Research on the Application and Optimization of Knowledge Graph in Automatic Machine Learning
Jiali He
Yong Liu
DOI: https://doi.org/10.59429/esta.v10i6.1673
Keywords: Knowledge Graph; Automatic Machine Learning; Application; Optimization
Abstract
Automatic Machine Learning (AutoML) refers to the use of machine learning techniques to automate the entire process of machine learning, including data preprocessing, feature selection, model selection, and hyperparameter optimization. As a structured method for representing and storing knowledge, knowledge graphs have broad application prospects in automatic machine learning. By fully utilizing the information in the knowledge graph, the intelligence and decision-making ability of automatic machine learning systems can be strengthened, promoting the development and application of machine learning technology in various fields.
References
[1] Cao Shujin, Li Ruijing. Construction and Application of Innovation Knowledge Graph Based on Patent Literature Abstracts [J]. Intelligence Theory and Practice. 2022; 45 (11): 21-28.
[2] Yang Guang. (2022) Research on Entity Recognition and Relationship Extraction Based on Biomedical Knowledge Enhancement
[D]. Shanghai: East China Normal University.
[3] Tang Wangjing. A Science Popularization Text Classification Algorithm Based on Attention Mechanism and Knowledge Graph Enhancement [D]. Beijing Jiaotong University, 2022
[4] Du Junlei. (2022) Design and Implementation of a Learning Resource Recommendation System Based on Knowledge Graph [D].
Beijing: Beijing Jiaotong University.
[5] Jin Zhe, Zhang Yin, Wu Fei, Zhu Wenwu, Pan Yunhe. Artificial Intelligence Algorithm Model Combining Data Driven and Knowl_x005fedge Guided [J]. Journal of Electronics and Information Science. 2023; 45 (07): 2580-2594.
[6] Yi Xiaoyu, Yi Mianzhu. Research on Knowledge Graph Fusion Technology [J]. Computer Programming Skills and Maintenance.
2022; (08): 144-146+164.
[7] Deng Liang, Cao Cungen. A method for constructing a patent knowledge graph [J]. Computer Science. 2022; 49 (11): 185-196.