Papers
Topics
Authors
Recent
Search
2000 character limit reached

ODMixer: Fine-grained Spatial-temporal MLP for Metro Origin-Destination Prediction

Published 24 Apr 2024 in cs.CV | (2404.15734v4)

Abstract: Metro Origin-Destination (OD) prediction is a crucial yet challenging spatial-temporal prediction task in urban computing, which aims to accurately forecast cross-station ridership for optimizing metro scheduling and enhancing overall transport efficiency. Analyzing fine-grained and comprehensive relations among stations effectively is imperative for metro OD prediction. However, existing metro OD models either mix information from multiple OD pairs from the station's perspective or exclusively focus on a subset of OD pairs. These approaches may overlook fine-grained relations among OD pairs, leading to difficulties in predicting potential anomalous conditions. To address these challenges, we learn traffic evolution from the perspective of all OD pairs and propose a fine-grained spatial-temporal MLP architecture for metro OD prediction, namely ODMixer. Specifically, our ODMixer has double-branch structure and involves the Channel Mixer, the Multi-view Mixer, and the Bidirectional Trend Learner. The Channel Mixer aims to capture short-term temporal relations among OD pairs, the Multi-view Mixer concentrates on capturing spatial relations from both origin and destination perspectives. To model long-term temporal relations, we introduce the Bidirectional Trend Learner. Extensive experiments on two large-scale metro OD prediction datasets HZMOD and SHMO demonstrate the advantages of our ODMixer. Our code is available at https://github.com/KLatitude/ODMixer.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Layer normalization. arXiv preprint arXiv:1607.06450 (2016).
  2. STG2seq: spatial-temporal graph to sequence model for multi-step passenger demand forecasting. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. 1981–1987.
  3. Tsmixer: An all-mlp architecture for time series forecasting. arXiv preprint arXiv:2303.06053 (2023).
  4. Visual-linguistic causal intervention for radiology report generation. arXiv preprint arXiv:2303.09117 (2023).
  5. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 1724–1734.
  6. TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting. arXiv preprint arXiv:2306.09364 (2023).
  7. Online spatio-temporal crowd flow distribution prediction for complex metro system. IEEE Transactions on knowledge and data engineering 34, 2 (2020), 865–880.
  8. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
  9. Spatio-temporal graph neural networks for predictive learning in urban computing: A survey. IEEE Transactions on Knowledge and Data Engineering (2023).
  10. A Survey on Graph Neural Networks in Intelligent Transportation Systems. arXiv preprint arXiv:2401.00713 (2024).
  11. MLP4Rec: A Pure MLP Architecture for Sequential Recommendations. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. 2138–2144.
  12. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. In International Conference on Learning Representations.
  13. DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. 6058–6066. https://doi.org/10.24963/ijcai.2023/672
  14. Pay attention to mlps. Advances in Neural Information Processing Systems 34 (2021), 9204–9215.
  15. Physical-virtual collaboration modeling for intra-and inter-station metro ridership prediction. IEEE Transactions on Intelligent Transportation Systems 23, 4 (2020), 3377–3391.
  16. Online metro origin-destination prediction via heterogeneous information aggregation. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 3 (2022), 3574–3589.
  17. Cross-modal causal relational reasoning for event-level visual question answering. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).
  18. Hierarchically learned view-invariant representations for cross-view action recognition. IEEE Transactions on Circuits and Systems for Video Technology 29, 8 (2018), 2416–2430.
  19. Global temporal representation based cnns for infrared action recognition. IEEE Signal Processing Letters 25, 6 (2018), 848–852.
  20. Deep image-to-video adaptation and fusion networks for action recognition. IEEE Transactions on Image Processing 29 (2019), 3168–3182.
  21. Temporal contrastive graph learning for video action recognition and retrieval. arXiv preprint arXiv:2101.00820 (2021).
  22. Semantics-aware adaptive knowledge distillation for sensor-to-vision action recognition. IEEE Transactions on Image Processing 30 (2021), 5573–5588.
  23. Tcgl: Temporal contrastive graph for self-supervised video representation learning. IEEE Transactions on Image Processing 31 (2022), 1978–1993.
  24. Causal reasoning meets visual representation learning: A prospective study. Machine Intelligence Research 19, 6 (2022), 485–511.
  25. Long Short-Term Memory. 2010. Long short-term memory. Neural computation 9, 8 (2010), 1735–1780.
  26. Discrete graph structure learning for forecasting multiple time series. (2021).
  27. Short-Term Metro Origin-Destination Passenger Flow Prediction via Spatio-Temporal Dynamic Attentive Multi-Hypergraph Network. IEEE Transactions on Intelligent Transportation Systems (2024).
  28. Sparse MLP for image recognition: Is self-attention really necessary?. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 2344–2351.
  29. Towards causalgpt: A multi-agent approach for faithful knowledge reasoning via promoting causal consistency in llms. arXiv preprint arXiv:2308.11914 (2023).
  30. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems 34 (2021), 24261–24272.
  31. Resmlp: Feedforward networks for image classification with data-efficient training. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 5314–5321.
  32. Urban regional function guided traffic flow prediction. Information Sciences 634 (2023), 308–320.
  33. Traffic Origin-Destination Demand Prediction via Multichannel Hypergraph Convolutional Networks. IEEE Transactions on Computational Social Systems (2024).
  34. Visual Causal Scene Refinement for Video Question Answering (MM ’23). Association for Computing Machinery, New York, NY, USA, 377 C386. https://doi.org/10.1145/3581783.3611873
  35. Graph wavenet for deep spatial-temporal graph modeling. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. 1907–1913.
  36. Dual adversarial adaptation for cross-device real-world image super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5667–5676.
  37. Adaptive Feature Fusion Networks for Origin-Destination Passenger Flow Prediction in Metro Systems. IEEE Transactions on Intelligent Transportation Systems (2023).
  38. Skeletonmae: graph-based masked autoencoder for skeleton sequence pre-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5606–5618.
  39. Spatiotemporal virtual graph convolution network for key origin-destination flow prediction in metro system. Mathematical Problems in Engineering 2022 (2022).
  40. Completion and augmentation-based spatiotemporal deep learning approach for short-term metro origin-destination matrix prediction under limited observable data. Neural Computing and Applications 35, 4 (2023), 3325–3341.
  41. Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method. Transportation Research Part C: Emerging Technologies 124 (2021), 102928.
  42. Deep Learning for Metro Short-Term Origin-Destination Passenger Flow Forecasting Considering Section Capacity Utilization Ratio. IEEE Transactions on Intelligent Transportation Systems (2023).
  43. MLPST: MLP is All You Need for Spatio-Temporal Prediction. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 3381–3390.
  44. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 11106–11115.
  45. Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit. IEEE Transactions on Intelligent Transportation Systems (2023).
  46. Hybrid-order representation learning for electricity theft detection. IEEE Transactions on Industrial Informatics 19, 2 (2022), 1248–1259.

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up