STLIB: An information bottleneck-guided LLM-spatiotemporal framework for traffic forecasting
Authors:
- Zewen ShangZSZewen Shang
- Xuewei LiXLXuewei Li
- Zhiqiang LiuZLZhiqiang Liu
- Yingzhou SunYSYingzhou Sun
- Zijian ZhangZZZijian Zhang
- Tianyi XuTXTianyi Xu
- Mei YuMYMei Yu
- 1 June 2026
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 347
Abstract
No abstract availableFunding Information
- National Key Research and Development Program of China
- National Key Research and Development Program of China Stem Cell and Translational Research (2024YFE0115700)
This publication has 42 references indexed in Scilit:
- Sequence-aware adaptive graph convolutional recurrent networks for traffic forecastingKnowledge-Based Systems, 2025
- TPLLM: A traffic prediction framework based on pretrained Large Language ModelsApplied Soft Computing, 2025
- Dynamic spatiotemporal graph convolutional network collaborative pre-training learning for traffic flow predictionKnowledge-Based Systems, 2025
- Spatio-temporal prediction using graph neural networks: A surveyNeurocomputing, 2025
- SHKD: A framework for traffic prediction based on Sub-Hypergraph and Knowledge DistillationKnowledge-Based Systems, 2025
- MGCN: Mamba-integrated spatiotemporal graph convolutional network for long-term traffic forecastingKnowledge-Based Systems, 2024
- SeizureLSTM: An optimal attention-based trans-LSTM network for epileptic seizure detection using optimal weighted feature integrationBiomedical Signal Processing and Control, 2024
- Spatio-temporal fusion and contrastive learning for urban flow predictionKnowledge-Based Systems, 2023
- Sequence to sequence hybrid Bi-LSTM model for traffic speed predictionExpert Systems with Applications, 2023
- GPT-3: Its Nature, Scope, Limits, and ConsequencesMinds and Machines, 2020