Probabilistic Graphical Models Parameter Learning with Transferred Prior and Constraints

Yun Zhou Queen Mary University of Londo, Norman Fenton Queen Mary University of London, Timothy Hospedales Queen Mary University of London, Martin Neil Queen Mary University of London
Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, PMLR R13:576-585, 2015.

Abstract

Learning accurate Bayesian networks (BNs) is a key challenge in real-world applications, especially when training data are hard to acquire. Two approaches have been used to address this challenge: 1) introducing expert judgements and 2) transferring knowledge from related domains. This is the first paper to present a generic framework that combines both approaches to improve BN parameter learning. This framework is built upon an extended multinomial parameter learning model, that itself is an auxiliary BN. It serves to integrate both knowledge transfer and expert constraints. Experimental results demonstrate improved accuracy of the new method on a variety of benchmark BNs, showing its potential to benefit many real-world problems.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR13-londo15a, title = {Probabilistic Graphical Models Parameter Learning with Transferred Prior and Constraints}, author = {Londo, Yun Zhou Queen Mary University of and London, Norman Fenton Queen Mary University of and London, Timothy Hospedales Queen Mary University of and London, Martin Neil Queen Mary University of}, booktitle = {Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence}, pages = {576--585}, year = {2015}, editor = {Meila, Marina and Heskes, Tom}, volume = {R13}, series = {Proceedings of Machine Learning Research}, month = {12--16 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r13/main/assets/londo15a/londo15a.pdf}, url = {https://proceedings.mlr.press/r13/londo15a.html}, abstract = {Learning accurate Bayesian networks (BNs) is a key challenge in real-world applications, especially when training data are hard to acquire. Two approaches have been used to address this challenge: 1) introducing expert judgements and 2) transferring knowledge from related domains. This is the first paper to present a generic framework that combines both approaches to improve BN parameter learning. This framework is built upon an extended multinomial parameter learning model, that itself is an auxiliary BN. It serves to integrate both knowledge transfer and expert constraints. Experimental results demonstrate improved accuracy of the new method on a variety of benchmark BNs, showing its potential to benefit many real-world problems.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Probabilistic Graphical Models Parameter Learning with Transferred Prior and Constraints %A Yun Zhou Queen Mary University of Londo %A Norman Fenton Queen Mary University of London %A Timothy Hospedales Queen Mary University of London %A Martin Neil Queen Mary University of London %B Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2015 %E Marina Meila %E Tom Heskes %F pmlr-vR13-londo15a %I PMLR %P 576--585 %U https://proceedings.mlr.press/r13/londo15a.html %V R13 %X Learning accurate Bayesian networks (BNs) is a key challenge in real-world applications, especially when training data are hard to acquire. Two approaches have been used to address this challenge: 1) introducing expert judgements and 2) transferring knowledge from related domains. This is the first paper to present a generic framework that combines both approaches to improve BN parameter learning. This framework is built upon an extended multinomial parameter learning model, that itself is an auxiliary BN. It serves to integrate both knowledge transfer and expert constraints. Experimental results demonstrate improved accuracy of the new method on a variety of benchmark BNs, showing its potential to benefit many real-world problems. %Z Reissued by PMLR on 04 October 2026.
APA
Londo, Y.Z.Q.M.U.o., London, N.F.Q.M.U.o., London, T.H.Q.M.U.o. & London, M.N.Q.M.U.o.. (2015). Probabilistic Graphical Models Parameter Learning with Transferred Prior and Constraints. Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R13:576-585 Available from https://proceedings.mlr.press/r13/londo15a.html. Reissued by PMLR on 04 October 2026.

Related Material