This is the code of paper ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs. Zhanqiu Zhang, Jie Wang, Jiajun Chen, Shuiwang Ji, Feng Wu. NeurIPS 2021. [arXiv]

• Python 3.7
• PyTorch 1.7
• tqdm

1. Download the datasets here.
2. Move the zipped datasets to the root directory of ConE and run unzip -d data KG_data.zip.
3. Run the scripts in scripts.sh.

If you find this code useful, please consider citing the following paper.

@inproceedings{NEURIPS2021_QECONE,
 author = {Zhanqiu Zhang and Jie Wang and Jiajun Chen and Shuiwang Ji and Feng Wu},
 booktitle = {Advances in Neural Information Processing Systems},
 title = {ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs},
 year = {2021}
}

We refer to the code of KGReasoning. Thanks for their contributions.

If you are interested in our work, you may find the following papers useful.

Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion. Zhanqiu Zhang, Jianyu Cai, Jie Wang. NeurIPS 2020. [paper] [code]

Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction. Zhanqiu Zhang, Jianyu Cai, Yongdong Zhang, Jie Wang. AAAI 2020. [paper] [code]