Home

Awesome

Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction

This is a Pytorch implementation of SHARE architecture as described in the paper Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction.

<p align="center"> <img width="600" height="380.5" src=./figs/framework.png> </p>

If you take advantage of the SHARE model in your research, please cite the following:

@inproceedings{zhang2019semi,
  title={Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction},
  author={Zhang, Weijia and Liu, Hao and Liu, Yanchi and Zhou, Jingbo and Xiong, Hui},
  booktitle={Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence},
  pages={1186--1193},
  year={2020}
}

Requirements

This code is based on Python3 (>= 3.6). There are a few dependencies to run the code. The major libraries are listed as follows: