Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

LightTR: A Lightweight Framework for Federated Trajectory Recovery (2405.03409v1)

Published 6 May 2024 in cs.LG

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. W. Luo, H. Tan, L. Chen, and L. M. Ni, “Finding time period-based most frequent path in big trajectory data,” in SIGMOD, 2013, pp. 713–724.
  2. S. Zhang, S. Wang, X. Wang, S. Zhang, H. Miao, and J. Zhu, “Multi-task adversarial learning for semi-supervised trajectory-user linking,” in ECML-PKDD, vol. 13716, 2022, pp. 418–434.
  3. Y. Zhao, S. Shang, Y. Wang, B. Zheng, Q. V. H. Nguyen, and K. Zheng, “Rest: A reference-based framework for spatio-temporal trajectory compression,” in SIGKDD, 2018, pp. 2797–2806.
  4. S. Liu, H. Su, Y. Zhao, K. Zeng, and K. Zheng, “Lane change scheduling for autonomous vehicle: A prediction-and-search framework,” in SIGKDD, 2021, pp. 3343–3353.
  5. M. Chen, Y. Zhao, Y. Liu, X. Yu, and K. Zheng, “Modeling spatial trajectories with attribute representation learning,” TKDE, vol. 34, no. 4, pp. 1902–1914, 2022.
  6. K. Zheng, Y. Zhao, D. Lian, B. Zheng, G. Liu, and X. Zhou, “Reference-based framework for spatio-temporal trajectory compression and query processing,” TKDE, vol. 32, no. 11, pp. 2227–2240, 2019.
  7. L. Deng, H. Sun, Y. Zhao, S. Liu, and K. Zheng, “S2tul: A semi-supervised framework for trajectory-user linking,” in WSDM, 2023, pp. 375–383.
  8. J. Xiao, Z. Xiao, D. Wang, V. Havyarimana, C. Liu, C. Zou, and D. Wu, “Vehicle trajectory interpolation based on ensemble transfer regression,” TITS, vol. 23, no. 7, pp. 7680–7691, 2021.
  9. C. Meng, S. Rambhatla, and Y. Liu, “Cross-node federated graph neural network for spatio-temporal data modeling,” in SIGKDD, 2021, pp. 1202–1211.
  10. Y. Tong, D. Shi, Y. Xu, W. Lv, Z. Qin, and X. Tang, “Combinatorial optimization meets reinforcement learning: Effective taxi order dispatching at large-scale,” TKDE, pp. 1–1, 2021.
  11. K. Zheng, Y. Zheng, X. Xie, and X. Zhou, “Reducing uncertainty of low-sampling-rate trajectories,” in ICDE.   IEEE, 2012, pp. 1144–1155.
  12. P. Banerjee, S. Ranu, and S. Raghavan, “Inferring uncertain trajectories from partial observations,” in ICDM, 2014, pp. 30–39.
  13. J. Yuan, Y. Zheng, C. Zhang, X. Xie, and G.-Z. Sun, “An interactive-voting based map matching algorithm,” in MDM, 2010, pp. 43–52.
  14. J. A. Alvarez-Garcia, J. A. Ortega, L. Gonzalez-Abril, and F. Velasco, “Trip destination prediction based on past gps log using a hidden markov model,” Expert Systems with Applications, vol. 37, no. 12, pp. 8166–8171, 2010.
  15. H. Sun, C. Yang, L. Deng, F. Zhou, F. Huang, and K. Zheng, “Periodicmove: Shift-aware human mobility recovery with graph neural network,” in CIKM’21, 2021, pp. 1734–1743.
  16. H. Ren, S. Ruan, Y. Li, J. Bao, C. Meng, R. Li, and Y. Zheng, “Mtrajrec: Map-constrained trajectory recovery via seq2seq multi-task learning,” in SIGKDD, 2021, pp. 1410–1419.
  17. T. Xia, Y. Qi, J. Feng, F. Xu, F. Sun, D. Guo, and Y. Li, “Attnmove: History enhanced trajectory recovery via attentional network,” in AAAI, vol. 35, no. 5, 2021, pp. 4494–4502.
  18. C. Yang and Z. Pei, “Long-short term spatio-temporal aggregation for trajectory prediction,” TITS, vol. 24, no. 4, pp. 4114–4126, 2023.
  19. J. Wang, N. Wu, X. Lu, W. X. Zhao, and K. Feng, “Deep trajectory recovery with fine-grained calibration using kalman filter,” TKDE, vol. 33, no. 3, pp. 921–934, 2019.
  20. K. Wei, J. Li, M. Ding, C. Ma, H. H. Yang, F. Farokhi, S. Jin, T. Q. S. Quek, and H. Vincent Poor, “Federated learning with differential privacy: Algorithms and performance analysis,” IEEE T INF FOREN SEC, vol. 15, pp. 3454–3469, 2020.
  21. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y. Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in AISTATS, 2017, pp. 1273–1282.
  22. Z. Lai, D. Zhang, H. Li, C. S. Jensen, H. Lu, and Y. Zhao, “Lightcts: A lightweight framework for correlated time series forecasting,” SIGMOD, vol. 1, no. 2, pp. 1–26, 2023.
  23. S. Brakatsoulas, D. Pfoser, R. Salas, and C. Wenk, “On map-matching vehicle tracking data,” in PVLDB, 2005, pp. 853–864.
  24. E. Rappos, S. Robert, and P. Cudré-Mauroux, “A force-directed approach for offline gps trajectory map matching,” in SIGSPATIAL, 2018, pp. 319–328.
