Learning Query Adaptive Anchor Representation for Inductive Relation Prediction

Zhiwen Xie, Yi Zhang, Jin Liu, Guangyou Zhou, Jimmy Huang


Abstract
Relation prediction on knowledge graphs (KGs) attempts to infer the missing links between entities. Most previous studies are limited to the transductive setting where all entities must be seen during the training, making them unable to perform reasoning on emerging entities. Recently, the inductive setting is proposed to handle the entities in the test phase to be unseen during training, However, it suffers from the inefficient reasoning under the enclosing subgraph extraction issue and the lack of effective entity-independent feature modeling. To this end, we propose a novel Query Adaptive Anchor Representation (QAAR) model for inductive relation prediction. First, we extract one opening subgraph and perform reasoning by one time for all candidate triples, which is more efficient when the number of candidate triples is large. Second, we define some query adaptive anchors which are independent on any specific entity. Based on these anchors, we take advantage of the transferable entity-independent features (relation-aware, structure-aware and distance features) that can be used to produce entity embeddings for emerging unseen entities. Such entity-independent features is modeled by a query-aware graph attention network on the opening subgraph. Experimental results demonstrate that our proposed QAAR outperforms state-of-the-art baselines in inductive relation prediction task.
Anthology ID:
2023.findings-acl.882
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14041–14053
Language:
URL:
https://aclanthology.org/2023.findings-acl.882
DOI:
10.18653/v1/2023.findings-acl.882
Bibkey:
Cite (ACL):
Zhiwen Xie, Yi Zhang, Jin Liu, Guangyou Zhou, and Jimmy Huang. 2023. Learning Query Adaptive Anchor Representation for Inductive Relation Prediction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 14041–14053, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Learning Query Adaptive Anchor Representation for Inductive Relation Prediction (Xie et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.882.pdf