DIVINE

Code and models for the paper DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning

We present a novel plug-and-play framework based on GAIL (Ho and Ermon, 2016) for enhancing existing RL-based methods, which is referred to as DIVINE for “Deep Inference via Imitating Non-human Experts”.

Citation

If you use this code, please cite our paper

@inproceedings{li-cheng-2019-divine,
    title = "{DIVINE}: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning",
    author = "Li, Ruiping and Cheng, Xiang",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D19-1266",
    doi = "10.18653/v1/D19-1266",
    pages = "2642--2651"
}