Hu, Zhiwei, Gutiérrez-Basulto, Víctor  ORCID: https://orcid.org/0000-0002-6117-5459, Xiang, Zhiliang ORCID: https://orcid.org/0000-0002-0263-7289, Li, Ru and Pan, Jeff Z.
2026.
COTET: Cross-view optimal transport for knowledge graph entity typing.
Neurocomputing
706
, 135053.
10.1016/j.neucom.2026.135053
|
Abstract
Knowledge graph entity typing (KGET) aims to infer missing entity type instances in knowledge graphs. Previous research has predominantly centered around leveraging contextual information associated with entities, which provides valuable clues for inference. However, it has long ignored the dual nature of information inherent in entities, encompassing both high-level coarse-grained cluster knowledge and fine-grained type knowledge. This paper introduces Cross-view Optimal Transport for knowledge graph Entity Typing (COTET), a method that effectively incorporates the information on how types are clustered into the representations of entities and types. COTET comprises three modules: i) Multi-view Generation and Encoder, which captures structured knowledge at different levels of granularity through entity-type, entity-cluster, and type-cluster-type perspectives; ii) Cross-view Optimal Transport, which transports view-specific embeddings to a unified space by minimizing the Wasserstein distance from a distributional alignment perspective; iii) Pooling-based Entity Typing Prediction, which employs a mixture pooling mechanism to aggregate prediction scores from diverse neighbors of an entity. Additionally, we introduce a distribution-based loss function to mitigate the occurrence of false negatives during training. Extensive experiments demonstrate the effectiveness of COTET when compared to existing baselines. Datasets and code are available at the following website: https://github.com/zhiweihu1103/ET-COTET.
| Item Type: | Article |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Computational & Mathematical Sciences Schools > Computer Science & Informatics |
| Publisher: | Elsevier |
| ISSN: | 0925-2312 |
| Date of Acceptance: | 7 September 2026 |
| Last Modified: | 15 Sep 2026 11:00 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/189610 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions