Yifei Zhang张逸飞

About

I am a second-year Ph.D. student in the Department of Biostatistics at the Yale School of Public Health, advised by Prof. Yize Zhao. My research focuses on statistical machine learning for multimodal neuroimaging and brain connectomics, with applications to Alzheimer's disease. I develop deep generative models that separate shared and modality-specific variation in structural and functional brain networks and can reconstruct one modality from the other. I also work on modeling disease progression from incomplete, largely cross-sectional biomarker data, and on multimodal normative models of healthy brain aging for identifying disease-related deviations.

Before Yale, I received an M.S. in Statistics and Operations Research from the University of North Carolina at Chapel Hill, where I worked with Prof. Zhengwu Zhang, and a B.S. in Applied Mathematics from the University of Liverpool.

Research Interests

• Deep generative models
• Normative modeling
• Disease progression modeling
• Missing data
• Multimodal neuroimaging
• Brain connectomics
• Alzheimer's disease

News

• 2026.09Two papers accepted to NeurIPS 2026.
• 2025.04Successfully passed my Master's thesis defense. Many thanks to Prof. Zhengwu Zhang for his careful guidance.
• 2025.03Honored to have been admitted to the Yale Biostatistics Program and to join Prof. Yize Zhao's group.
• 2024.09Joined the School of Data Science and Society as a Graduate Teaching Assistant.
• 2024.07Honored to participate in the EPIC Summer Camp and Workshop.

Publications & Preprints

• Orthogonal Sparse Subgraph Alignment for Structure-Function Coupling in Brain Networks
  Gao, H., Ham, D., Zhang, Y., Tian, X., Ding, S., Zhao, Y.* and Li, T.*
  Conference on Neural Information Processing Systems (NeurIPS), accepted (2026)
• ELPAC: Endpoint-Anchored Latent Progression with Stage-Varying Multimodal Coordination
  Ding, S., Zhang, Y., Tian, X., Guo, Y. and Zhao, Y.
  Conference on Neural Information Processing Systems (NeurIPS), accepted (2026)
• A Bayesian deep learning framework for brain dynamic functional connectivity linked with cognition
  Tian, X., Guo, Y., Ding, S., Zhang, Y., Esserman, D. and Zhao, Y.
  Biometrics, accepted (2026)
• Attention-Based Variational Framework for Joint and Individual Components Learning with Applications in Brain Network Analysis
  Zhang, Y., Liu, M. and Zhang, Z.
  arXiv preprint arXiv:2601.17073, under review (2026)
  PDFarXiv

  Brain organization is increasingly characterized through multiple imaging modalities, most notably structural connectivity (SC) and functional connectivity (FC). Integrating these inherently distinct yet complementary data sources is essential for uncovering the cross-modal patterns that drive behavioral phenotypes. However, effective integration is hindered by the high dimensionality and non-linearity of connectome data, complex non-linear SC–FC coupling, and the challenge of disentangling shared information from modality-specific variations. To address these issues, we propose the Cross-Modal Joint-Individual Variational Network (CM-JIVNet), a unified probabilistic framework designed to learn factorized latent representations from paired SC–FC datasets. Our model utilizes a multi-head attention fusion module to capture non-linear cross-modal dependencies while isolating independent, modality-specific signals. Validated on Human Connectome Project Young Adult (HCP-YA) data, CM-JIVNet demonstrates superior performance in cross-modal reconstruction and behavioral trait prediction. By effectively disentangling joint and individual feature spaces, CM-JIVNet provides a robust, interpretable, and scalable solution for large-scale multimodal brain analysis.

Education

• 2025.08 – Present Ph.D. Student, Yale School of Public Health · BiostatisticsSupervised by Prof. Yize Zhao.
• 2023.08 – 2025.05 M.S. in Statistics & Operations Research, UNC Chapel Hill · STOR DepartmentSupervised by Prof. Zhengwu Zhang.
• 2019.09 – 2023.07 B.S. in Applied Mathematics, University of Liverpool

Honors & Awards

• 2024.07SDSS Departmental and In-State Tuition Award (Fully Funded MS Student), UNC, US.
• 2023.07First Honor Class Graduate in Applied Mathematics, University of Liverpool, UK.

Talks

• 2024 Connecting Questions to Questions: How to Translate Real-World Questions Into Deductible InsightsTCM Conference, Durham, NC, USA

Experience

• 2020.05 – 2020.09 Data Analyst Intern, China Construction BankHenan, China