Hu, Zhiwei, Gutierrez Basulto, Victor  ORCID: https://orcid.org/0000-0002-6117-5459, Xiang, Zhiliang ORCID: https://orcid.org/0000-0002-0263-7289, Li, Ru and Pan, Jeff Z.
2023.
HyperFormer: Enhancing entity and relation interaction for hyper-relational knowledge graph completion.
Presented at: 32nd ACM International Conference on Information and Knowledge Management,
Birmingham, UK,
21-25 October 2023.
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management.
ACM,
pp. 803-812.
10.1145/3583780.3614922
|
Preview |
PDF
- Accepted Post-Print Version
Download (1MB) | Preview |
Abstract
Hyper-relational knowledge graphs (HKGs) extend standard knowledge graphs by associating attribute-value qualifiers to triples, which effectively represent additional fine-grained information about its associated triple. Hyper-relational knowledge graph completion (HKGC) aims at inferring unknown triples while considering its qualifiers. Most existing approaches to HKGC exploit a global-level graph structure to encode hyper-relational knowledge into the graph convolution message passing process. However, the addition of multi-hop information might bring noise into the triple prediction process. To address this problem, we propose HyperFormer, a model that considers local-level sequential information, which encodes the content of the entities, relations and qualifiers of a triple. More precisely, HyperFormer is composed of three different modules: an entity neighbor aggregator module allowing to integrate the information of the neighbors of an entity to capture different perspectives of it; a relation qualifier aggregator module to integrate hyper-relational knowledge into the corresponding relation to refine the representation of relational content; a convolution-based bidirectional interaction module based on a convolutional operation, capturing pairwise bidirectional interactions of entity-relation, entity-qualifier, and relation-qualifier. Furthermore, we introduce a Mixture-of-Experts strategy into the feed-forward layers of HyperFormer to strengthen its representation capabilities while reducing the amount of model parameters and computation. Extensive experiments on three well-known datasets with four different conditions demonstrate HyperFormer's effectiveness. Datasets and code are available at https://github.com/zhiweihu1103/HKGC-HyperFormer.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Computer Science & Informatics |
| Publisher: | ACM |
| ISBN: | 9798400701245 |
| Funders: | Leverhulme Trust |
| Date of First Compliant Deposit: | 15 August 2023 |
| Date of Acceptance: | 5 August 2023 |
| Last Modified: | 01 Jul 2025 10:47 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/161781 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions