Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs
This work addresses the challenge of handling noise and missing information in knowledge graphs for applications like question answering and recommendation systems, representing an incremental improvement over existing embedding-based methods.
The paper tackles the problem of multi-hop reasoning over knowledge graphs by proposing a type-aware embedding model that leverages semantic type information to enhance entity and relation representations, achieving improved performance on three real-world datasets.
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.