I am a Ph.D. researcher in Computer Science at the University of Sheffield, UK, with my thesis submitted and viva pending, supervised by Professor Po Yang and Professor Vitaveska Lanfranchi.

My research focuses on general-purpose, trustworthy white-box deep learning grounded in information theory. I also have extensive experience and a strong interest in developing machine learning algorithms for healthcare, particularly disease progression modelling and biomarker identification.

I received my M.Sc. in Computer Science from Yunnan University (2020–2023), where I studied Alzheimer’s disease progression using multi-task learning, and my B.S. in Software Engineering from Sun Yat-sen University (2013–2017).

I welcome research collaborations and opportunities in trustworthy AI and machine learning for healthcare. Please get in touch.

🔬 Research

Trustworthy White-Box Machine Learning

I develop learning systems whose objectives, representations, architecture and inference process are explicit and interpretable. My research addresses four complementary levels:

• Learning objectives: Clarifying what a model learns to achieve and why its objectives are meaningful.
• Representation structure: Making the organisation of learned representations explicit and understandable.
• Model architecture: Explaining the roles of model components and their interactions.
• Inference process: Making the reasoning behind model outputs traceable.

This work brings together information theory, coding theory, representation learning, robustness to label noise and out-of-distribution generalisation.

Machine Learning for Healthcare

I develop multi-task and statistical learning methods for single-disease and cross-disease progression modelling, biomarker identification, wearable sensor analysis and medical imaging, including 3D MRI. My work spans Alzheimer’s disease, Parkinson’s disease and mobility-related conditions.

🔥 News

• 2026.10: My Ph.D. thesis has been submitted; I am awaiting my viva.
• 2026.09: My paper Less Structure is More: Minimal Representations for Supervised Learning was accepted by NeurIPS 2026.
• 2026.09: Our preprint On the Limits of Maximal Coding Rate Reduction for Out-of-Distribution Generalisation is available on arXiv (17 September 2026).
• 2026.08: Our preprint DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning is available on arXiv (25 August 2026).
• 2026.06: Our paper Beyond Single Scores: A Multi-Cognitive Objective Learning for AD Progression Prediction, on which I am a co-corresponding author, was accepted by Pattern Recognition.
• 2025.05: Co-corresponding-author paper on joint image synthesis and fusion accepted by Engineering Applications of Artificial Intelligence.
• 2024.12: Four papers accepted by the IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

📝 Selected Publications

Google Scholar citations: 252 · Google Scholar

• NeurIPS 2026 — Less Structure is More: Minimal Representations for Supervised Learning
  Menghui Zhou, Vitaveska Lanfranchi, Po Yang.
  Conference on Neural Information Processing Systems (NeurIPS), 2026.

• TKDE 2024 — Integrating Visualised Automatic Temporal Relation Graph into Multi-Task Learning for Alzheimer’s Disease Progression Prediction
  Menghui Zhou, Xulong Wang, Tong Liu, Yun Yang, Po Yang.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024.

• KDD 2023 — Automatic Temporal Relation in Multi-Task Learning
  Menghui Zhou, Po Yang.
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023.

• AAAI 2023 — Robust Temporal Smoothness in Multi-Task Learning
  Menghui Zhou, Yu Zhang, Yun Yang, Tong Liu, Po Yang.
  AAAI Conference on Artificial Intelligence (AAAI), 2023.

• BIBM 2024 — Learning Interpretable Continuous Representation for Alzheimer’s Disease Classification
  Menghui Zhou, Mingxia Wang, Yu Zhang, Zhipeng Yuan, Vitaveska Lanfranchi, Po Yang.
  IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024.

• BIBM 2023 — Integrating Automatic Temporal Relation Graph into Multi-Task Learning for Alzheimer’s Disease Progression Prediction
  Menghui Zhou, T. Liu, X. Wang, K. Liu, Y. Zhang, P. Yang.
  IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2023.

• CIKM 2022 — Multi-task Learning with Adaptive Global Temporal Structure for Predicting Alzheimer’s Disease Progression
  Menghui Zhou, Yu Zhang, Tong Liu, Yun Yang, Po Yang.
  ACM International Conference on Information and Knowledge Management (CIKM), 2022.

• MSN 2021 — Modeling Disease Progression Flexibly with Nonlinear Disease Structure via Multi-task Learning
  Menghui Zhou, Xulong Wang, Yun Yang, Fengtao Nan, Yu Zhang, Jun Qi, Po Yang.
  IEEE International Conference on Mobility, Sensing and Networking (MSN), 2021.

See my Google Scholar profile for the full publication record.

🌈 Professional Activities

• Conference reviewing / programme committee service: ICML, NeurIPS, ICLR, AAAI and KDD.
• Journal reviewing: IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Pattern Recognition (PR), Knowledge-Based Systems (KBS) and Engineering Applications of Artificial Intelligence (EAAI).

🎖 Honors and Awards

• 2024: First Prize, Ph.D. Poster Competition, University of Sheffield.
• 2024: IEEE BIBM Travel Grant.
• 2023: EPSRC Ph.D. Scholarship.
• 2023: Outstanding Master’s Thesis Award, Yunnan University.
• 2022: China National Scholarship.