Pavlovic, Aleksandar, Sallinger, Emanuel and Schockaert, Steven  ORCID: https://orcid.org/0000-0002-9256-2881
2025.
Faithful differentiable reasoning with reshuffled region-based embeddings.
Presented at: 22nd International Conference on Principles of Knowledge Representation and Reasoning (KR 2025),
Melbourne, Australia,
11-17 November 2025.
Proceedings of the 22nd International Conference on Principles of Knowledge Representation and Reasoning.
Proceedings of the Conference on Principles of Knowledge Representation and Reasoning.
International Joint Conferences on Artificial Intelligence Organization,
pp. 489-499.
10.24963/kr.2025/48
|
Preview |
PDF
- Accepted Post-Print Version
Download (338kB) | Preview |
Abstract
Knowledge graph (KG) embedding methods learn geometric representations of entities and relations to predict plausible missing knowledge. These representations are typically assumed to capture rule-like inference patterns. However, our theoretical understanding of which inference patterns can be captured remains limited. Ideally, KG embedding methods should be expressive enough such that for any set of rules, there exist relation embeddings that exactly capture these rules. This principle has been studied within the framework of region-based embeddings, but existing models are severely limited in the kinds of rule bases that can be captured. We argue that this stems from the fact that entity embeddings are only compared in a coordinate-wise fashion. As an alternative, we propose \modelName, a simple model based on ordering constraints that can faithfully capture a much larger class of rule bases than existing approaches. Most notably, RESHUFFLE can capture bounded inference w.r.t. arbitrary sets of closed path rules. The entity embeddings in our framework can be learned by a Graph Neural Network (GNN), which effectively acts as a differentiable rule base.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Publisher: | International Joint Conferences on Artificial Intelligence Organization |
| ISBN: | 978-1-956792-08-9 |
| ISSN: | 2334-1033 |
| Date of First Compliant Deposit: | 20 August 2025 |
| Date of Acceptance: | 10 July 2025 |
| Last Modified: | 20 Nov 2025 12:15 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/180578 |
Actions (repository staff only)
 |
Edit Item |
Altmetric
Altmetric