This is a TensorFlow implementation of the GCN-GRU model as described in our paper:
Xujiang Zhao, Feng Chen, Jin-Hee Cho [Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data], Bigdata (2018)
GCN-GRU model are end-to-end trainable deep learning models for dynamic uncertain opinions prediction in dynamic network data.
Clone this repository.
git clone https://github.com/zxj32/GCN-GRU
cd GCN-GRU
Install the dependencies. The code should run with TensorFlow 1.0 and newer.
pip install -r requirements.txt # or make install
python GCN_GRU_run.py
If your graph is very large, please use
python GCN_GRU_sparse.py
In order to use your own data, you have to provide
Have a look at the generate_train_test_epinion() or generate_train_test_epinion_sparse()
function in read_data/read_data.py
for an example.
In this example, we load epinion data with a subgraph 500 nodes. The original datasets can be found here:http://www.trustlet.org/downloaded
For now, you can only choose the following model:
GCN-GRU
: GCN_GRU_run.pyGCN-GRU (sparse)
: GCN_GRU_sparse.pyI will upload the other baseline models later.
If you have any question, please feel free to contact me. Email is good for me.
Please cite our paper if you use this code in your own work:
@inproceedings{zhao2018deep,
title={Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data},
author={Zhao, Xujiang and Chen, Feng and Cho, Jin-Hee},
booktitle={2018 IEEE International Conference on Big Data (Big Data)},
pages={1150--1155},
year={2018},
organization={IEEE}
}