English

Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Artificial Intelligence 2022-07-05 v2 Machine Learning

Abstract

Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem as traditional subgraph matching methods are not capable to deal with noise and missing information. To address this problem, it has been recently introduced a promising approach based on jointly embedding logical queries and KGs into a low-dimensional space to identify answer entities. However, existing proposals ignore critical semantic knowledge inherently available in KGs, such as type information. To leverage type information, we propose a novel TypE-aware Message Passing (TEMP) model, which enhances the entity and relation representations in queries, and simultaneously improves generalization, deductive and inductive reasoning. Remarkably, TEMP is a plug-and-play model that can be easily incorporated into existing embedding-based models to improve their performance. Extensive experiments on three real-world datasets demonstrate TEMP's effectiveness.

Keywords

Cite

@article{arxiv.2205.00782,
  title  = {Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs},
  author = {Zhiwei Hu and Víctor Gutiérrez-Basulto and Zhiliang Xiang and Xiaoli Li and Ru Li and Jeff Z. Pan},
  journal= {arXiv preprint arXiv:2205.00782},
  year   = {2022}
}

Comments

Accepted to IJCAI-ECAI 2022

R2 v1 2026-06-24T11:04:31.942Z