Deep Learning with Logical Constraints

Abstract

In recent years, there has been an increasing interest in exploiting logically specified background knowledge in order to obtain neural models (i) with a better performance, (ii) able to learn from less data, and/or (iii) guaranteed to be compliant with the background knowledge itself, e.g., for safety-critical applications. In this survey, we retrace such works and categorize them based on (i) the logical language that they use to express the background knowledge and (ii) the goals that they achieve.

Cite

Text

Giunchiglia et al. "Deep Learning with Logical Constraints." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/767

Markdown

[Giunchiglia et al. "Deep Learning with Logical Constraints." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/giunchiglia2022ijcai-deep/) doi:10.24963/IJCAI.2022/767

BibTeX

@inproceedings{giunchiglia2022ijcai-deep,
  title     = {{Deep Learning with Logical Constraints}},
  author    = {Giunchiglia, Eleonora and Stoian, Mihaela Catalina and Lukasiewicz, Thomas},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {5478-5485},
  doi       = {10.24963/IJCAI.2022/767},
  url       = {https://mlanthology.org/ijcai/2022/giunchiglia2022ijcai-deep/}
}