ABSTRACT
The continuous increase of medical data promotes the development of knowledge graphs in specific fields. Currently, lung cancer ranks first in terms of morbidity and mortality. In the context of medical intelligence, the top-down and bottom-up methods are combined to semi-automatically construct a knowledge graph of lung cancer. The constructed domain knowledge graph is usually incomplete and lacking the relationship between entities. Therefore, the paper presents a real-time reasoning method of graph attention network to automatically learn reasoning from knowledge graph. This method not only considers neighbor information, but also introduces an attention mechanism, and it can make full use of all nodes and edges in the knowledge graph. The convergence time is reduced by changing the activation function and loss function in the network. This paper adopts three traditional data sets and a new data set for experiment comparison. The experiment results show the proposed method has good performance.
- Tao, Z.; Lu, H.; Hu, F.; Qiu, S.; Wu, C. A Model of High-Dimensional Feature Reduction Based on Variable Precision Rough Set and Genetic Algorithm in Medical Image. Mathematical Problems in Engineering. 2020.Google Scholar
- Ji, S.; Pan, S.; Cambria, E.; Marttinen, P.; Yu, P.S. A Survey on Knowledge Graphs: Representation, Acquisition and Applications. CoRR 2020.Google Scholar
- Yupu Guo, Yanxiang Ling, Honghui Chen: A Time-Aware Graph Neural Network for Session-Based Recommendation. IEEE Access 8: 2020:167371-167382.Google Scholar
- Shengbo Chen, Xianrui Liu, Yiyong Huang, Congcong Zhou, Huaikou Miao:Video Synopsis Based on Attention Mechanism and Local Transparent Processing. IEEE Access 8: 2020:92603-92614.Google Scholar
- Li, W.; Zhang, X.; Wang, Y.; Yan, Z.; Peng, R. Graph2Seq: Fusion Embedding Learning for Knowledge Graph Completion. IEEE Access 2019:157960-157971.Google Scholar
- Li Tailang. Research on knowledge representation and reasoning algorithm based on deduction lattice in clinical decision support system. Wuhan University, 2019.Google Scholar
- Zhao Chao. Chinese text-oriented medical knowledge acquisition, representation and reasoning. Harbin Institute of Technology, 2018.Google Scholar
- Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In European Semantic Web Conference (ESWC), 2018, pages 593-607.Google Scholar
- Balaevi I, Allen C, Hospedales T M. TuckER: Tensor Factorization for Knowledge Graph Completion. 2019.Google Scholar
Recommendations
Removable edges in a 5-connected graph and a construction method of 5-connected graphs
An edge e of a k-connected graph G is said to be a removable edge if G@?e is still k-connected. A k-connected graph G is said to be a quasi (k+1)-connected if G has no nontrivial k-separator. The existence of removable edges of 3-connected and 4-...
Removable edges in a k-connected graph and a construction method for k-connected graphs
An edge e of a k-connected graph G is said to be a removable edge if G@?e is still k-connected, where G@?e denotes the graph obtained from G by deleting e to get G-e and, for any end vertex of e with degree k-1 in G-e, say x, deleting x and then adding ...
Comments