Zhiliang Xiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zhiliang Xiang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Jeff Z. Pan
2 shared publications- Jeff Z. Pan
The University of Edinburgh, Edinburgh, United Kingdom
2 shared publications Ru Li
2 shared publications- Ru Li
Shanxi University Taiyuan China
2 shared publications Víctor Gutiérrez-Basulto
2 shared publications- Víctor Gutiérrez-Basulto
Cardiff University, Cardiff, United Kingdom
2 shared publications
Latest Publications
- 8 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 706
COTET: Cross-view optimal transport for knowledge graph entity typing
- 8 September 2026
- Published by Elsevier in Neurocomputing
- Vol. 706
COTET: Cross-view optimal transport for knowledge graph entity typing
- 12 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 676
Leveraging intra-modal and inter-modal interaction for multi-modal entity alignment
- 12 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 676
Leveraging intra-modal and inter-modal interaction for multi-modal entity alignment
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 979-990
Multi-level Mixture of Experts for Multimodal Entity Linking
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 979-990
Open AccessMulti-level Mixture of Experts for Multimodal Entity Linking
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 803-812
HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion
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.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 803-812
Open AccessHyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion
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.