PEJL: A path-enhanced joint learning approach for knowledge graph completion
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 ca...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-06-01
|
| Series: | AIMS Mathematics |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/math.20231067?viewType=HTML |
| _version_ | 1797778470129893376 |
|---|---|
| author | Xinyu Lu Lifang Wang Zejun Jiang Shizhong Liu Jiashi Lin |
| author_facet | Xinyu Lu Lifang Wang Zejun Jiang Shizhong Liu Jiashi Lin |
| author_sort | Xinyu Lu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-12T23:17:45Z |
| format | Article |
| id | doaj.art-d30c325e760e48638b8093743fa10279 |
| institution | Directory Open Access Journal |
| issn | 2473-6988 |
| language | English |
| last_indexed | 2024-03-12T23:17:45Z |
| publishDate | 2023-06-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Mathematics |
| spelling | doaj.art-d30c325e760e48638b8093743fa102792023-07-17T01:22:45ZengAIMS PressAIMS Mathematics2473-69882023-06-0189209662098810.3934/math.20231067PEJL: A path-enhanced joint learning approach for knowledge graph completionXinyu Lu0Lifang Wang1Zejun Jiang2Shizhong Liu3Jiashi Lin4School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China, 710072School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China, 710072School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China, 710072School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China, 710072School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China, 710072Knowledge 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.https://www.aimspress.com/article/doi/10.3934/math.20231067?viewType=HTMLknowledge graph completionknowledge graphspathtriplesmulti-hop components |
| spellingShingle | Xinyu Lu Lifang Wang Zejun Jiang Shizhong Liu Jiashi Lin PEJL: A path-enhanced joint learning approach for knowledge graph completion AIMS Mathematics knowledge graph completion knowledge graphs path triples multi-hop components |
| title | PEJL: A path-enhanced joint learning approach for knowledge graph completion |
| title_full | PEJL: A path-enhanced joint learning approach for knowledge graph completion |
| title_fullStr | PEJL: A path-enhanced joint learning approach for knowledge graph completion |
| title_full_unstemmed | PEJL: A path-enhanced joint learning approach for knowledge graph completion |
| title_short | PEJL: A path-enhanced joint learning approach for knowledge graph completion |
| title_sort | pejl a path enhanced joint learning approach for knowledge graph completion |
| topic | knowledge graph completion knowledge graphs path triples multi-hop components |
| url | https://www.aimspress.com/article/doi/10.3934/math.20231067?viewType=HTML |
| work_keys_str_mv | AT xinyulu pejlapathenhancedjointlearningapproachforknowledgegraphcompletion AT lifangwang pejlapathenhancedjointlearningapproachforknowledgegraphcompletion AT zejunjiang pejlapathenhancedjointlearningapproachforknowledgegraphcompletion AT shizhongliu pejlapathenhancedjointlearningapproachforknowledgegraphcompletion AT jiashilin pejlapathenhancedjointlearningapproachforknowledgegraphcompletion |