Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding

Qi, Zhiyuan; Zhang, Ziheng; Chen, Jiaoyan; Chen, Xi; Xiang, Yuejia; Zhang, Ningyu; Zheng, Yefeng

doi:10.24963/ijcai.2021/278

Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding

Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yuejia Xiang, Ningyu Zhang, Yefeng Zheng

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 2019-2025.

https://doi.org/10.24963/ijcai.2021/278

Keywords

Knowledge Representation and Reasoning: Semantic Web
Knowledge Representation and Reasoning: Leveraging Knowledge and Learning

Abstract

Knowledge Graph (KG) alignment is to discover the mappings (i.e., equivalent entities, relations, and others) between two KGs. The existing methods can be divided into the embedding-based models, and the conventional reasoning and lexical matching based systems. The former compute the similarity of entities via their cross-KG embeddings, but they usually rely on an ideal supervised learning setting for good performance and lack appropriate reasoning to avoid logically wrong mappings; while the latter address the reasoning issue but are poor at utilizing the KG graph structures and the entity contexts. In this study, we aim at combining the above two solutions and thus propose an iterative framework named PRASE which is based on probabilistic reasoning and semantic embedding. It learns the KG embeddings via entity mappings from a probabilistic reasoning system named PARIS, and feeds the resultant entity mappings and embeddings back into PARIS for augmentation. The PRASE framework is compatible with different embedding-based models, and our experiments on multiple datasets have demonstrated its state-of-the-art performance.

Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yuejia Xiang, Ningyu Zhang, and Yefeng Zheng. 2021. Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 2019–2025. https://doi.org/10.24963/ijcai.2021/278

@inproceedings{ijcai2021p278,
  title     = {Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding},
  author    = {Qi, Zhiyuan and Zhang, Ziheng and Chen, Jiaoyan and Chen, Xi and Xiang, Yuejia and Zhang, Ningyu and Zheng, Yefeng},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {2019--2025},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/278},
  url       = {https://doi.org/10.24963/ijcai.2021/278},
}

TY  - CPAPER
TI  - Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding
AU  - Qi, Zhiyuan
AU  - Zhang, Ziheng
AU  - Chen, Jiaoyan
AU  - Chen, Xi
AU  - Xiang, Yuejia
AU  - Zhang, Ningyu
AU  - Zheng, Yefeng
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 2019
EP  - 2025
DO  - 10.24963/ijcai.2021/278
UR  - https://doi.org/10.24963/ijcai.2021/278
ER  -