Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecasting (2312.16403v1)

Published 27 Dec 2023 in cs.LG and cs.AI

Abstract: Spatio-temporal forecasting of future values of spatially correlated time series is important across many cyber-physical systems (CPS). Recent studies offer evidence that the use of graph neural networks to capture latent correlations between time series holds a potential for enhanced forecasting. However, most existing methods rely on pre-defined or self-learning graphs, which are either static or unintentionally dynamic, and thus cannot model the time-varying correlations that exhibit trends and periodicities caused by the regularity of the underlying processes in CPS. To tackle such limitation, we propose Time-aware Graph Structure Learning (TagSL), which extracts time-aware correlations among time series by measuring the interaction of node and time representations in high-dimensional spaces. Notably, we introduce time discrepancy learning that utilizes contrastive learning with distance-based regularization terms to constrain learned spatial correlations to a trend sequence. Additionally, we propose a periodic discriminant function to enable the capture of periodic changes from the state of nodes. Next, we present a Graph Convolution-based Gated Recurrent Unit (GCGRU) that jointly captures spatial and temporal dependencies while learning time-aware and node-specific patterns. Finally, we introduce a unified framework named Time-aware Graph Convolutional Recurrent Network (TGCRN), combining TagSL, and GCGRU in an encoder-decoder architecture for multi-step spatio-temporal forecasting. We report on experiments with TGCRN and popular existing approaches on five real-world datasets, thus providing evidence that TGCRN is capable of advancing the state-of-the-art. We also cover a detailed ablation study and visualization analysis, offering detailed insight into the effectiveness of time-aware structure learning.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. STG2Seq: spatial-temporal graph to sequence model for multi-step passenger demand forecasting. In IJCAI, pages 1981–1987, 2019.
  2. Adaptive graph convolutional recurrent network for traffic forecasting. In NeurIPS, pages 17804–17815, 2020.
  3. Time series analysis: forecasting and control. John Wiley & Sons, 2015.
  4. Spectral temporal graph neural network for multivariate time-series forecasting. In NeurIPS, pages 17766–17778, 2020.
  5. XGBoost: A scalable tree boosting system. In KDD, pages 785–794, 2016.
  6. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS, pages 3837–3845, 2016.
  7. Regularization networks and support vector machines. Advances in computational mathematics, 13:1–50, 2000.
  8. Jerome H Friedman. Greedy function approximation: a gradient boosting machine. Annals of statistics, 29:1189–1232, 2001.
  9. Neural message passing for quantum chemistry. In ICML, pages 1263–1272, 2017.
  10. Time2vec: Learning a vector representation of time. arXiv preprint arXiv:1907.05321, 2019.
  11. Graph self-supervised learning with accurate discrepancy learning. In NeurIPS, pages 14085–14098, 2022.
  12. Adam: A method for stochastic optimization. In ICLR, 2015.
  13. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.
  14. Modeling long-and short-term temporal patterns with deep neural networks. In SIGIR, pages 95–104, 2018.
  15. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In ICLR, 2018.
  16. Conditional local convolution for spatio-temporal meteorological forecasting. In AAAI, pages 7470–7478, 2022.
  17. Physical-virtual collaboration modeling for intra-and inter-station metro ridership prediction. IEEE Transactions on Intelligent Transportation Systems, 23(4):3377–3391, 2020.
  18. Mba-stnet: Bayes-enhanced discriminative multi-task learning for flow prediction. IEEE Transactions on Knowledge and Data Engineering, pages 7164–7177, 2022.
  19. Spatio-temporal planning in multi-vehicle scenarios for autonomous vehicle using support vector machines. IEEE Transactions on Intelligent Vehicles, 6(4):611–621, 2020.
  20. Discrete graph structure learning for forecasting multiple time series. In ICLR, 2021.
  21. Convolutional LSTM Network: A machine learning approach for precipitation nowcasting. In NeurIPS, pages 802–810, 2015.
  22. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine, 30(3):83–98, 2013.
  23. Sequence to sequence learning with neural networks. In NeurIPS, pages 3104–3112, 2014.
  24. The simpler the better: a unified approach to predicting original taxi demands based on large-scale online platforms. In KDD, pages 1653–1662, 2017.
  25. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, 9(11):2579–2605, 2008.
  26. AutoCTS: Automated correlated time series forecasting. In PVLDB, pages 971–983, 2021.
  27. Graph wavenet for deep spatial-temporal graph modeling. In IJCAI, pages 1907–1913, 2019.
  28. Connecting the dots: Multivariate time series forecasting with graph neural networks. In KDD, pages 753–763, 2020.
  29. Self-attention with functional time representation learning. In NeurIPS, pages 15889–15899, 2019.
  30. SimpleTS: An efficient and universal model selection framework for time series forecasting. Proceedings of the VLDB Endowment, 16:3741–3753, 2023.
  31. Coupled layer-wise graph convolution for transportation demand prediction. In AAAI, pages 4617–4625, 2021.
  32. Learning the evolutionary and multi-scale graph structure for multivariate time series forecasting. In KDD, pages 2296–2306, 2022.
  33. Deep spatio-temporal residual networks for citywide crowd flows prediction. In AAAI, pages 1655–1661, 2017.
  34. Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. In ICLR, 2023.
  35. A novel analytic framework of real-time multi-vessel collision risk assessment for maritime traffic surveillance. Ocean Engineering, 145:492–501, 2017.
  36. Forecasting fine-grained air quality based on big data. In KDD, pages 2267–2276, 2015.
  37. Informer: Beyond efficient transformer for long sequence time-series forecasting. In AAAI, pages 11106–11115, 2021.
  38. A survey on graph structure learning: Progress and opportunities. arXiv preprint arXiv:2103.03036, 2021.
Citations (1)
View on Semantic Scholar

Summary

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

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