Beyond Link Prediction: On Pre-Training Knowledge Graph Embeddings

Daniel Ruffinelli, Rainer Gemulla


Abstract
Knowledge graph embeddings (KGEs) provide low-dimensional representations of the entities and relations in a knowledge graph (KG) in order to reason about the KG and to inject structured knowledge into various downstream applications. Most prior work, however, focuses almost exclusively on training and evaluating KGE models for the task of link prediction. In this work, we explore KGE models as general-purpose representations of KGs and study their suitability (i) for more generally capturing properties of the KG and (ii) for downstream tasks such as entity classification and regression. For (i), we designed a new set of graph-structure prediction tasks to assess whether models capture different structures in the graph. For (ii), we investigate whether models provide useful features for a variety of downstream tasks. We found that strong link prediction performance was neither an indication that models generally capture patterns in the graph, nor that they were more useful in downstream tasks. As a result, we included our proposed graph-structure prediction tasks as additional training objectives and found that models trained with this multi-task approach generally, but not always, performed better at both graph-structure prediction and downstream tasks. However, the most suitable choice of pre-training tasks varies across KGE models and types of downstream tasks, suggesting opportunities for more research into the relation between pre-training KGE models and their usability on downstream applications.
Anthology ID:
2024.repl4nlp-1.11
Volume:
Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Chen Zhao, Marius Mosbach, Pepa Atanasova, Seraphina Goldfarb-Tarrent, Peter Hase, Arian Hosseini, Maha Elbayad, Sandro Pezzelle, Maximilian Mozes
Venues:
RepL4NLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
136–162
Language:
URL:
https://aclanthology.org/2024.repl4nlp-1.11
DOI:
Bibkey:
Cite (ACL):
Daniel Ruffinelli and Rainer Gemulla. 2024. Beyond Link Prediction: On Pre-Training Knowledge Graph Embeddings. In Proceedings of the 9th Workshop on Representation Learning for NLP (RepL4NLP-2024), pages 136–162, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Beyond Link Prediction: On Pre-Training Knowledge Graph Embeddings (Ruffinelli & Gemulla, RepL4NLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.repl4nlp-1.11.pdf