  25. E. Chambers, B. T. Fasy, Y. Wang, and C. Wenk, “Map-matching using shortest paths,” TSAS, vol. 6, no. 1, pp. 1–17, 2020.
  26. S. Zheng, Y. Yue, and P. Lucey, “Generating long-term trajectories using deep hierarchical networks,” in NIPS, 2016, p. 1551–1559.
  27. Z. Chen, H. T. Shen, and X. Zhou, “Discovering popular routes from trajectories,” in ICDE, 2011, pp. 900–911.
  28. H. Su, K. Zheng, H. Wang, J. Huang, and X. Zhou, “Calibrating trajectory data for similarity-based analysis,” in SIGMOD, 2013, pp. 833–844.
  29. H. Su, K. Zheng, J. Huang, H. Wang, and X. Zhou, “Calibrating trajectory data for spatio-temporal similarity analysis,” VLDBJ, vol. 24, pp. 93–116, 2015.
  30. Y. Lun, H. Miao, J. Shen, R. Wang, X. Wang, and S. Wang, “Resisting tul attack: balancing data privacy and utility on trajectory via collaborative adversarial learning,” GeoInformatica, pp. 1–21, 2023.
  31. J. Fang, C. Zhu, P. Zhang, H. Yu, and J. Xue, “Heterogeneous trajectory forecasting via risk and scene graph learning,” TITS, 2023.
  32. W. Chen, L. Chen, Y. Xie, W. Cao, Y. Gao, and X. Feng, “Multi-range attentive bicomponent graph convolutional network for traffic forecasting,” in AAAI, vol. 34, no. 04, 2020, pp. 3529–3536.
  33. X. Wu, D. Zhang, C. Guo, C. He, B. Yang, and C. S. Jensen, “Autocts: Automated correlated time series forecasting,” PVLDB, vol. 15, no. 4, pp. 971–983, 2021.
  34. X. Wu, D. Zhang, M. Zhang, C. Guo, B. Yang, and C. S. Jensen, “Autocts+: Joint neural architecture and hyperparameter search for correlated time series forecasting,” SIGMOD, vol. 1, no. 1, pp. 1–26, 2023.
  35. J. Liang, X. Zhao, M. Li, Z. Zhang, W. Wang, H. Liu, and Z. Liu, “Mmmlp: Multi-modal multilayer perceptron for sequential recommendations,” in WWW, 2023, pp. 1109–1117.
  36. M. Li, Z. Zhang, X. Zhao, W. Wang, M. Zhao, R. Wu, and R. Guo, “Automlp: Automated mlp for sequential recommendations,” in WWW, 2023, pp. 1190–1198.
  37. S. J. Pan and Q. Yang, “A survey on transfer learning,” TKDE, vol. 22, no. 10, pp. 1345–1359, 2009.
  38. S. Hoteit, S. Secci, S. Sobolevsky, C. Ratti, and G. Pujolle, “Estimating human trajectories and hotspots through mobile phone data,” Comput. Netw., vol. 64, pp. 296–307, 2014.
  39. Y. Chen, H. Zhang, W. Sun, and B. Zheng, “Rntrajrec: Road network enhanced trajectory recovery with spatial-temporal transformer,” arXiv:2211.13234, 2022.
  40. F. Chen, M. Luo, Z. Dong, Z. Li, and X. He, “Federated meta-learning with fast convergence and efficient communication,” arXiv preprint arXiv:1802.07876, 2018.
  41. J. Feng, C. Rong, F. Sun, D. Guo, and Y. Li, “Pmf: A privacy-preserving human mobility prediction framework via federated learning,” IMWUT, vol. 4, no. 1, pp. 1–21, 2020.
  42. Y. Zhang, L. Deng, Y. Zhao, J. Chen, J. Xie, and K. Zheng, “Simidtr: Deep trajectory recovery with enhanced trajectory similarity,” in DASFAA, 2023, pp. 431–447.
  43. Y. Chen, G. Cong, and C. Anda, “Teri: An effective framework for trajectory recovery with irregular time intervals,” PVLDB, vol. 17, no. 3, pp. 414–426, 2024.
  44. X. Luo, Y. Wu, X. Xiao, and B. C. Ooi, “Feature inference attack on model predictions in vertical federated learning,” in ICDE, 2021, pp. 181–192.
  45. Y. Liu, Y. Kang, C. Xing, T. Chen, and Q. Yang, “A secure federated transfer learning framework,” IEEE INTELL SYST, vol. 35, no. 4, pp. 70–82, 2020.
  46. L. Gao, H. Fu, L. Li, Y. Chen, M. Xu, and C.-Z. Xu, “Feddc: Federated learning with non-iid data via local drift decoupling and correction,” in CVPR, 2022, pp. 10 112–10 121.
  47. E. Diao, J. Ding, and V. Tarokh, “Heterofl: Computation and communication efficient federated learning for heterogeneous clients,” arXiv:2010.01264, 2020.
  48. Y. Shi, Y. Tong, Y. Zeng, Z. Zhou, B. Ding, and L. Chen, “Efficient approximate range aggregation over large-scale spatial data federation,” TKDE, vol. 35, no. 1, pp. 418–430, 2021.
  49. Y. Liu, J. J. Q. Yu, J. Kang, D. Niyato, and S. Zhang, “Privacy-preserving traffic flow prediction: A federated learning approach,” IoTJ, vol. 7, no. 8, pp. 7751–7763, 2020.
  50. F. Yin, Z. Lin, Q. Kong, Y. Xu, D. Li, S. Theodoridis, and S. R. Cui, “Fedloc: Federated learning framework for data-driven cooperative localization and location data processing,” IEEE Open Journal of Signal Processing, vol. 1, pp. 187–215, 2020.
Citations (11)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now