PAC-Reasoning in Relational Domains

Ondrej Kuzelka, Yuyi Wang, Jesse Davis, Steven Schockaert
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:926-935, 2018.

Abstract

We consider the problem of predicting plausible missing facts in relational data, given a set of imperfect logical rules. In particular, our aim is to provide bounds on the (expected) number of incorrect inferences that are made in this way. Since for classical inference it is in general impossible to bound this number in a non-trivial way, we consider two inference relations that weaken, but remain close in spirit to classical inference.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-kuzelka18a, title = {{PAC}-Reasoning in Relational Domains}, author = {Kuzelka, Ondrej and Wang, Yuyi and Davis, Jesse and Schockaert, Steven}, booktitle = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {926--935}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/kuzelka18a/kuzelka18a.pdf}, url = {https://proceedings.mlr.press/r16/kuzelka18a.html}, abstract = {We consider the problem of predicting plausible missing facts in relational data, given a set of imperfect logical rules. In particular, our aim is to provide bounds on the (expected) number of incorrect inferences that are made in this way. Since for classical inference it is in general impossible to bound this number in a non-trivial way, we consider two inference relations that weaken, but remain close in spirit to classical inference.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T PAC-Reasoning in Relational Domains %A Ondrej Kuzelka %A Yuyi Wang %A Jesse Davis %A Steven Schockaert %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-kuzelka18a %I PMLR %P 926--935 %U https://proceedings.mlr.press/r16/kuzelka18a.html %V R16 %X We consider the problem of predicting plausible missing facts in relational data, given a set of imperfect logical rules. In particular, our aim is to provide bounds on the (expected) number of incorrect inferences that are made in this way. Since for classical inference it is in general impossible to bound this number in a non-trivial way, we consider two inference relations that weaken, but remain close in spirit to classical inference. %Z Reissued by PMLR on 04 October 2026.
APA
Kuzelka, O., Wang, Y., Davis, J. & Schockaert, S.. (2018). PAC-Reasoning in Relational Domains. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:926-935 Available from https://proceedings.mlr.press/r16/kuzelka18a.html. Reissued by PMLR on 04 October 2026.

Related Material