@inproceedings{d272f5c2367947109027342debb6e7cb,
title = "Contrastive Language-Entity Pre-training for Richer Knowledge Graph Embedding",
abstract = "In this work we propose a pretraining procedure that aligns a graph encoder and a text encoder to learn a common multi-modal graph-text embedding space. The alignment is obtained by training a model to predict the correct associations between Knowledge Graph nodes and their corresponding descriptions. We test the procedure with two popular Knowledge Bases: Wikidata (formerly Freebase) and YAGO. Our results indicate that such a pretraining method allows for link prediction without the need for additional fine-tuning. Furthermore, we demonstrate that a graph encoder pretrained on the description matching task allows for improved link prediction performance after fine-tuning, without the need for providing node descriptions as additional inputs. We make available the code used in the experiments on GitHub(https://github.com/BrunoLiegiBastonLiegi/CLEP) under the MIT license to encourage further work.",
keywords = "Knowledge Graphs, Multi-modal Learning",
author = "Andrea Papaluca and Daniel Krefl and Artem Lensky and Hanna Suominen",
note = "{\textcopyright} 2025 The Editor(s) (if applicable) and The Author(s); 4th International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2024 ; Conference date: 03-07-2024 Through 06-07-2024",
year = "2025",
doi = "10.1007/978-981-97-8702-9\_16",
language = "English",
isbn = "9789819787012",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science+Business Media B.V.",
pages = "233--246",
editor = "Christian Wallraven and Cheng-Lin Liu and Arun Ross",
booktitle = "Pattern Recognition and Artificial Intelligence - 4th International Conference, ICPRAI 2024, Proceedings",
address = "Netherlands",
}