TransD-based Multi-hop Meta Learning for Few-shot Knowledge Graph Completion

Jindi Li, Kui Yu, Yuling Li, Yuhong ZhangIJCNN 2023 · OpenReview

Abstract

Few-shot knowledge graph completion (FKGC), which aims to infer missing facts about a relation from only a few reference triples, has recently attracted great attention. The core of solving the FKGC task is to learn a vector representation for each few-shot relation using the corresponding entity represen-tations. To this end, existing models generally enhance entity representations with their direct neighbors. However, a large number of entities have few direct neighbors. Hence, encoding only direct neighborhood is insufficient to obtain satisfactory en-tity representations. In addition, current models typically utilize static embeddings to represent entities, ignoring their diverse semantics, i.e., an entity may show distinct semantics within different few-shot relations. To address these issues, we propose a new FKGC framework, namely TransD-based Multi-hop Meta Learning (TDML). TDML consists of three main components: a multi-hop neighbor encoder to enhance entity representations by aggregating heterogeneous multi-hop neighbors, a transformer encoder to generate the relation meta representations, and a TransD-based relation representation updater that allows each entity to exhibit relation-specific semantics and tune the relation meta representations. Extensive experiments on two public datasets demonstrate that our model outperforms state-of-the-art FKGC methods.
BibTeX
@inproceedings{li2023transd,
  author = {Jindi Li and Kui Yu and Yuling Li and Yuhong Zhang},
  title = {{TransD-based Multi-hop Meta Learning for Few-shot Knowledge Graph Completion}},
  booktitle = {IJCNN},
  year = {2023},
  url = {https://openreview.net/forum?id=GhDCSIB5qr},
}

Loading related content...

Figure