Ontological Concept Structure Aware Knowledge Transfer for Inductive Knowledge Graph Embedding

Ren, Chao; Zhang, Le; Fang, Lintao; Xu, Tong; Wang, Zhefeng; Yuan, Senchao; Chen, Enhong

doi:10.1109/ijcnn52387.2021.9533852

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. Using more powerful and expressive model to improve the performance of structure embedding representation of triples is worth further exploring [29]- [32]. Meanwhile, how to extract the semantic information of triples more effectively is challenging [33]- [37].…”

Section: Figurementioning

confidence: 99%

A Knowledge Graph Embedding Framework With Triple Semantics

et al. 2023

View full text Add to dashboard Cite

The knowledge graph embedding model aims to use low-dimensional real-valued vectors to represent the entities and relations in the triples, where operations such as link prediction and triple classification can be performed based on these representations. However, existing embedding models only consider the structural embedding of triples, while ignoring the semantic information of triples. This paper proposes a knowledge graph embedding learning framework combined with triple semantic information (KGSE). KGSE comprehensively considers the structural embedding and semantic embedding of triples, where semantic embedding is used as a supplement to improve the quality of embedding. Specifically, KGSE uses the improved TransD model to obtain the structural embedding of triples, and employs the deep convolutional neural model combined with an attention mechanism to obtain the semantic embedding of triples. In addition, a novel energy function is designed to jointly train the above two embeddings. Experimental results show that the proposed framework improves significantly compared with Trans-based models and other baseline models in link prediction and triple classification tasks, which verifies the effectiveness of the proposed framework.

show abstract

Section: Figurementioning

confidence: 99%

A Knowledge Graph Embedding Framework With Triple Semantics

et al. 2023

View full text Add to dashboard Cite

show abstract

“…SNRI (Xu et al, 2022) enhances the processing for sparse subgraphs by exploiting full neighbor relationships and by applying mutual information (MI) maximization to knowledge graphs. Ontology Enhanced Inference: Incorporating ontology information through various methods (Xie et al, 2016;Ren et al, 2021), it helps models learn richer semantic information. TransC (Lv et al, 2018) models the embedding of concepts as a sphere and assumes that the embedding corresponding to the entity belonging to the concept should be in this sphere.…”

Section: Related Workmentioning

confidence: 99%

Inductive Relation Inference of Knowledge Graph Enhanced by Ontology Information

Zhou,

Zhao,

Gui

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

The inductive inference of the knowledge graph aims to complete the potential relations between the new unknown entities in the graph. Most existing methods are based on entityindependent features such as graph structure information and relationship information to inference. However, the neighborhood of these new entities is often too sparse to obtain enough information to build these features effectively. In this work, we propose a knowledge graph inductive inference method that fuses ontology information. Based on the enclosing subgraph, we bring in feature embeddings of concepts corresponding to entities to learn the semantic information implicit in the ontology. Considering that the ontology information of entities may be missing, we build a type constraint regular loss to explicitly model the semantic connections between entities and concepts, and thus capture the missing concepts of entities. Experimental results show that our approach significantly outperforms large language models like ChatGPT on two benchmark datasets, YAGO21K-610 and DB45K-165, and improves the MRR metrics by 15.4% and 44.1%, respectively, when compared with the state-of-the-art methods.

show abstract