@article{Lu2023, 
author = {Xinyu Lu and Lifang Wang and Zejun Jiang and Shizhong Liu and Jiashi Lin},
title = {PEJL: A path-enhanced joint learning approach for knowledge graph completion},
year = {2023},
journal = {AIMS Mathematics},
volume = {8},
number = {9},
pages = {20966-20988},
keywords = {knowledge graph completion, knowledge graphs, path, triples, multi-hop components},
url = {https://www.sciopen.com/article/10.3934/math.20231067},
doi = {10.3934/math.20231067},
abstract = {Knowledge graphs (KGs) often suffer from incompleteness. Knowledge graph completion (KGC) is proposed to complete missing components in a KG. Most KGC methods focus on direct relations and fail to leverage rich semantic information in multi-hop paths. In contrast, path-based embedding methods can capture path information and utilize extra semantics to improve KGC. However, most path-based methods cannot take advantage of full multi-hop information and neglect to capture multiple semantic associations between single and multi-hop triples. To bridge the gap, we propose a novel path-enhanced joint learning approach called PEJL for KGC. Rather than learning multi-hop representations, PEJL can recover multi-hop embeddings by encoding full multi-hop components. Meanwhile, PEJL extends the definition of translation energy functions and generates new semantic representations for each multi-hop component, which is rarely considered in path-based methods. Specifically, we first use the path constraint resource allocation (PCRA) algorithm to extract multi-hop triples. Then we use an embedding recovering module consisting of a bidirectional gated recurrent unit (GRU) layer and a fully connected layer to obtain multi-hop embeddings. Next, we employ a KG modeling module to leverage various semantic information and model the whole knowledge graph based on translation methods. Finally, we define a joint learning approach to train our proposed PEJL. We evaluate our model on two KGC datasets: FB15K-237 and NELL-995. Experiments show the effectiveness and superiority of PEJL.}
}