Capturing knowledge graphs and rules with octagon embeddings

Charpenay, Victor and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2024. Capturing knowledge graphs and rules with octagon embeddings. Presented at: 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024), Jeju, South Korea, 3-9 August 2024. Published in: Larson, Kate ed. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. pp. 3289-3297. 10.24963/ijcai.2024/364

Preview

PDF - Accepted Post-Print Version Download (425kB) | Preview

Abstract

Region based knowledge graph embeddings represent relations as geometric regions. This has the advantage that the rules which are captured by the model are made explicit, making it straightforward to incorporate prior knowledge and to inspect learned models. Unfortunately, existing approaches are severely restricted in their ability to model relational composition, and hence also their ability to model rules, thus failing to deliver on the main promise of region based models. With the aim of addressing these limitations, we investigate regions which are composed of axis-aligned octagons. Such octagons are particularly easy to work with, as intersections and compositions can be straightforwardly computed, while they are still sufficiently expressive to model arbitrary knowledge graphs. Among others, we also show that our octagon embeddings can properly capture a non-trivial class of rule bases. Finally, we show that our model achieves competitive experimental results.

Item Type:	Conference or Workshop Item (Paper)
Status:	Published
Schools:	Computer Science & Informatics
ISBN:	9781956792041
Date of First Compliant Deposit:	20 May 2024
Date of Acceptance:	16 April 2024
Last Modified:	21 Aug 2024 13:15
URI:	https://orca.cardiff.ac.uk/id/eprint/169048

Actions (repository staff only)

Edit Item