Semantic Interaction Matching Network for Few-Shot Knowledge Graph Completion

This repository is the official implementation for the paper titled "Semantic Interaction Matching Network for Few-Shot Knowledge Graph Completion".

Usage

Step 1: Set up the environment

We recommend using Conda to manage virtual environments, and we use Python version 3.8.12.

conda create -n sim python==3.8.12
conda activate sim

Please install the specified versions of Python libraries according to the requirements.txt file.

Step 2: Download the data

• Wiki-One
• NELL-One

Step 3: Modify the data path

Please modify the dataset parameter in the run_nell_all_fold.sh and run_wiki_all_fold.sh script to the path where you have stored the data.

Step 4: Start the training

Now you can execute bash run_<dataset>_all_fold.sh to begin the training.

bash run_nell_all_fold.sh
bash run_wiki_all_fold.sh

Citation

If you find this project useful in your research, please cite the following paper:

@artical{luo2023semantic,
    author = {Luo, Pengfei and Zhu, Xi and Xu, Tong and Zheng, Yi and Chen, Enhong},
    title = {Semantic Interaction Matching Network for Few-Shot Knowledge Graph Completion},
    year = {2023},
    publisher = {Association for Computing Machinery},
    journal = {ACM Trans. Web}
}

Contact Information

If you have any questions, please contact pfluo@mail.ustc.edu.cn.