Our project focuses on applying large language models (LLMs) to mobility and transportation forecasting. We propose a new model called STGCN-L that incorporates LLMs into spatio-temporal graph convolutional networks for predicting future traffic conditions.
- TCN: An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- GLU and GTU: Language Modeling with Gated Convolutional Networks
- ChebNet: Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- GCN: Semi-Supervised Classification with Graph Convolutional Networks
- STGCN: Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
- TCN: https://github.com/locuslab/TCN
- ChebNet: https://github.com/mdeff/cnn_graph
- GCN: https://github.com/tkipf/pygcn
- STGCN-PyTorch: https://github.com/hazdzz/STGCN/tree/main