Papers
Topics
Authors
Recent
Search
2000 character limit reached

Enhancing Traffic Prediction with Textual Data Using Large Language Models

Published 10 May 2024 in cs.CL and cs.AI | (2405.06719v1)

Abstract: Traffic prediction is pivotal for rational transportation supply scheduling and allocation. Existing researches into short-term traffic prediction, however, face challenges in adequately addressing exceptional circumstances and integrating non-numerical contextual information like weather into models. While, LLMs offer a promising solution due to their inherent world knowledge. However, directly using them for traffic prediction presents drawbacks such as high cost, lack of determinism, and limited mathematical capability. To mitigate these issues, this study proposes a novel approach. Instead of directly employing large models for prediction, it utilizes them to process textual information and obtain embeddings. These embeddings are then combined with historical traffic data and inputted into traditional spatiotemporal forecasting models. The study investigates two types of special scenarios: regional-level and node-level. For regional-level scenarios, textual information is represented as a node connected to the entire network. For node-level scenarios, embeddings from the large model represent additional nodes connected only to corresponding nodes. This approach shows a significant improvement in prediction accuracy according to our experiment of New York Bike dataset.

Authors (1)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA, 2020. Curran Associates Inc.
  2. Spatial-temporal large language model for traffic prediction. ArXiv, abs/2401.10134, 2024.
  3. Promptcast: A new prompt-based learning paradigm for time series forecasting. IEEE Transactions on Knowledge and Data Engineering, 2022.
  4. Large language models are zero-shot time series forecasters. ArXiv, abs/2310.07820, 2023.
  5. Urbangpt: Spatio-temporal large language models. ArXiv, abs/2403.00813, 2024.
  6. Adaptive graph convolutional recurrent network for traffic forecasting. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA, 2020. Curran Associates Inc.
  7. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In International Conference on Learning Representations, 2018.
  8. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI’18, page 3634–3640. AAAI Press, 2018.
  9. 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, KDD ’20, page 753–763, New York, NY, USA, 2020. Association for Computing Machinery.
  10. Graph wavelet neural network. In International Conference on Learning Representations, 2019.
  11. T-gcn: A temporal graph convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems, 21(9):3848–3858, 2020.
  12. Spatial-temporal transformer networks for traffic flow forecasting. ArXiv, abs/2001.02908, 2020.
  13. Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting. In AAAI Conference on Artificial Intelligence, 2020.
  14. Time series forecasting with llms: Understanding and enhancing model capabilities. ArXiv, abs/2402.10835, 2024.
  15. Temporal data meets llm - explainable financial time series forecasting. ArXiv, abs/2306.11025, 2023.
  16. Lstprompt: Large language models as zero-shot time series forecasters by long-short-term prompting. ArXiv, abs/2402.16132, 2024.
  17. Timegpt-1. ArXiv, abs/2310.03589, 2023.
  18. One fits all: Power general time series analysis by pretrained lm. In Neural Information Processing Systems, 2023.
  19. Multi-patch prediction: Adapting llms for time series representation learning. ArXiv, abs/2402.04852, 2024.
  20. Autotimes: Autoregressive time series forecasters via large language models. ArXiv, abs/2402.02370, 2024.
  21. Dewave: Discrete eeg waves encoding for brain dynamics to text translation. ArXiv, abs/2309.14030, 2023.
  22. Leveraging vision-language models for granular market change prediction. ArXiv, abs/2301.10166, 2023.
  23. Etp: Learning transferable ecg representations via ecg-text pre-training. ArXiv, abs/2309.07145, 2023.
  24. Large language models for time series: A survey. ArXiv, abs/2402.01801, 2024.
  25. Talk like a graph: Encoding graphs for large language models. In The Twelfth International Conference on Learning Representations, 2024.
  26. Graphtext: Graph reasoning in text space. ArXiv, abs/2310.01089, 2023.
  27. One for all: Towards training one graph model for all classification tasks. In The Twelfth International Conference on Learning Representations, 2024.
  28. Exploring the potential of large language models (llms) in learning on graphs. ArXiv, abs/2307.03393, 2023.
  29. Llaga: Large language and graph assistant. ArXiv, abs/2402.08170, 2024.
  30. Graphgpt: Graph instruction tuning for large language models. ArXiv, abs/2310.13023, 2023.
  31. Exploring large language models for human mobility prediction under public events. ArXiv, abs/2311.17351, 2023.
  32. Hilm-d: Towards high-resolution understanding in multimodal large language models for autonomous driving. ArXiv, abs/2309.05186, 2023.
  33. Talk2bev: Language-enhanced bird’s-eye view maps for autonomous driving. ArXiv, abs/2310.02251, 2023.
  34. Evaluation of large language models for decision making in autonomous driving. ArXiv, abs/2312.06351, 2023.
  35. Gpt-4v as traffic assistant: An in-depth look at vision language model on complex traffic events. ArXiv, abs/2402.02205, 2024.
  36. Surrealdriver: Designing generative driver agent simulation framework in urban contexts based on large language model. ArXiv, abs/2309.13193, 2023.
  37. Language conditioned traffic generation. ArXiv, abs/2307.07947, 2023.
  38. Urban generative intelligence (ugi): A foundational platform for agents in embodied city environment. ArXiv, abs/2312.11813, 2023.
  39. Transportationgames: Benchmarking transportation knowledge of (multimodal) large language models. ArXiv, abs/2401.04471, 2024.
  40. Large language models in analyzing crash narratives - a comparative study of chatgpt, bard and gpt-4. ArXiv, abs/2308.13563, 2023.
  41. Leveraging social media data to identify factors influencing public attitude towards accessibility, socioeconomic disparity and public transportation. ArXiv, abs/2402.01682, 2024.
  42. Where would i go next? large language models as human mobility predictors. ArXiv, abs/2308.15197, 2023.
  43. Large language models for travel behavior prediction. ArXiv, abs/2312.00819, 2023.
  44. Trafficgpt: Viewing, processing and interacting with traffic foundation models. ArXiv, abs/2309.06719, 2023.
  45. Open-ti: Open traffic intelligence with augmented language model. ArXiv, abs/2401.00211, 2023.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

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

Sign Up to Generate

Open Problems

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

Generate Now

Continue Learning

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

Generate Now

Collections

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

Sign Up

Tweets

Sign up for free to view the 2 tweets with 0 likes about this paper.

Sign Up for Free