Student Performance Prediction by Graph Neural Network


The invention is a model to visulize the relationship between students and questions. Through the student-interaction-question network, it provides an innovative way to reflect the implicit relations of questions.

  • Student Performance Prediction by Graph Neural Network
Commercialisation opportunities
Technology licensing agreement
Problem addressed

Generalizable GNN-based student performance prediction with student-interaction-question network.

  • A novel GNN-based approach to model student knowledge level and predict student performance in interactive online question pools with highly effective and efficient R2GCN model.
Key impact
  • Generalizable student performance prediction with students' interactions
  • Robust Performance: Achieve the best performance on a real-world dataset containing 4000 questions and 1600 students
  • State-of-the-Art Accuracy: 66% in 4-class classification
  • Online education – personalized recommendation, retention rate improvement
  • E-sports – player performance analysis
  • E-commerce – customer satisfaction estimation


  • USPTO US Granted Patent: Application # 17/343769
  • CNIPA Chinese Patent Application 202110676427.3
The Hong Kong University of Science and Technology (HKUST)

The Hong Kong University of Science and Technology (HKUST) ( is a world-class research intensive university that focuses on science, technology and business as well as humanities and social science. HKUST offers an international campus, and a holistic and interdisciplinary pedagogy to nurture well-rounded graduates with global vision, a strong entrepreneurial spirit and innovative thinking. Over 80% of our research work were rated “Internationally excellent” or “world leading” in the Research Assessment Exercise 2020 of Hong Kong’s University Grants Committee. We were ranked 3rd in Times Higher Education’s Young University Rankings 2022, and our graduates were ranked 23rd worldwide and among the best from universities from Asia in Global University Employability Survey 2021.