Official Pytorch Code for "Inductive Graph Transformer for Delivery Time Estimation", WSDM 2023
Enter IGT-main:
python main.py -d toy -m IGTYou may configure datasets and models in configs.
Under PIPL, we are unable to provide the evaluated datasets for public use. However, we generate a toy dataset (datasets/toy) with the same format to demonstrate how IGT works.
@inproceedings{zhou2023inductive,
title={Inductive Graph Transformer for Delivery Time Estimation},
author={Zhou, Xin and Wang, Jinglong and Liu, Yong and Wu, Xingyu and Shen, Zhiqi and Leung, Cyril},
booktitle={Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining},
pages={679--687},
year={2023}
}
No commercial use. License reserved by authors.