Domain Knowledge Uncertainty and Probabilistic Parameter Constraints
Abstract
Incorporating domain knowledge into the modeling process is an effective way to improve learning accuracy. However, as it is provided by humans, domain knowledge can only be specified with some degree of uncertainty. We propose to explicitly model such uncertainty through probabilistic constraints over the parameter space. In contrast to hard parameter constraints, our approach is effective also when the domain knowledge is inaccurate and generally results in superior modeling accuracy. We focus on generative and conditional modeling where the parameters are assigned a Dirichlet or Gaussian prior and demonstrate the framework with experiments on both synthetic and real-world data.
Cite
Text
Mao and Lebanon. "Domain Knowledge Uncertainty and Probabilistic Parameter Constraints." Conference on Uncertainty in Artificial Intelligence, 2009.Markdown
[Mao and Lebanon. "Domain Knowledge Uncertainty and Probabilistic Parameter Constraints." Conference on Uncertainty in Artificial Intelligence, 2009.](https://mlanthology.org/uai/2009/mao2009uai-domain/)BibTeX
@inproceedings{mao2009uai-domain,
title = {{Domain Knowledge Uncertainty and Probabilistic Parameter Constraints}},
author = {Mao, Yi and Lebanon, Guy},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2009},
pages = {375-382},
url = {https://mlanthology.org/uai/2009/mao2009uai-domain/}
}