Hu, Zhiwei, Gutierrez Basulto, Victor ![]() |
Preview |
PDF
- Accepted Post-Print Version
Download (2MB) | Preview |
Abstract
Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem as traditional subgraph matching methods are not capable to deal with noise and missing information. To address this problem, it has been recently introduced a promising approach based on jointly embedding logical queries and KGs into a low-dimensional space to identify answer entities. However, existing proposals ignore critical semantic knowledge inherently available in KGs, such as type information. To leverage type information, we propose a novel TypE-aware Message Passing (TEMP) model, which enhances the entity and relation representations in queries, and simultaneously improves generalization, deductive and inductive reasoning. Remarkably, TEMP is a plug-and-play model that can be easily incorporated into existing embedding-based models to improve their performance. Extensive experiments on three real-world datasets demonstrate TEMP’s effectiveness.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Completion |
Status: | Unpublished |
Schools: | Computer Science & Informatics |
Funders: | Leverhulme Trust Research Project Grant (RPG-2021-140) |
Date of First Compliant Deposit: | 6 May 2022 |
Last Modified: | 30 Nov 2022 07:42 |
URI: | https://orca.cardiff.ac.uk/id/eprint/149582 |
Actions (repository staff only)
![]() |
Edit Item |