Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules
Knowledge graphs (KGs) play a crucial role in many applications, such as question answering, but incompleteness is an urgent issue for their broad application. Much research in knowledge graph completion (KGC) has been performed to resolve this issue. The methods of KGC can be classified into two ma...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/19/10660 |
_version_ | 1797576284053700608 |
---|---|
author | Yinyu Lan Shizhu He Kang Liu Jun Zhao |
author_facet | Yinyu Lan Shizhu He Kang Liu Jun Zhao |
author_sort | Yinyu Lan |
collection | DOAJ |
description | Knowledge graphs (KGs) play a crucial role in many applications, such as question answering, but incompleteness is an urgent issue for their broad application. Much research in knowledge graph completion (KGC) has been performed to resolve this issue. The methods of KGC can be classified into two major categories: rule-based reasoning and embedding-based reasoning. The former has high accuracy and good interpretability, but a major challenge is to obtain effective rules on large-scale KGs. The latter has good efficiency and scalability, but it relies heavily on data richness and cannot fully use domain knowledge in the form of logical rules. We propose a novel method that injects rules and learns representations iteratively to take full advantage of rules and embeddings. Specifically, we model the conclusions of rule groundings as 0–1 variables and use a rule confidence regularizer to remove the uncertainty of the conclusions. The proposed approach has the following advantages: (1) It combines the benefits of both rules and knowledge graph embeddings (KGEs) and achieves a good balance between efficiency and scalability. (2) It uses an iterative method to continuously improve KGEs and remove incorrect rule conclusions. Evaluations of two public datasets show that our method outperforms the current state-of-the-art methods, improving performance by 2.7% and 4.3% in mean reciprocal rank (MRR). |
first_indexed | 2024-03-10T21:50:03Z |
format | Article |
id | doaj.art-e65e35e84f444bcfb9a4fda444c9ba26 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T21:50:03Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-e65e35e84f444bcfb9a4fda444c9ba262023-11-19T14:02:26ZengMDPI AGApplied Sciences2076-34172023-09-0113191066010.3390/app131910660Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft RulesYinyu Lan0Shizhu He1Kang Liu2Jun Zhao3Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaInstitute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaKnowledge graphs (KGs) play a crucial role in many applications, such as question answering, but incompleteness is an urgent issue for their broad application. Much research in knowledge graph completion (KGC) has been performed to resolve this issue. The methods of KGC can be classified into two major categories: rule-based reasoning and embedding-based reasoning. The former has high accuracy and good interpretability, but a major challenge is to obtain effective rules on large-scale KGs. The latter has good efficiency and scalability, but it relies heavily on data richness and cannot fully use domain knowledge in the form of logical rules. We propose a novel method that injects rules and learns representations iteratively to take full advantage of rules and embeddings. Specifically, we model the conclusions of rule groundings as 0–1 variables and use a rule confidence regularizer to remove the uncertainty of the conclusions. The proposed approach has the following advantages: (1) It combines the benefits of both rules and knowledge graph embeddings (KGEs) and achieves a good balance between efficiency and scalability. (2) It uses an iterative method to continuously improve KGEs and remove incorrect rule conclusions. Evaluations of two public datasets show that our method outperforms the current state-of-the-art methods, improving performance by 2.7% and 4.3% in mean reciprocal rank (MRR).https://www.mdpi.com/2076-3417/13/19/10660distributed representationknowledge graphlink predictionlogical rule |
spellingShingle | Yinyu Lan Shizhu He Kang Liu Jun Zhao Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules Applied Sciences distributed representation knowledge graph link prediction logical rule |
title | Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules |
title_full | Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules |
title_fullStr | Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules |
title_full_unstemmed | Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules |
title_short | Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules |
title_sort | knowledge reasoning via jointly modeling knowledge graphs and soft rules |
topic | distributed representation knowledge graph link prediction logical rule |
url | https://www.mdpi.com/2076-3417/13/19/10660 |
work_keys_str_mv | AT yinyulan knowledgereasoningviajointlymodelingknowledgegraphsandsoftrules AT shizhuhe knowledgereasoningviajointlymodelingknowledgegraphsandsoftrules AT kangliu knowledgereasoningviajointlymodelingknowledgegraphsandsoftrules AT junzhao knowledgereasoningviajointlymodelingknowledgegraphsandsoftrules |