DomiKnowS is a Python library that facilitates the integration of domain knowledge in deep learning architectures. With DomiKnowS, you can express the structure of your data symbolically via graph declarations and seamlessly add logical constraints over outputs or latent variables to your deep models. This allows you to define domain knowledge explicitly, improving your models' explainability, performance, and generalizability, especially in low-data regimes.
While several approaches for integrating symbolic and sub-symbolic models have been introduced, no generic library facilitates programming for such integration with various underlying algorithms. DomiKnowS aims to simplify the programming for knowledge integration in training and inference phases while separating the knowledge representation from learning algorithms.
DomiKnowS is developed and maintained by HLR. We would like to acknowledge the contributions of the open-source community and express our gratitude to the developers of Gurobi for their excellent optimization solver.
If you use DomiKnowS in your research or work, please cite our paper:
@inproceedings{rajaby-faghihi-etal-2021-domiknows,
title = "{D}omi{K}now{S}: A Library for Integration of Symbolic Domain Knowledge in Deep Learning",
author = "Rajaby Faghihi, Hossein and
Guo, Quan and
Uszok, Andrzej and
Nafar, Aliakbar and
Kordjamshidi, Parisa",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-demo.27",
doi = "10.18653/v1/2021.emnlp-demo.27",
pages = "231--241",
}