Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

11-2024

Abstract

Knowledge graphs (KGs) are instrumental in various real-world applications, yet they often suffer from incompleteness due to missing relations. To predict instances for novel relations with limited training examples, few-shot relation learning approaches have emerged, utilizing techniques such as meta-learning. However, the assumption is that novel relations in meta-testing and base relations in meta-training are independently and identically distributed, which may not hold in practice. To address the limitation, we propose RelAdapter, a context-aware adapter for few-shot relation learning in KGs designed to enhance the adaptation process in meta-learning. First, RelAdapter is equipped with a lightweight adapter module that facilitates relation-specific, tunable adaptation of meta-knowledge in a parameter-efficient manner. Second, RelAdapter is enriched with contextual information about the target relation, enabling enhanced adaptation to each distinct relation. Extensive experiments on three benchmark KGs validate the superiority of RelAdapter over state-of-the-art methods.

Keywords

Knowledge graphs, Few-shot relation learning, Meta-learning, Meta-training, Context-aware adapter

Discipline

Artificial Intelligence and Robotics | Computer Sciences

Areas of Excellence

Digital transformation

Publication

Proceedings of the 19th Conference on Empirical Methods in Natural Language Processing (EMNLP 2024) : Miami, Florida, USA, November 12-16

First Page

17525

Last Page

17537

Identifier

10.18653/v1/2024.emnlp-main.970

Publisher

Association for Computational Linguistics

City or Country

Miami, Florida

Comments

PDF provided by faculty

Additional URL

https://doi.org/10.18653/v1/2024.emnlp-main.970

Download

Share

COinS