Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion

TL;DR

This paper introduces a meta-learning framework that improves knowledge graph completion by effectively handling long-tailed relations and rare entities through few-shot learning, textual descriptions, and generative data augmentation.

Contribution

It proposes a novel meta-learning model that leverages textual descriptions and a generative approach to better predict infrequent relations and uncommon entities in knowledge graphs.

Findings

Outperforms previous methods on real-world datasets

Effectively handles infrequent relations and rare entities

Enhances training with generated triplets

Abstract

For large-scale knowledge graphs (KGs), recent research has been focusing on the large proportion of infrequent relations which have been ignored by previous studies. For example few-shot learning paradigm for relations has been investigated. In this work, we further advocate that handling uncommon entities is inevitable when dealing with infrequent relations. Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions. We design a novel model to better extract key information from textual descriptions. Besides, we also develop a novel generative model in our framework to enhance the performance by generating extra triplets during the training stage. Experiments are conducted on two datasets from real-world KGs, and the results show that our framework outperforms previous methods when dealing with infrequent relations and their accompanying uncommon entities.