Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

SARN: Structurally-Aware Recurrent Network for Spatio-Temporal Disaggregation (2306.07292v4)

Published 9 Jun 2023 in cs.LG, cs.AI, and cs.CR

Abstract: Open data is frequently released spatially aggregated, usually to comply with privacy policies. But coarse, heterogeneous aggregations complicate learning and integration for downstream AI/ML systems. In this work, we consider models to disaggregate spatio-temporal data from a low-resolution, irregular partition (e.g., census tract) to a high-resolution, irregular partition (e.g., city block). We propose an overarching model named the Structurally-Aware Recurrent Network (SARN), which integrates structurally-aware spatial attention (SASA) layers into the Gated Recurrent Unit (GRU) model. The spatial attention layers capture spatial interactions among regions, while the gated recurrent module captures the temporal dependencies. Each SASA layer calculates both global and structural attention -- global attention facilitates comprehensive interactions between different geographic levels, while structural attention leverages the containment relationship between different geographic levels (e.g., a city block being wholly contained within a census tract) to ensure coherent and consistent results. For scenarios with limited historical training data, we explore transfer learning and show that a model pre-trained on one city variable can be fine-tuned for another city variable using only a few hundred samples. Evaluating these techniques on two mobility datasets, we find that on both datasets, SARN significantly outperforms other neural models (5% and 1%) and typical heuristic methods (40% and 14%), enabling us to generate realistic, high-quality fine-grained data for downstream applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. STAR-Transformer: a spatio-temporal cross attention transformer for human action recognition. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. , , 3330–3339.
  2. A simulation study of disaggregation regression for spatial disease mapping. Statistics in Medicine 41 (2020), 1 – 16.
  3. Federated Machine Learning, Privacy-Enhancing Technologies, and Data Protection Laws in Medical Research: Scoping Review. J Med Internet Res 25 (30 Mar 2023), e41588. https://doi.org/10.2196/41588
  4. Vineyard Computing: Sensor Networks in Agricultural Production. Pervasive Computing, IEEE 3 (02 2004), 38– 45. https://doi.org/10.1109/MPRV.2004.1269130
  5. S2tnet: Spatio-temporal transformer networks for trajectory prediction in autonomous driving. In Asian Conference on Machine Learning. PMLR, , , 454–469.
  6. Traffic forecasting with graph spatial–temporal position recurrent network. Neural Networks 162 (2023), 340–349.
  7. Alexis J. Comber and Wen Zeng. 2019. Spatial interpolation using areal features: A review of methods and opportunities using new forms of data with coded illustrations. Geography Compass (2019), .
  8. Dynamic population mapping using mobile phone data. Proceedings of the National Academy of Sciences of the United States of America 111, 45 (Sept. 2014), 15888–15893. https://doi.org/10.1073/pnas.1408439111
  9. Privacy-preserving data aggregation in smart metering systems: an overview. IEEE Signal Processing Magazine 30, 2 (2013), 75–86. https://doi.org/10.1109/MSP.2012.2228343
  10. Learning all dynamics: Traffic forecasting via locality-aware spatio-temporal joint transformer. IEEE Transactions on Intelligent Transportation Systems 23, 12 (2022), 23433–23446.
  11. A Framework for the Areal Interpolation of Socioeconomic Data. Environment and Planning A 25 (1993), 383 – 397.
  12. Open Data Privacy: A risk-benefit, process-oriented approach to sharing and protecting municipal data. In . , , .
  13. Bin Han and Bill Howe. 2023. Adapting to Skew: Imputing Spatiotemporal Urban Data with 3D Partial Convolutions and Biased Masking. arXiv:2301.04233 [cs.CV]
  14. PDA: Privacy-Preserving Data Aggregation in Wireless Sensor Networks. In IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications. , , 2045–2053. https://doi.org/10.1109/INFCOM.2007.237
  15. Integrative urban AI to expand coverage, access, and equity of urban data. The European Physical Journal Special Topics 231 (04 2022). https://doi.org/10.1140/epjs/s11734-022-00475-z
  16. Blockchain-Enabled Federated Learning Data Protection Aggregation Scheme With Differential Privacy and Homomorphic Encryption in IIoT. IEEE Transactions on Industrial Informatics 18, 6 (2022), 4049–4058. https://doi.org/10.1109/TII.2021.3085960
  17. Selective cross-city transfer learning for traffic prediction via source city region re-weighting. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. , , 731–741.
  18. Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. , , 1032–1043.
  19. Daniel Jurafsky and James Martin. 2008. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Vol. 2. , .
  20. Integrating Data Lake Tables. Proc. VLDB Endow. 16, 4 (dec 2022), 932–945. https://doi.org/10.14778/3574245.3574274
  21. Dstagnn: Dynamic spatial-temporal aware graph neural network for traffic flow forecasting. In International conference on machine learning. PMLR, , , 11906–11917.
