avatar

Qinyi Liu

Assistant Professor
City University of Macau
qyliu@cityu.edu.mo or qinyi876@outlook.com


About Me

Hi! I’m Qinyi Liu, an Assistant Professor at the City University of Macau. My research explores how we can build AI systems that remain trustworthy when they encounter the complexity of the real world, with a focus on applications in the education domain. My research has appeared in leading venues across AI and education, including WWW, RecSys, LAK, and BJET.

I have an interdisciplinary background in computer science and social science, holding degrees in both fields. I completed my PhD at the Centre for the Science of Learning & Technology (SLATE), University of Bergen, working with Prof. Mohammad Khalil. During my PhD, I also visited the University of South Australia and Monash University as a visiting scholar funded by Meltzerfondet.

I pursued my master’s studies at the University of Edinburgh and the University of Liverpool. Previously, I received my Bachelor’s degree from Chongqing University. During my time at Edinburgh, I was part of the Covid-19 Response Governance Mapping Project. I also worked at the University of North Carolina at Chapel Hill with Prof Joseph Tucker, where I contributed to website development and research dissemination.

Research Interests

I work at the intersection of Trustworthy AI, Data Science, and Education.

What I study

How I approach it

I develop privacy-preserving, fair, and behaviour-aware methods, including synthetic data, differential privacy, and responsible learning analytics.

Where I study it

Education serves as an important real-world setting for this work, while many of the underlying questions extend to data-driven systems more broadly.

🚀 If you see our research intersect, feel free to reach out — I am always open to discussing potential collaborations.

Publications

Peer-Reviewed Conference Papers

  1. Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores
    S, Urmian, Q Liu, M Khalil
    ACM Conference on Recommender Systems (RecSys) Main Track
    Accepted · 18% acceptance rate · CORE-A · CCF-B
  2. Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN
    Q Liu, M Khalil, N Goel
    The Web Conference (WWW) Main Papers Track
    DOI Code · 23% acceptance rate · CORE-A · CCF-A
  3. Quality Degradation Attack in Synthetic Data
    Q Liu, D Liu, F Vadiee, M Khalil, and P Barrios
    International Conference on Data Science and AI for Social Good and Responsible Innovation (DASGRI-2026), Springer
    PDF Slides Accepted
  4. Measuring the Impact of Student Gaming Behaviors on Learner Modeling
    Q Liu, L Li, V Švábenský, C Borchers, M Khalil
    LAK26: 16th International Learning Analytics and Knowledge Conference (2026)
    arXiv Code Slides 🏆 Best Full Paper Award (Top 2%) 28% acceptance rate · CORE-A
  5. Brief but Impactful: How Human Tutoring Interactions Shape Engagement in Online Learning
    C Borchers, A Gurung, Q Liu, D Thomas, M Khalil, K Koedinger
    LAK26: 16th International Learning Analytics and Knowledge Conference (2026)
    arXiv Code 28% acceptance rate · CORE-A
  6. Advancing privacy in learning analytics using differential privacy
    Q Liu, M Khalil, R Shakya, J Jovanovic
    LAK25: 15th International Learning Analytics and Knowledge Conference (2025)
    DOI Slides Accepted · 29% acceptance rate · Best Paper Honorable Mention · CORE-A
  7. Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms
    Q Liu, O Deho, F Vadiee, M Khalil, S Joksimovic, G Siemens
    LAK25: 15th International Learning Analytics and Knowledge Conference (2025)
    DOI Slides Code 29% acceptance rate · CORE-A
  8. Towards Privacy-Preserving Data-Driven Education: the Potential of Federated Learning
    M Khalil, R Shakya, Q Liu
    International Conference on New Trends In Computing Sciences (ICTCS), IEEE Xplore (2025)
    DOI
  9. Creating artificial students that never existed: Leveraging large language models and CTGANs for synthetic data generation
    M Khalil, F Vadiee, R Shakya, Q Liu
    LAK25: 15th International Learning Analytics and Knowledge Conference (2025)
    DOI 29% acceptance rate · CORE-A
  10. Scaling While Privacy Preserving: a Comprehensive Synthetic Tabular Data Generation and Evaluation in Learning Analytics
    Q Liu, M Khalil, R Shakya, J Jovanovic
    LAK24: 14th International Learning Analytics and Knowledge Conference (2024)
    DOI Slides Code 30% acceptance rate · CORE-A
  11. Explainable AI in Learning Analytics: Improving Predictive Models and Advancing Transparency and Trust
    Q Liu, M Khalil
    2024 IEEE Global Engineering Education Conference (EDUCON), pp. 1-7 (2024)
    DOI

