Mr. Guangxuan Song began his academic path with a Bachelor's degree in Automation at the University of Science and Technology Beijing (USTB), where he studied from September 2016 to June 2020. His dedication and academic excellence earned him prestigious honors, including the 2017 National Scholarship, 2019 Dean's Medal, and recognition as a 2019 Beijing Outstanding Student. His commitment extended beyond academics into student leadership roles such as Vice President of the Youth League Committee and Head of the News and Publicity Department. These formative years laid a strong foundation for his later research in Knowledge Graphs and Graph Neural Networks for Materials Science.
Professional Endeavors
Currently pursuing a Ph.D. in Control at USTB, Mr. Song has established himself as a promising researcher in Knowledge Graphs and Graph Neural Networks for Materials Science. His work involves pioneering projects supported by major national initiatives such as the National Environmental Corrosion Platform of China, the “Belt and Road” Corrosion Big Data Sharing Platform, and the State Grid Corporation’s corrosion data mining project. In addition, he has participated in building three national-level scientific data platforms, secured six invention patent applications, and holds seven software copyrights.
Contributions and Research Focus
Mr. Song’s research centers on Knowledge Graphs and Graph Neural Networks for Materials Science, aiming to revolutionize how scientific data is mined and utilized. His work bridges materials science with artificial intelligence, creating intelligent platforms that optimize data correlation, structural understanding, and prediction models. His integration of knowledge graphs with graph neural networks (GNNs) allows for robust material property prediction, failure analysis, and intelligent design essential in modern materials engineering and corrosion prediction of power systems.
Impact and Influence
Mr. Guangxuan Song’s research has had a significant impact on the convergence of machine learning and material science. His efforts in Knowledge Graphs and Graph Neural Networks for Materials Science have shaped new methodologies for predictive modeling, uncertainty estimation, and scientific data integration. He has also been recognized by tech leaders, being named a Huawei Student Developer in 2021 and a Baidu Lingjing Developer (LLM Applications) in 2023. His cross-disciplinary influence continues to grow, bridging AI, materials science, and real-world engineering applications.
Academic Cites
Although still in the early stages of his Ph.D., Mr. Song's publications and platform contributions have begun to attract academic recognition. His frameworks and research in Knowledge Graphs and Graph Neural Networks for Materials Science are being utilized and cited within Chinese and international academic communities. His contributions, especially to open science infrastructures, have laid the groundwork for a well-cited research portfolio.
Legacy and Future Contributions
With a trajectory defined by innovation and interdisciplinary excellence, Mr. Guangxuan Song is poised to become a leader in intelligent scientific research systems. His future contributions are expected to include further integration of large language models (LLMs) with scientific databases, enhancement of cross-modal knowledge extraction, and the development of robust AI frameworks for industrial material applications. His involvement in high-profile projects and competitions (e.g., 2021 First Prize in the "Internet+" Beijing Entrepreneurship Competition, 2020 iCAN International Entrepreneurship Global Winner) exemplifies his long-term vision and dedication.
📘Knowledge Graphs and Graph Neural Networks for Materials Science
Through his scholarly and practical work in Knowledge Graphs and Graph Neural Networks for Materials Science, Mr. Song continues to redefine the boundaries of AI-driven material prediction and data integration. His research outputs, professional recognitions, and national-level engagements collectively illustrate his influential role in the evolution of Knowledge Graphs and Graph Neural Networks for Materials Science applications.
✍️ Notable Publication
📘Cross-category prediction of corrosion inhibitor performance based on molecular graph structures via a three-level message passing neural network model
Authors: J. Dai, D. Fu, G. Song, L. Ma, X. Guo, A. Mol, I. Cole, D. Zhang
Journal: Corrosion Science
Year: 2022
Citations: 17
📘From Knowledge Graph Development to Serving Industrial Knowledge Automation: A Review
Authors: G. Song, D. Fu, D. Zhang
Conference: 2022 41st Chinese Control Conference (CCC)
Year: 2022
Citations: 6
📘Bridging the Semantic-Numerical Gap: A Numerical Reasoning Method of Cross-modal Knowledge Graph for Material Property Prediction
Authors: G. Song, D. Fu, Z. Qiu, Z. Yang, J. Dai, L. Ma, D. Zhang
Journal: arXiv preprint
Year: 2023
Citations: 2
📘A Named Entity Extraction Method for Commonly Used Steel Knowledge Graph
Authors: Z. Ma, L. Ma, D. Fu, G. Song, D. Zhang
Book Title: Proceedings of 2021 Chinese Intelligent Systems Conference: Volume III
Year: 2022
Citations: 2
📘Corrosion Resistant Performance Prediction in High-Entropy Alloys: A Framework for Model, Interpretation and Multi-Dimensional Visualization
Authors: G. Song, D. Fu, W. Chang, Z. Fu, L. Ma, D. Zhang
Journal: Corrosion Science
Year: 2025
Citations: 0
📘A Message Passing Neural Network Framework with Learnable PageRank for Author Impact Assessment
Authors: S. Guangxuan (G. Song), D. Fu, X. Wu (Xiaomeng Wu)
Journal: Advances in Electrical & Computer Engineering
Year: 2025
Citations: 0
📘Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data
Authors: G. Song, D. Fu, Z. Qiu, J. Meng, D. Zhang
Journal: arXiv preprint
Year: 2024
Citations: 0