Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks

Authors: Yijing Liu, Qinxian Liu, Jian-Wei Zhang, Haozhe Feng, Zhongwei Wang, Zihan Zhou, Wei Chen

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments on two traffic datasets with prior structure and four benchmark datasets. The results indicate that TPGNN achieves the state-of-the-art on both short-term and long-term MTS forecastings.
Researcher Affiliation Academia 1 State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China {3150105531,22021050,zjw.cs,fenghz,wzw09,12121109,chenvis}@zju.edu.cn
Pseudocode No The paper describes its framework and inference pipeline but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes 1Code is available at https://github.com/zyplanet/TPGNN.
Open Datasets Yes For the Traffic dataset, the sensor ID s coordinates are provided. We use these coordinates to construct the physical graph... PEMS-D7, PEMS-Bay are publicly available from PEMS [3]... The Traffic, Solar-Energy, Electricity, and Exchange-Rate are publicly available from [2, 19]...
Dataset Splits Yes We divide the dataset into three parts for training, validation, and testing with a ratio of 7:1:2.
Hardware Specification Yes All experiments are conducted on an NVIDIA GeForce RTX 3090 GPU.
Software Dependencies Yes We implement our models with PyTorch 1.10 and CUDA 11.3.
Experiment Setup Yes We tune the hyperparameters on the validation dataset, the results are presented in the Appendix A.7. The learning rate is set to 0.001, and the batch size is set to 32...