Journal Articles

  1. A systematic review on student engagement in undergraduate mathematics: Conceptualization, measurement, and learning outcomes
    E Papageorgiou, J Wong, Q Liu, M Khalil, A Cabo
    Educational Psychology Review (2025)
    DOI IF=10.1 · SSCI
  2. Ensuring privacy through synthetic data generation in education
    Q Liu, R Shakya, J Jovanovic, M Khalil, J de la Hoz-Ruiz
    British Journal of Educational Technology, 00, 1–21 (2025)
    DOI IF=6.7 · SSCI
  3. Learning analytics for enhanced professional capital development: a systematic review
    J de La Hoz-Ruiz, M Khalil, J.D. Segovia, Q Liu
    Frontiers in Psychology, 15 (2024)
    DOI IF=3.8 · SSCI
  4. Understanding privacy and data protection issues in learning analytics using a systematic review
    Q Liu, M Khalil
    British Journal of Educational Technology, 54, 1715–1747 (2023)
    DOI IF=6.7 · SSCI

Book Chapters & Contributions to Edited Volumes

  1. AI for data generation in education: Towards learning and teaching support at scale [Editorial]
    M Khalil, Q Liu, J Jovanovic
    British Journal of Educational Technology (2025)
    DOI IF=6.7 · SSCI
  2. How to plan and manage a blended learning course module using generative artificial intelligence?
    M Khalil, R Shakya, Q Liu, M Ebner
    Case Studies on Blended Learning in Higher Education (pp. 53–72). Springer (2024)
    DOI

Open Source Projects

  1. Awesome Synthetic Data Application Education
    Q Liu
    Curated list of resources and papers for synthetic data application in education
    GitHub
  2. Generative AI for Synthetic Data in Learning Analytics – LAK 2026 Workshop
    Qinyi Liu et al. (with Mohammad Khalil et al.)
    Hands-on workshop materials, slides, datasets, and lab resources for the LAK 2026 workshop on synthetic data generation and privacy-presing learning analytics
    GitHub Workshop Page

Teaching

Teaching

Mentoring

Funding & Awards

Funding

Awards

Services

Guest Editor

Organization Committee Member

Journal Reviewer (27 international journals)

AI & Security:
IEEE Transactions on Knowledge and Data Engineering (TKDE); IEEE Transactions on Information Forensics and Security (TIFS);
Computers & Security; Artificial Intelligence Review; Neurocomputing;
Journal of Big Data; Journal of System Architecture; PeerJ Computer Science;
Computers in Biology and Medicine; Array; Archives of Computational Methods in Engineering;
Universal Access in the Information Society; AI and Ethics; Scientific Data;
Knowledge-Based System; Discover Informatics; Discover Computing; SoftwareX;

Education Technology:
Computers & Education; International Journal of Artificial Intelligence in Education (IJAIED);
British Journal of Educational Technology (BJET); Computers & Education: Artificial Intelligence;
Journal of Learning Analytics (JLA); Frontiers in Education; International Journal of Emerging Technologies in Learning (iJET).

Conference Program Committee & Reviewer


Powered by Jekyll and Minimal Light theme.