Journal article · 2026 · Open access

P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning

Zhuliang Jia, Suprio Ray, Rongxing Lu, Pulei Xiong

IEEE Transactions on Mobile Computing, 1–15 · Published 1 January 2026 · DOI 10.1109/tmc.2026.3739657

Open full textCite this paper

In brief

“P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning” is a 2026 journal article by Zhuliang Jia and 3 co-authors, published in IEEE Transactions on Mobile Computing. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Mobile Computing.

Citations
0
Authors
4

Abstract

Movement trajectory similarity learning supports many transportation applications, such as trajectory retrieval, route analysis, and anomaly detection. In practice, trajectories are increasingly collected by distributed mobile and edge devices rather than stored at a central location. Federated learning enables collaborative training without directly sharing raw trajectories, but differences among client data can reduce model performance. Existing solutions also face challenges in privacypreserving client clustering and usually require separate models for different trajectory similarity relations. To address these problems, we propose P-FLITS, a privacy-preserving federated framework for multi-relation trajectory similarity learning. PFLITS separates public road representation from private trajectory processing and transfers multiple knowledge of trajectory relations into one compact Student model. It further uses trajectory-level differential privacy for client clustering, together with shuffled reporting and secure aggregation to protect client reports and model updates. Formal security analysis shows that P-FLITS provides trajectory-level differential privacy for routeprofile reporting, client-report unlinkability under the shuffling assumptions, and confidentiality of individual model updates under secure aggregation. Experiments on T-Drive, Porto, and GeoLife show that, compared with the closely related F-TSL scheme, P-FLITS achieves better retrieval performance in 46 of 48 evaluated settings, with an average absolute improvement of 17.5 percentage points.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Jia, Z., Ray, S., Lu, R., & Xiong, P. (2026). P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning. IEEE Transactions on Mobile Computing, 1–15. https://doi.org/10.1109/tmc.2026.3739657

MLA 9

Jia, Zhuliang, et al. “P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning.” IEEE Transactions on Mobile Computing, 2026, pp. 1–15. https://doi.org/10.1109/tmc.2026.3739657.

Chicago

Jia, Zhuliang, Suprio Ray, Rongxing Lu, and Pulei Xiong. 2026. “P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning.” IEEE Transactions on Mobile Computing: 1–15. https://doi.org/10.1109/tmc.2026.3739657.

Harvard

Jia, Z. et al. (2026) ‘P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning’, IEEE Transactions on Mobile Computing, pp. 1–15. doi:10.1109/tmc.2026.3739657.

IEEE

Z. Jia, S. Ray, R. Lu, and P. Xiong, “P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning,” IEEE Transactions on Mobile Computing, pp. 1–15, 2026, doi: 10.1109/tmc.2026.3739657.

BibTeX

@article{jia2026flits,
  title     = {{P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning}},
  author    = {Jia, Zhuliang and Ray, Suprio and Lu, Rongxing and Xiong, Pulei},
  journal   = {IEEE Transactions on Mobile Computing},
  year      = {2026},
  pages     = {1--15},
  doi       = {10.1109/tmc.2026.3739657},
  url       = {https://doi.org/10.1109/tmc.2026.3739657}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • federated learning
  • privacy preservation
  • differential privacy
  • client clustering
  • secure aggregation
  • trajectory retrieval
  • edge devices
  • knowledge transfer

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Jia, Z., Ray, S., Lu, R., & Xiong, P. (2026). P-FLITS: Privacy-Preserving Federated Mobile Trajectory Similarity Learning. IEEE Transactions on Mobile Computing, 1–15. https://doi.org/10.1109/tmc.2026.3739657

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Transactions on Mobile Computing: sign in and open the full text from this page.

Who wrote this paper?

Zhuliang Jia, Suprio Ray, Rongxing Lu, Pulei Xiong.

What is the DOI of this paper?

10.1109/tmc.2026.3739657, permanently at https://doi.org/10.1109/tmc.2026.3739657. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.