Deep Reinforcement Learning Based Ontology Meta-Matching Technique

Xingsi XUE; Yirui HUANG; Zeqing ZHANG

doi:10.1587/transinf.2022DLP0050

Deep Reinforcement Learning Based Ontology Meta-Matching Technique

Xingsi XUE, Yirui HUANG, Zeqing ZHANG

Full Text Views

1

Cite this

Summary :

Ontologies are regarded as the solution to data heterogeneity on the Semantic Web (SW), but they also suffer from the heterogeneity problem, which leads to the ambiguity of data information. Ontology Meta-Matching technique (OMM) is able to solve the ontology heterogeneity problem through aggregating various similarity measures to find the heterogeneous entities. Inspired by the success of Reinforcement Learning (RL) in solving complex optimization problems, this work proposes a RL-based OMM technique to address the ontology heterogeneity problem. First, we propose a novel RL-based OMM framework, and then, a neural network that is called evaluated network is proposed to replace the Q table when we choose the next action of the agent, which is able to reduce memory consumption and computing time. After that, to better guide the training of neural network and improve the accuracy of RL agent, we establish a memory bank to mine depth information during the evaluated network's training procedure, and we use another neural network that is called target network to save the historical parameters. The experiment uses the famous benchmark in ontology matching domain to test our approach's performance, and the comparisons among Deep Reinforcement Learning(DRL), RL and state-of-the-art ontology matching systems show that our approach is able to effectively determine high-quality alignments.

Publication: IEICE TRANSACTIONS on Information Vol.E106-D No.5 pp.635-643

Publication Date: 2023/05/01

Publicized: 2022/03/04

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2022DLP0050

Type of Manuscript: Special Section PAPER (Special Section on Deep Learning Technologies: Architecture, Optimization, Techniques, and Applications)

Category: Core Methods

Authors

Xingsi XUE
  Fujian University of Technology
Yirui HUANG
  Fujian University of Technology
Zeqing ZHANG
  Xiamen University

Keyword

ontology meta-matching, reinforcement learning, neural network

Cite this

Copy

Xingsi XUE, Yirui HUANG, Zeqing ZHANG, "Deep Reinforcement Learning Based Ontology Meta-Matching Technique" in IEICE TRANSACTIONS on Information, vol. E106-D, no. 5, pp. 635-643, May 2023, doi: 10.1587/transinf.2022DLP0050.
Abstract: Ontologies are regarded as the solution to data heterogeneity on the Semantic Web (SW), but they also suffer from the heterogeneity problem, which leads to the ambiguity of data information. Ontology Meta-Matching technique (OMM) is able to solve the ontology heterogeneity problem through aggregating various similarity measures to find the heterogeneous entities. Inspired by the success of Reinforcement Learning (RL) in solving complex optimization problems, this work proposes a RL-based OMM technique to address the ontology heterogeneity problem. First, we propose a novel RL-based OMM framework, and then, a neural network that is called evaluated network is proposed to replace the Q table when we choose the next action of the agent, which is able to reduce memory consumption and computing time. After that, to better guide the training of neural network and improve the accuracy of RL agent, we establish a memory bank to mine depth information during the evaluated network's training procedure, and we use another neural network that is called target network to save the historical parameters. The experiment uses the famous benchmark in ontology matching domain to test our approach's performance, and the comparisons among Deep Reinforcement Learning(DRL), RL and state-of-the-art ontology matching systems show that our approach is able to effectively determine high-quality alignments.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DLP0050/_p

Copy

@ARTICLE{e106-d_5_635,
author={Xingsi XUE, Yirui HUANG, Zeqing ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Deep Reinforcement Learning Based Ontology Meta-Matching Technique},
year={2023},
volume={E106-D},
number={5},
pages={635-643},
abstract={Ontologies are regarded as the solution to data heterogeneity on the Semantic Web (SW), but they also suffer from the heterogeneity problem, which leads to the ambiguity of data information. Ontology Meta-Matching technique (OMM) is able to solve the ontology heterogeneity problem through aggregating various similarity measures to find the heterogeneous entities. Inspired by the success of Reinforcement Learning (RL) in solving complex optimization problems, this work proposes a RL-based OMM technique to address the ontology heterogeneity problem. First, we propose a novel RL-based OMM framework, and then, a neural network that is called evaluated network is proposed to replace the Q table when we choose the next action of the agent, which is able to reduce memory consumption and computing time. After that, to better guide the training of neural network and improve the accuracy of RL agent, we establish a memory bank to mine depth information during the evaluated network's training procedure, and we use another neural network that is called target network to save the historical parameters. The experiment uses the famous benchmark in ontology matching domain to test our approach's performance, and the comparisons among Deep Reinforcement Learning(DRL), RL and state-of-the-art ontology matching systems show that our approach is able to effectively determine high-quality alignments.},
keywords={},
doi={10.1587/transinf.2022DLP0050},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Deep Reinforcement Learning Based Ontology Meta-Matching Technique
T2 - IEICE TRANSACTIONS on Information
SP - 635
EP - 643
AU - Xingsi XUE
AU - Yirui HUANG
AU - Zeqing ZHANG
PY - 2023
DO - 10.1587/transinf.2022DLP0050
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - Ontologies are regarded as the solution to data heterogeneity on the Semantic Web (SW), but they also suffer from the heterogeneity problem, which leads to the ambiguity of data information. Ontology Meta-Matching technique (OMM) is able to solve the ontology heterogeneity problem through aggregating various similarity measures to find the heterogeneous entities. Inspired by the success of Reinforcement Learning (RL) in solving complex optimization problems, this work proposes a RL-based OMM technique to address the ontology heterogeneity problem. First, we propose a novel RL-based OMM framework, and then, a neural network that is called evaluated network is proposed to replace the Q table when we choose the next action of the agent, which is able to reduce memory consumption and computing time. After that, to better guide the training of neural network and improve the accuracy of RL agent, we establish a memory bank to mine depth information during the evaluated network's training procedure, and we use another neural network that is called target network to save the historical parameters. The experiment uses the famous benchmark in ontology matching domain to test our approach's performance, and the comparisons among Deep Reinforcement Learning(DRL), RL and state-of-the-art ontology matching systems show that our approach is able to effectively determine high-quality alignments.
ER -