Eureka: Neural Insight Learning for Knowledge Graph Reasoning

Alex X. Zhang, Xun Liang, Bo Wu, Xiangping Zheng, Sensen Zhang, Yuhui Guo, Jun Wang, Xinyao Liu


Abstract
The human recognition system has presented the remarkable ability to effortlessly learn novel knowledge from only a few trigger events based on prior knowledge, which is called insight learning. Mimicking such behavior on Knowledge Graph Reasoning (KGR) is an interesting and challenging research problem with many practical applications. Simultaneously, existing works, such as knowledge embedding and few-shot learning models, have been limited to conducting KGR in either “seen-to-seen” or “unseen-to-unseen” scenarios. To this end, we propose a neural insight learning framework named Eureka to bridge the “seen” to “unseen” gap. Eureka is empowered to learn the seen relations with sufficient training triples while providing the flexibility of learning unseen relations given only one trigger without sacrificing its performance on seen relations. Eureka meets our expectation of the model to acquire seen and unseen relations at no extra cost, and eliminate the need to retrain when encountering emerging unseen relations. Experimental results on two real-world datasets demonstrate that the proposed framework also outperforms various state-of-the-art baselines on datasets of both seen and unseen relations.
Anthology ID:
2022.coling-1.398
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4517–4527
Language:
URL:
https://aclanthology.org/2022.coling-1.398
DOI:
Bibkey:
Cite (ACL):
Alex X. Zhang, Xun Liang, Bo Wu, Xiangping Zheng, Sensen Zhang, Yuhui Guo, Jun Wang, and Xinyao Liu. 2022. Eureka: Neural Insight Learning for Knowledge Graph Reasoning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4517–4527, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Eureka: Neural Insight Learning for Knowledge Graph Reasoning (Zhang et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2022.coling-1.398.pdf