mlsanityData to 14 Oct 2026

LightTR: A Lightweight Framework for Federated Trajectory Recovery

arXiv 2405.03409 ↗First posted 6 May 2024cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

With the proliferation of GPS-equipped edge devices, huge trajectory data is generated and accumulated in various domains, motivating a variety of urban applications. Due to the limited acquisition capabilities of edge devices, a lot of trajectories are recorded at a low sampling rate, which may lead to the effectiveness drop of urban applications. We aim to recover a high-sampled trajectory based on the low-sampled trajectory in free space, i.e., without road network information, to enhance the usability of trajectory data and support urban applications more effectively. Recent proposals targeting trajectory recovery often assume that trajectories are available at a central location, which fail to handle the decentralized trajectories and hurt privacy. To bridge the gap between decentralized training and trajectory recovery, we propose a lightweight framework, LightTR, for federated trajectory recovery based on a client-server architecture, while keeping the data decentralized and private in each client/platform center (e.g., each data center of a company). Specifically, considering the limited processing capabilities of edge devices, LightTR encompasses a light local trajectory embedding module that offers improved computational efficiency without compromising its feature extraction capabilities. LightTR also features a meta-knowledge enhanced local-global training scheme to reduce communication costs between the server and clients and thus further offer efficiency improvement. Extensive experiments demonstrate the effectiveness and efficiency of the proposed framework.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 19 of its 50 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

19 of 50 references.

References · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  3. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
  4. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  5. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  6. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  7. 2020Privacy-preserving Traffic Flow Prediction: A Federated Learning Approachcited by 83
  8. 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
  9. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  10. 2021AutoCTS: Automated Correlated Time Series Forecasting -- Extended Versioncited by 48
  11. 2023AutoMLP: Automated MLP for Sequential Recommendationscited by 25
  12. 2017Generating Long-term Trajectories Using Deep Hierarchical Networkscited by 23
7 more
  1. 2022Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecastingcited by 22
  2. 2022RNTrajRec: Road Network Enhanced Trajectory Recovery with Spatial-Temporal Transformercited by 21
  3. 2023LightCTS: A Lightweight Framework for Correlated Time Series Forecastingcited by 18
  4. 2021AttnMove: History Enhanced Trajectory Recovery via Attentional Networkcited by 11
  5. 2022Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learningcited by 11
  6. 2016Inferring Uncertain Trajectories from Partial Observationscited by 4
  7. 2019A Force-Directed Approach for Offline GPS Trajectory Map Matchingcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 10; 2025: 9.

19 papers.

Sort:

By area:

  1. 2024TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignmentcited by 103
  2. 2025Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillationcited by 20
  3. 2024UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Tracescited by 18
  4. 2024MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Versioncited by 14
  5. 2025Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Eracited by 12
  6. 2025Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Reviewcited by 10
  7. 2024Self-Supervised Representation Learning for Geospatial Objects: A Surveycited by 9
  8. 2024C2F-TP: A Coarse-to-Fine Denoising Framework for Uncertainty-Aware Trajectory Predictioncited by 9
  9. 2024PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detectioncited by 7
  10. 2025T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusioncited by 7
  11. 2024DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimationcited by 6
  12. 2024UniTE: A Survey and Unified Pipeline for Pre-training Spatiotemporal Trajectory Embeddingscited by 4
7 more
  1. 2024FairTP: A Prolonged Fairness Framework for Traffic Predictioncited by 3
  2. 2025Breaking Data Silos: Towards Open and Scalable Mobility Foundation Models via Generative Continual Learningcited by 1
  3. 2025LLMs Meet Cross-Modal Time Series Analytics: Overview and Directionscited by 1
  4. 2024PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Modelscited by 0
  5. 2025FedTDP: A Privacy-Preserving and Unified Framework for Trajectory Data Preparation via Federated Learningcited by 0
  6. 2025Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignmentcited by 0
  7. 2025Data-Efficient and Robust Trajectory Generation through Pathlet Dictionary Learningcited by 0