CS 7150: Deep Learning project
Project Report is found here.
Use test.ipynb to get test results for the baseline LSTM, DCRNN, STGCN and our novel solution on the test dataset.
Use test_a3tgcn.ipynb to get test results for the A3TGCN model on a small test data subset.
Open-source implementations referred:
- STGCN: https://github.com/FelixOpolka/STGCN-PyTorch
- A3TGCN: https://colab.research.google.com/drive/132hNQ0voOtTVk3I4scbD3lgmPTQub0KR?usp=sharing
References:
[1] Yu, B., Yin, H., & Zhu, Z. (2018, July). Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (pp. 3634-3640) https://arxiv.org/pdf/1709.04875v4.pdf
[2]Li, Y., Yu, R., Shahabi, C., & Liu, Y. (2018). Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. In International Conference on Learning Representations.
[3] Bai, J., Zhu, J., Song, Y., Zhao, L., Hou, Z., Du, R., & Li, H. (2021). A3t-gcn: Attention temporal graph convolutional network for traffic forecasting. ISPRS International Journal of Geo-Information, 10(7), 485. 10