Notification

This is an implementation of this paper(GCE-GNN) based on Tensorflow 2.X, which contains the extra functions as below:

• Log(output figure for loss and MRR@20, P@20)
• preformance enhanced evaluation

Requirements

TensorFlow 2.X (version>=2.10 is prefer)
Python 3.9
CUDA11.6 and above is prefer
cudnn8.7.0 and above is prefer
Caution: For who wants to run in native-Windows, TensorFlow 2.10 was the last TensorFlow release that supported GPU on native-Windows.

Paper data and code

T-mall dataset: https://www.dropbox.com/sh/dbzmtq4zhzbj5o9/AAAMMlmNKL-wAAYK8QWyL9MEa/Datasets?dl=0&subfolder_nav_tracking=1

Citation

Citation
@inproceedings{wang2020global,
    title={Global Context Enhanced Graph Neural Networks for Session-based Recommendation},
    author={Wang, Ziyang and Wei, Wei and Cong, Gao and Li, Xiao-Li and Mao, Xian-Ling and Qiu, Minghui},
    booktitle={Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
    pages={169--178},
    year={2020}
}