Conformalized answer set prediction for knowledge graph embedding

Zhu, Yuqicheng, Potyka, Nico, Pan, Jiarong, Xiong, Bo, He, Yunjie, Kharlamov, Evgeny and Staab, Steffen 2025. Conformalized answer set prediction for knowledge graph embedding. Presented at: 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, Albuquerque, New Mexico, 29 April - 4 May 2025. Proceedings Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. , vol.1 ACL, pp. 731-750.

Full text not available from this repository.

Abstract

Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking all potential answers, but rankings often lack a meaningful probabilistic interpretation - lower-ranked answers do not necessarily have a lower probability of being true. This limitation makes it difficult to quantify uncertainty of model's predictions, posing challenges for the application of KGE methods in high-stakes domains like medicine. We address this issue by applying the theory of conformal prediction that allows generating answer sets, which contain the correct answer with probabilistic guarantees. We explain how conformal prediction can be used to generate such answer sets for link prediction tasks. Our empirical evaluation on four benchmark datasets using six representative KGE methods validates that the generated answer sets satisfy the probabilistic guarantees given by the theory of conformal prediction. We also demonstrate that the generated answer sets often have a sensible size and that the size adapts well with respect to the difficulty of the query.

Item Type:	Conference or Workshop Item (Paper)
Status:	Published
Schools:	Schools > Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher:	ACL
Last Modified:	23 Sep 2025 11:15
URI:	https://orca.cardiff.ac.uk/id/eprint/178820

Actions (repository staff only)

Edit Item