Survey on Inductive Learning for Knowledge Graph Completion
Knowledge graph completion can make knowledge graph more complete. However, traditional knowledge graph completion methods assume that all test entities and relations appear in the training process. Due to the evolving nature of real world KG, once unseen entities or relations appear, the knowledge...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2023-11-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2303063.pdf |
| _version_ | 1797633152037945344 |
|---|---|
| author | LIANG Xinyu, SI Guannan, LI Jianxin, TIAN Pengxin, AN Zhaoliang, ZHOU Fengyu |
| author_facet | LIANG Xinyu, SI Guannan, LI Jianxin, TIAN Pengxin, AN Zhaoliang, ZHOU Fengyu |
| author_sort | LIANG Xinyu, SI Guannan, LI Jianxin, TIAN Pengxin, AN Zhaoliang, ZHOU Fengyu |
| collection | DOAJ |
| description | Knowledge graph completion can make knowledge graph more complete. However, traditional knowledge graph completion methods assume that all test entities and relations appear in the training process. Due to the evolving nature of real world KG, once unseen entities or relations appear, the knowledge graph needs to be retrained. Inductive learning for knowledge graph completion aims to complete triples containing unseen entities or unseen relations without training the knowledge graph from scratch, so it has received much attention in recent years. Firstly, starting from the basic concept of knowledge graph, this paper divides knowledge graph completion into two categories: transductive and inductive. Secondly, from the theoretical perspective of inductive knowledge graph completion, it is divided into two categories: semi-inductive and fully-inductive, and the models are summarized from this perspective. Then, from the technical perspective of inductive knowledge graph completion, it is divided into two categories: based on structural information and based on additional information. The methods based on structural information are subdivided into three categories: based on inductive embedding, based on logical rules and based on meta learning, and the methods based on additional information are subdivided into two categories: based on text information and other information. The current methods are further subdivided, analyzed and compared. Finally, it forecasts the main research directions in the future. |
| first_indexed | 2024-03-11T11:49:59Z |
| format | Article |
| id | doaj.art-a3301d575a0c4b01babc0913d37d25d3 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-03-11T11:49:59Z |
| publishDate | 2023-11-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-a3301d575a0c4b01babc0913d37d25d32023-11-09T08:18:08ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182023-11-0117112580260410.3778/j.issn.1673-9418.2303063Survey on Inductive Learning for Knowledge Graph CompletionLIANG Xinyu, SI Guannan, LI Jianxin, TIAN Pengxin, AN Zhaoliang, ZHOU Fengyu01. School of Information Science & Electrical Engineering, Shandong Jiaotong University, Jinan 250357, China 2. School of Control Science & Engineering, Shandong University, Jinan 250000, ChinaKnowledge graph completion can make knowledge graph more complete. However, traditional knowledge graph completion methods assume that all test entities and relations appear in the training process. Due to the evolving nature of real world KG, once unseen entities or relations appear, the knowledge graph needs to be retrained. Inductive learning for knowledge graph completion aims to complete triples containing unseen entities or unseen relations without training the knowledge graph from scratch, so it has received much attention in recent years. Firstly, starting from the basic concept of knowledge graph, this paper divides knowledge graph completion into two categories: transductive and inductive. Secondly, from the theoretical perspective of inductive knowledge graph completion, it is divided into two categories: semi-inductive and fully-inductive, and the models are summarized from this perspective. Then, from the technical perspective of inductive knowledge graph completion, it is divided into two categories: based on structural information and based on additional information. The methods based on structural information are subdivided into three categories: based on inductive embedding, based on logical rules and based on meta learning, and the methods based on additional information are subdivided into two categories: based on text information and other information. The current methods are further subdivided, analyzed and compared. Finally, it forecasts the main research directions in the future.http://fcst.ceaj.org/fileup/1673-9418/PDF/2303063.pdfknowledge graph; knowledge graph completion; inductive learning |
| spellingShingle | LIANG Xinyu, SI Guannan, LI Jianxin, TIAN Pengxin, AN Zhaoliang, ZHOU Fengyu Survey on Inductive Learning for Knowledge Graph Completion Jisuanji kexue yu tansuo knowledge graph; knowledge graph completion; inductive learning |
| title | Survey on Inductive Learning for Knowledge Graph Completion |
| title_full | Survey on Inductive Learning for Knowledge Graph Completion |
| title_fullStr | Survey on Inductive Learning for Knowledge Graph Completion |
| title_full_unstemmed | Survey on Inductive Learning for Knowledge Graph Completion |
| title_short | Survey on Inductive Learning for Knowledge Graph Completion |
| title_sort | survey on inductive learning for knowledge graph completion |
| topic | knowledge graph; knowledge graph completion; inductive learning |
| url | http://fcst.ceaj.org/fileup/1673-9418/PDF/2303063.pdf |
| work_keys_str_mv | AT liangxinyusiguannanlijianxintianpengxinanzhaoliangzhoufengyu surveyoninductivelearningforknowledgegraphcompletion |