Tractable Explanations for D-DNNF Classifiers
Abstract
Compilation into propositional languages finds a growing number of practical uses, including in constraint programming, diagnosis and machine learning (ML), among others. One concrete example is the use of propositional languages as classifiers, and one natural question is how to explain the predictions made. This paper shows that for classifiers represented with some of the best-known propositional languages, different kinds of explanations can be computed in polynomial time. These languages include deterministic decomposable negation normal form (d-DNNF), and so any propositional language that is strictly less succinct than d-DNNF. Furthermore, the paper describes optimizations, specific to Sentential Decision Diagrams (SDDs), which are shown to yield more efficient algorithms in practice.
Cite
Text
Huang et al. "Tractable Explanations for D-DNNF Classifiers." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I5.20514Markdown
[Huang et al. "Tractable Explanations for D-DNNF Classifiers." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/huang2022aaai-tractable/) doi:10.1609/AAAI.V36I5.20514BibTeX
@inproceedings{huang2022aaai-tractable,
title = {{Tractable Explanations for D-DNNF Classifiers}},
author = {Huang, Xuanxiang and Izza, Yacine and Ignatiev, Alexey and Cooper, Martin C. and Asher, Nicholas and Marques-Silva, João},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {5719-5728},
doi = {10.1609/AAAI.V36I5.20514},
url = {https://mlanthology.org/aaai/2022/huang2022aaai-tractable/}
}