.628, a Recall@10 of 0.416, and a Path Completion Rate of 0.743, outperforming FedAvg, FedProx, SCAFFOLD, and DP-FedAvg. With privacy budget ε=4, membership and attribute inference attack success rates fall to 39.6% and 36.7% while recommendation performance is largely preserved, and performance stays stable as clients scale to 200 and under 30% anomalous clients.

Keywords: federated learning, vocational learner profiling, privacy protection, practical training path recommendation, differential privacy

  1. [1] P. Kairouz et al., (2021) “Advances and Open Problems in Federated Learning” Foundations and Trends in Machine Learning DOI: https://doi.org/10.1561/2200000083.
  2. [2] Q. Li et al., (2023) “A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection” IEEE Transactions on Knowledge and Data Engineering DOI: https://doi.org/10.1109/TKDE.2021.3124599.
  3. [3] D. C. Nguyen et al., (2021) “Federated Learning for Internet of Things: A Comprehensive Survey” IEEE Communications Surveys & Tutorials DOI: https://doi.org/10.1109/COMST.2021.3075439.
  4. [4] C. Zhang et al., (2021) “A Survey on Federated Learning” Knowledge-Based Systems DOI: https://doi.org/10.1016/j.knosys.2021.106775.
  5. [5] X. Ma et al., (2022) “A State-of-the-Art Survey on Solving Non-IID Data in Federated Learning” Future Generation Computer Systems DOI: https://doi.org/10.1016/j.future.2022.05.003.
  6. [6] M. Ye et al., (2024) “Heterogeneous Federated Learning: State-of-the-Art and Research Challenges” ACM Computing Surveys DOI: https://doi.org/10.1145/3625558.
  7. [7] A. Z. Tan et al., (2023) “Towards Personalized Federated Learning” IEEE Transactions on Neural Networks and Learning Systems DOI: https://doi.org/10.1109/TNNLS.2022.3160699.
  8. [8] V. Mothukuri et al., (2021) “A Survey on Security and Privacy of Federated Learning” Future Generation Computer Systems DOI: https://doi.org/10.1016/j.future.2020.10.007.
  9. [9] A. El Ouadrhiri and A. Abdelhadi, (2022) “Differential Privacy for Deep and Federated Learning: A Survey” IEEE Access DOI: https://doi.org/10.1109/ACCESS.2022.3151670.
  10. [10] R. Xu et al., (2024) “TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning” IEEE Transactions on Dependable and Secure Computing DOI: https://doi.org/10.1109/TDSC.2024.3350206.
  11. [11] M. Aggarwal et al., (2024) “A Comprehensive Review of Federated Learning: Methods, Applications, and Challenges in Privacy-Preserving Collaborative Model Training” Applied Data Science and Smart Systems DOI: https://doi.org/10.1201/9781003471059-73.
  12. [12] M. Aggarwal et al., (2023) “Privacy Preserved Collaborative Transfer Learning Model with Heterogeneous Distributed Data for Brain Tumor Classification” International Journal of Imaging Systems and Technology DOI: https://doi.org/10.1002/ima.22994.
  13. [13] C. Gupta et al., (2023) “Cross-Silo, Privacy-Preserving, and Lightweight Federated Multimodal System for the Identification of Major Depressive Disorder Using Audio and Electroencephalogram” Diagnostics DOI: https://doi.org/10.3390/diagnostics14010043.
  14. [14] F. L. da Silva et al., (2023) “A Systematic Literature Review on Educational Recommender Systems for Teaching and Learning: Research Trends, Limitations and Opportunities” Education and Information Technologies DOI: https://doi.org/10.1007/s10639-022-11341-9.
  15. [15] M. L. Bernacki et al., (2021) “A Systematic Review of Research on Personalized Learning: Personalized by Whom, to What, How, and for What Purpose(s)?” Educational Psychology Review DOI: https://doi.org/10.1007/s10648-021-09615-8.
  16. [16] G. Abdelrahman et al., (2023) “Knowledge Tracing: A Survey” ACM Computing Surveys DOI: https://doi.org/10.1145/3569576.
  17. [17] M. Aggarwal et al., (2025) “FL-QNNs: Memory Efficient and Privacy Preserving Framework for Peripheral Blood Cell Classification” IEEE Access DOI: https://doi.org/10.1109/ACCESS.2025.3595861.
  18. [18] M. Aggarwal et al., (2025) “A Survey on Privacy-Preserving Enabled Healthcare Services Focusing on Robust Aggregation” International Journal of Computational Intelligence Systems DOI: https://doi.org/10.1007/s44196-025-01020-1.
  19. [19] D. K. Gude et al., (2026) “An Efficient Privacy-Aware Framework for Traffic Violation Detection Using Federated Learning” ICASST DOI: https://doi.org/10.1109/ICASST68917.2026.11484514.
  20. [20] C. Gao et al., (2023) “A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions” ACM Transactions on Recommender Systems DOI: https://doi.org/10.1145/3568022.
  21. [21] Z. Alamgir et al., (2022) “Federated Recommenders: Methods, Challenges and Future” Cluster Computing DOI: https://doi.org/10.1007/s10586-022-03644-w.