  22. Variational Learning on Aggregate Outputs with Gaussian Processes. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc., . https://proceedings.neurips.cc/paper_files/paper/2018/file/24b43fb034a10d78bec71274033b4096-Paper.pdf
  23. Mengzhang Li and Zhanxing Zhu. 2021. Spatial-temporal fusion graph neural networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. , , 4189–4196.
  24. Multi-task representation learning for travel time estimation. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. , , 1695–1704.
  25. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926 , (2017).
  26. Spatio-temporal adaptive embedding makes vanilla transformer sota for traffic forecasting. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. , , 4125–4129.
  27. Unified route representation learning for multi-modal transportation recommendation with spatiotemporal pre-training. The VLDB Journal 32, 2 (2023), 325–342.
  28. Spatial-temporal causal modeling for climate change attribution, In . Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , , 587–596. https://doi.org/10.1145/1557019.1557086
  29. Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. , , 1162–1172.
  30. Learning Stochastic Behaviour of Aggregate Data. In International Conference on Machine Learning. , , .
  31. Jiqian Mo and Zhiguo Gong. 2022. Cross-City Multi-Granular Adaptive Transfer Learning for Traffic Flow Prediction. IEEE Transactions on Knowledge and Data Engineering , (2022), .
  32. Spatial Disaggregation of Historical Census Data Leveraging Multiple Sources of Ancillary Information. ISPRS International Journal of Geo-Information 8, 8 (2019), . https://doi.org/10.3390/ijgi8080327
  33. A hybrid approach for the spatial disaggregation of socio-economic indicators. International Journal of Data Science and Analytics 5 (03 2018). https://doi.org/10.1007/s41060-017-0080-z
  34. Geospatial Disaggregation of Population Data in Supporting SDG Assessments: A Case Study from Deqing County, China. ISPRS Int. J. Geo Inf. 8 (2019), 356.
  35. Transformer-enhanced periodic temporal convolution network for long short-term traffic flow forecasting. Expert Systems with Applications 227 (2023), 120203.
  36. U-Net: Convolutional Networks for Biomedical Image Segmentation. CoRR abs/1505.04597 (2015), . arXiv:1505.04597 http://arxiv.org/abs/1505.04597
  37. Rahul Singh and Yongxin Chen. 2023. Learning Gaussian Hidden Markov Models From Aggregate Data. IEEE Control Systems Letters 7 (2023), 478–483. https://doi.org/10.1109/LCSYS.2022.3187352
  38. Derek Sonderegger and Robert Buscaglia. 2020. Introduction to Statistical Methodology, Second Edition. , .
  39. Disaggregating Census Data for Population Mapping Using Random Forests with Remotely-Sensed and Ancillary Data. PLOS ONE 10, 2 (02 2015), 1–22. https://doi.org/10.1371/journal.pone.0107042
  40. Waldo R. Tobler. 1979. Smooth Pycnophylactic Interpolation for Geographical Regions. J. Amer. Statist. Assoc. 74, 367 (1979), 519–530. http://www.jstor.org/stable/2286968
  41. Secure Healthcare Data Aggregation and Transmission in IoT—A Survey. IEEE Access 9 (2021), 16849–16865. https://doi.org/10.1109/ACCESS.2021.3052850
  42. A spatial regression model for the disaggregation of areal unit based data to high-resolution grids with application to vaccination coverage mapping. Statistical Methods in Medical Research 28 (2018), 3226 – 3241.
  43. Attention is all you need. In Advances in neural information processing systems. 5998–6008.
  44. The emergence of a third wave of open data. , (2020), .
  45. Understanding bike-sharing systems using data mining: Exploring activity patterns. Procedia-Social and Behavioral Sciences 20 (2011), 514–523.
  46. Traffic flow prediction via spatial temporal graph neural network. In Proceedings of the web conference 2020. , , 1082–1092.
  47. Spatially disaggregated population estimates in the absence of national population and housing census data. In . , , .
  48. A Universal Unbiased Method for Classification from Aggregate Observations. arXiv:2306.11343 [cs.LG]
  49. Learning spatio-temporal transformer for visual tracking. In Proceedings of the IEEE/CVF international conference on computer vision. , , 10448–10457.
  50. Spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks. Sensors 17, 7 (2017), 1501.
  51. Deep learning: A generic approach for extreme condition traffic forecasting. In Proceedings of the 2017 SIAM International Conference on Data Mining. SIAM, , , 777–785.
  52. MCL-STGAT: Taxi demand forecasting using spatio-temporal graph attention network with Markov cluster algorithm. Int. J. Innovative Comput. Inf. Control 19, 4 (2023), 1251–1264.
  53. Learning from Aggregate Observations. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS’20). Curran Associates Inc., Red Hook, NY, USA, Article 670,  pages.
  54. Supply-demand-aware deep reinforcement learning for dynamic fleet management. ACM Transactions on Intelligent Systems and Technology (TIST) 13, 3 (2022), 1–19.
  55. Gman: A graph multi-attention network for traffic prediction. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. , , 1234–1241.
  56. AST-GCN: Attribute-augmented spatiotemporal graph convolutional network for traffic forecasting. IEEE Access 9 (2021), 35973–35983.

Summary

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

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

Tweets