Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 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

COLA: Cross-city Mobility Transformer for Human Trajectory Simulation (2403.01801v1)

Published 4 Mar 2024 in cs.LG and cs.AI

Abstract: Human trajectory data produced by daily mobile devices has proven its usefulness in various substantial fields such as urban planning and epidemic prevention. In terms of the individual privacy concern, human trajectory simulation has attracted increasing attention from researchers, targeting at offering numerous realistic mobility data for downstream tasks. Nevertheless, the prevalent issue of data scarcity undoubtedly degrades the reliability of existing deep learning models. In this paper, we are motivated to explore the intriguing problem of mobility transfer across cities, grasping the universal patterns of human trajectories to augment the powerful Transformer with external mobility data. There are two crucial challenges arising in the knowledge transfer across cities: 1) how to transfer the Transformer to adapt for domain heterogeneity; 2) how to calibrate the Transformer to adapt for subtly different long-tail frequency distributions of locations. To address these challenges, we have tailored a Cross-city mObiLity trAnsformer (COLA) with a dedicated model-agnostic transfer framework by effectively transferring cross-city knowledge for human trajectory simulation. Firstly, COLA divides the Transformer into the private modules for city-specific characteristics and the shared modules for city-universal mobility patterns. Secondly, COLA leverages a lightweight yet effective post-hoc adjustment strategy for trajectory simulation, without disturbing the complex bi-level optimization of model-agnostic knowledge transfer. Extensive experiments of COLA compared to state-of-the-art single-city baselines and our implemented cross-city baselines have demonstrated its superiority and effectiveness. The code is available at https://github.com/Star607/Cross-city-Mobility-Transformer.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Bike flow prediction with multi-graph convolutional networks. In ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.
  2. Practical Lossless Federated Singular Vector Decomposition over Billion-Scale Data. In ACM Knowledge Discovery and Data Mining.
  3. Mobility network models of COVID-19 explain inequities and inform reopening. Nature 589, 7840 (2021), 82–87.
  4. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research 16 (2002), 321–357.
  5. Bias and debias in recommender system: A survey and future directions. ACM Transactions on Information Systems 41, 3 (2023), 1–39.
  6. TrajGAIL: Generating urban vehicle trajectories using generative adversarial imitation learning. Transportation Research Part C: Emerging Technologies 128 (2021), 103091.
  7. Charles Elkan. 2001. The foundations of cost-sensitive learning. In International Joint Conference on Artificial Intelligence.
  8. DEPTS: deep expansion learning for periodic time series forecasting. International Conference on Learning Representations (2022).
  9. Deepmove: Predicting human mobility with attentional recurrent networks. In International World Wide Web Conferences.
  10. Learning to simulate human mobility. In ACM Knowledge Discovery and Data Mining.
  11. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning.
  12. Bent Fuglede and Flemming Topsoe. 2004. Jensen-Shannon divergence and Hilbert space embedding. In IEEE International Symposium on Information Theory.
  13. Next place prediction using mobility markov chains. In Proceedings of the First Workshop on Measurement, Privacy, and Mobility.
  14. Contextual Spatio-Temporal Graph Representation Learning for Reinforced Human Mobility Mining. Information Sciences 606 (2022), 230–249.
  15. CityNet: A Multi-city Multi-modal Dataset for Smart City Applications. arXiv preprint arXiv:2106.15802 (2021).
  16. Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting. In AAAI Conference on Artificial Intelligence.
  17. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144.
  18. On calibration of modern neural networks. In International Conference on Machine Learning.
  19. What is the Human Mobility in a New City: Transfer Mobility Knowledge Across Cities. In International World Wide Web Conferences.
  20. Sepp Hochreiter and Jurgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.
  21. Disentangling label distribution for long-tailed visual recognition. In IEEE Conference on Computer Vision and Pattern Recognition.
  22. Spatio-temporal meta-graph learning for traffic forecasting. In AAAI Conference on Artificial Intelligence.
  23. Domain adaptation for time series forecasting via attention sharing. In International Conference on Machine Learning.
  24. Selective Cross-City Transfer Learning for Traffic Prediction via Source City Region Re-Weighting. In ACM Knowledge Discovery and Data Mining.
  25. Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics: Systems 39, 2 (2008), 539–550.
  26. Long-tail learning via logit adjustment. In International Conference on Learning Representations.
  27. A non-parametric generative model for human trajectories.. In International Joint Conference on Artificial Intelligence.
  28. Transfer graph neural networks for pandemic forecasting. In AAAI Conference on Artificial Intelligence.
  29. Improving language understanding by generative pre-training. (2018).
  30. Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting. The VLDB Journal 15, 11 (2022), 2733–2746.
  31. Attention is all you need. In Annual Conference on Neural Information Processing Systems.
  32. Forecasting influenza activity using machine-learned mobility map. Nature communications 12, 1 (2021), 1–12.
  33. Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planning. In AAAI Conference on Artificial Intelligence.
  34. LibCity: An Open Library for Traffic Prediction. In ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.
  35. Cross-city transfer learning for deep spatio-temporal prediction. In International Joint Conference on Artificial Intelligence.
  36. Transfer knowledge between cities. In ACM Knowledge Discovery and Data Mining.
  37. Understanding Contrastive Learning via Distributionally Robust Optimization. In Annual Conference on Neural Information Processing Systems.
  38. Adversarial robustness under long-tailed distribution. In IEEE Conference on Computer Vision and Pattern Recognition.
  39. Metropolitan Scale and Longitudinal Dataset of Anonymized Human Mobility Trajectories. arXiv preprint arXiv:2307.03401 (2023).
  40. Participatory cultural mapping based on collective behavior data in location-based social networks. ACM Transactions on Intelligent Systems and Technology 7, 3 (2016), 1–23.
  41. Learning from multiple cities: A meta-learning approach for spatial-temporal prediction. In International World Wide Web Conferences.
  42. A generative model of urban activities from cellular data. IEEE Transactions on Intelligent Transportation Systems 19, 6 (2017), 1682–1696.
  43. Seqgan: Sequence generative adversarial nets with policy gradient. In AAAI Conference on Artificial Intelligence.
  44. Activity trajectory generation via modeling spatiotemporal dynamics. In ACM Knowledge Discovery and Data Mining.
  45. Learning to Simulate Daily Activities via Modeling Dynamic Human Needs. In International World Wide Web Conferences.
  46. Region Embedding With Intra and Inter-View Contrastive Learning. IEEE Transactions on Knowledge and Data Engineering 35, 9 (2023), 9031–9036.
  47. DeepTrip: A Deep Learning Model for the Individual Next Trip Prediction With Arbitrary Prediction Times. IEEE Transactions on Intelligent Transportation Systems 24, 6 (2023), 5842–5855.
  48. Online adaptive asymmetric active learning with limited budgets. IEEE Transactions on Knowledge and Data Engineering 33, 6 (2019), 2680–2692.
  49. Zizhao Zhang and Tomas Pfister. 2021. Learning fast sample re-weighting without reward data. In IEEE Conference on Computer Vision and Pattern Recognition.
  50. Adaptive cost-sensitive online classification. IEEE Transactions on Knowledge and Data Engineering 31, 2 (2018), 214–228.
  51. GeoLife: A collaborative social networking service among user, location and trajectory. IEEE Data Eng. Bull. 33, 2 (2010), 32–39.
Citations (10)
View on Semantic Scholar

Summary

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

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