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

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment (2309.13378v1)

Published 23 Sep 2023 in cs.LG and cs.AI

Abstract: Spatio-Temporal Graph (STG) forecasting is a fundamental task in many real-world applications. Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distribution (OoD) issues and dynamic spatial causation. In this paper, we propose a novel framework called CaST to tackle these two challenges via causal treatments. Concretely, leveraging a causal lens, we first build a structural causal model to decipher the data generation process of STGs. To handle the temporal OoD issue, we employ the back-door adjustment by a novel disentanglement block to separate invariant parts and temporal environments from input data. Moreover, we utilize the front-door adjustment and adopt the Hodge-Laplacian operator for edge-level convolution to model the ripple effect of causation. Experiments results on three real-world datasets demonstrate the effectiveness and practicality of CaST, which consistently outperforms existing methods with good interpretability.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (58)
  1. Adaptive graph convolutional recurrent network for traffic forecasting. Advances in neural information processing systems 33 (2020), 17804–17815.
  2. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018).
  3. Mutual information neural estimation. In International conference on machine learning. PMLR, 531–540.
  4. Graph neural controlled differential equations for traffic forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 6367–6374.
  5. Adarnn: Adaptive learning and forecasting of time series. In Proceedings of the 30th ACM international conference on information & knowledge management. 402–411.
  6. Topological persistence and simplification. In Proceedings 41st annual symposium on foundations of computer science. IEEE, 454–463.
  7. Spatial-temporal graph ode networks for traffic flow forecasting. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. 364–373.
  8. Predicting human mobility with semantic motivation via multi-task attentional recurrent networks. IEEE Transactions on Knowledge and Data Engineering 34, 5 (2020), 2360–2374.
  9. Causal inference in recommender systems: A survey and future directions. arXiv preprint arXiv:2208.12397 (2022).
  10. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In AAAI, Vol. 33. 3656–3663.
  11. Causal inference in statistics: A primer. John Wiley & Sons.
  12. Alex Graves. 2013. Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013).
  13. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence, Vol. 33. 922–929.
  14. Dynamic and multi-faceted spatio-temporal deep learning for traffic speed forecasting. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. 547–555.
  15. Heterogeneous Graph Convolutional Neural Network via Hodge-Laplacian for Brain Functional Data. arXiv preprint arXiv:2302.09323 (2023).
  16. STDEN: Towards physics-guided neural networks for traffic flow prediction. In AAAI, Vol. 36. 4048–4056.
  17. Dl-traff: Survey and benchmark of deep learning models for urban traffic prediction. In Proceedings of the 30th ACM international conference on information & knowledge management. 4515–4525.
  18. CensNet: Convolution with Edge-Node Switching in Graph Neural Networks.. In IJCAI. 2656–2662.
  19. Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey. arXiv preprint arXiv:2303.14483 (2023).
  20. Edge representation learning with hypergraphs. Advances in Neural Information Processing Systems 34 (2021), 7534–7546.
  21. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  22. Thomas N Kipf and Max Welling. [n. d.]. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations.
  23. Hole detection in metabolic connectivity of Alzheimer’s disease using k- Laplacian. In MICCAI. Springer, 297–304.
  24. Ood-gnn: Out-of-distribution generalized graph neural network. IEEE Transactions on Knowledge and Data Engineering (2022).
  25. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926 (2017).
  26. AirFormer: Predicting Nationwide Air Quality in China with Transformers. arXiv preprint arXiv:2211.15979 (2022).
  27. A causal inference look at unsupervised video anomaly detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 1620–1629.
  28. Msdr: Multi-step dependency relation networks for spatial temporal forecasting. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1042–1050.
  29. Do We Really Need Graph Neural Networks for Traffic Forecasting? arXiv preprint arXiv:2301.12603 (2023).
  30. Meinard Müller. 2007. Dynamic time warping. Information retrieval for music and motion (2007), 69–84.
  31. Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge, UK: CambridgeUniversityPress 19, 2 (2000).
  32. Adjusting for confounding with text matching. American Journal of Political Science 64, 4 (2020), 887–903.
  33. Flora Salim and Usman Haque. 2015. Urban computing in the wild: A survey on large scale participation and citizen engagement with ubiquitous computing, cyber physical systems, and Internet of Things. International Journal of Human-Computer Studies 81 (2015), 31–48.
  34. 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 (2013), 83–98.
  35. Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting. AAAI 34, 1 (2020), 914–921.
  36. Causal attention for interpretable and generalizable graph classification. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1696–1705.
  37. Debiasing nlu models via causal intervention and counterfactual reasoning. In AAAI, Vol. 36. 11376–11384.
  38. Hiroyuki Toda. 1991. Vector autoregression and causality. Yale University.
  39. Neural discrete representation learning. Advances in neural information processing systems 30 (2017).
  40. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
  41. Modeling inter-station relationships with attentive temporal graph convolutional network for air quality prediction. In WSDM. 616–634.
  42. Libcity: An open library for traffic prediction. In Proceedings of the 29th International Conference on Advances in Geographic Information Systems. 145–148.
  43. Deep learning for spatio-temporal data mining: A survey. IEEE transactions on knowledge and data engineering (2020).
  44. Visual commonsense r-cnn. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10760–10770.
  45. CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting. In International Conference on Learning Representations.
  46. Deconfounding to explanation evaluation in graph neural networks. arXiv preprint arXiv:2201.08802 (2022).
  47. Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 753–763.
  48. Graph WaveNet for Deep Spatial-Temporal Graph Modeling. In IJCAI. 1907–1913.
  49. Towards out-of-distribution sequential event prediction: A causal treatment. arXiv preprint arXiv:2210.13005 (2022).
  50. Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction. In AAAI, Vol. 33. 5668–5675.
  51. Deep distributed fusion network for air quality prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 965–973.
  52. A literature survey on smart cities. Sci. China Inf. Sci. 58, 10 (2015), 1–18.
  53. Spatio-temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. In IJCAI.
  54. Causal intervention for weakly-supervised semantic segmentation. Advances in Neural Information Processing Systems 33 (2020), 655–666.
  55. Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction. In AAAI. 1655–1661.
  56. Gman: A graph multi-attention network for traffic prediction. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 1234–1241.
  57. Disentangling user interest and conformity for recommendation with causal embedding. In Proceedings of the Web Conference 2021. 2980–2991.
  58. OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs. In Advances in Neural Information Processing Systems.
Citations (27)
View on Semantic Scholar

Summary

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

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