PAC-reasoning in relational domains

Kuzelka, Ondrej, Wang, Yuyi, Davis, Jesse and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2018. PAC-reasoning in relational domains. Presented at: UAI2018: 34th Conference on Uncertainty in Artificial Intelligence, Monterey, CA, USA, 6-10 August 2018. Proceedings of the Thirty-Fourth Conference (2018). AUAI Press, 927 - 936. 10.48550/arXiv.1803.05768

Preview

PDF - Accepted Post-Print Version Download (331kB) | Preview

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.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Completion
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	AUAI Press
ISBN:	978-1-5108-7160-1
Related URLs:	Organisation
Date of First Compliant Deposit:	23 July 2018
Last Modified:	04 Sep 2025 10:45
URI:	https://orca.cardiff.ac.uk/id/eprint/113239

Citation Data

Cited 4 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item