Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
This work addresses a specific challenge in knowledge graph completion for researchers and practitioners, representing an incremental advancement in handling long-tailed data.
The paper tackles the problem of infrequent relations and uncommon entities in knowledge graph completion by proposing a meta-learning framework that uses textual descriptions and generative triplet augmentation, achieving improved performance over previous methods on two real-world datasets.
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.