A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning
Discovering tactical knowledge aims to extract tactical data derived from battlefield signal data, which is vital in information warfare. The learning and reasoning from battlefield signal information can help commanders make effective decisions. However, traditional methods are limited in capturing...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/4/528 |
| _version_ | 1827343300328161280 |
|---|---|
| author | Xiaodong Wang Pei He Hongjing Yao Xiangnan Shi Jiwei Wang Yangming Guo |
| author_facet | Xiaodong Wang Pei He Hongjing Yao Xiangnan Shi Jiwei Wang Yangming Guo |
| author_sort | Xiaodong Wang |
| collection | DOAJ |
| description | Discovering tactical knowledge aims to extract tactical data derived from battlefield signal data, which is vital in information warfare. The learning and reasoning from battlefield signal information can help commanders make effective decisions. However, traditional methods are limited in capturing sequential and global representation due to their reliance on prior knowledge or feature engineering. The current models based on deep learning focus on extracting implicit behavioral characteristics from combat process data, overlooking the embedded martial knowledge within the recognition of combat intentions. In this work, we fill the above challenge by proposing a dual fusion pipeline introducing graph representation learning into sequence learning to construct tactical behavior sequence graphs expressing implicit martial knowledge, named TBGCN. Specifically, the TBGCN utilizes graph representation learning to represent prior knowledge by building a graph to induce deep learning paradigms, and sequence learning finds the hidden representation from the target’s serialized data. Then, we employ a fusion module to merge two such representations. The significance of integrating graphs with deep learning lies in using the artificial experience of implicit graph structure guiding adaptive learning, which can improve representation ability and model generalization. Extensive experimental results demonstrate that the proposed TBGCN can effectively discover tactical knowledge and significantly outperform the traditional and deep learning methods. |
| first_indexed | 2024-03-07T22:23:19Z |
| format | Article |
| id | doaj.art-f06b4654dae24f41b738cf5d2fa734ce |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-07T22:23:19Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-f06b4654dae24f41b738cf5d2fa734ce2024-02-23T15:26:04ZengMDPI AGMathematics2227-73902024-02-0112452810.3390/math12040528A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation LearningXiaodong Wang0Pei He1Hongjing Yao2Xiangnan Shi3Jiwei Wang4Yangming Guo5School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Computer Science, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Cybersecurity, Northwestern Polytechnical University, Xi’an 710072, ChinaUnmanned System Research Institute, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Computer Science, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Cybersecurity, Northwestern Polytechnical University, Xi’an 710072, ChinaDiscovering tactical knowledge aims to extract tactical data derived from battlefield signal data, which is vital in information warfare. The learning and reasoning from battlefield signal information can help commanders make effective decisions. However, traditional methods are limited in capturing sequential and global representation due to their reliance on prior knowledge or feature engineering. The current models based on deep learning focus on extracting implicit behavioral characteristics from combat process data, overlooking the embedded martial knowledge within the recognition of combat intentions. In this work, we fill the above challenge by proposing a dual fusion pipeline introducing graph representation learning into sequence learning to construct tactical behavior sequence graphs expressing implicit martial knowledge, named TBGCN. Specifically, the TBGCN utilizes graph representation learning to represent prior knowledge by building a graph to induce deep learning paradigms, and sequence learning finds the hidden representation from the target’s serialized data. Then, we employ a fusion module to merge two such representations. The significance of integrating graphs with deep learning lies in using the artificial experience of implicit graph structure guiding adaptive learning, which can improve representation ability and model generalization. Extensive experimental results demonstrate that the proposed TBGCN can effectively discover tactical knowledge and significantly outperform the traditional and deep learning methods.https://www.mdpi.com/2227-7390/12/4/528graph representation learninggraph structurediscovering tactical knowledgedeep learning |
| spellingShingle | Xiaodong Wang Pei He Hongjing Yao Xiangnan Shi Jiwei Wang Yangming Guo A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning Mathematics graph representation learning graph structure discovering tactical knowledge deep learning |
| title | A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning |
| title_full | A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning |
| title_fullStr | A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning |
| title_full_unstemmed | A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning |
| title_short | A Dual Fusion Pipeline to Discover Tactical Knowledge Guided by Implicit Graph Representation Learning |
| title_sort | dual fusion pipeline to discover tactical knowledge guided by implicit graph representation learning |
| topic | graph representation learning graph structure discovering tactical knowledge deep learning |
| url | https://www.mdpi.com/2227-7390/12/4/528 |
| work_keys_str_mv | AT xiaodongwang adualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT peihe adualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT hongjingyao adualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT xiangnanshi adualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT jiweiwang adualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT yangmingguo adualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT xiaodongwang dualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT peihe dualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT hongjingyao dualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT xiangnanshi dualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT jiweiwang dualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning AT yangmingguo dualfusionpipelinetodiscovertacticalknowledgeguidedbyimplicitgraphrepresentationlearning |