Guifang Fu's long-term career goal is to strengthen the mathematical and statistical foundations of machine learning and Artificial Intelligence through the development of novel methodology and theory driven by real-world datasets and scientific applications. She is particularly interested in applications involving morphology and shape analysis, the microbiome, genome-wide association studies (GWAS), and other biomedical areas. These application domains motivate the development of innovative data analytical strategies that leverage rigorous statistical methodology in functional and longitudinal data analysis, variable selection, statistical inference, as well as state-of-the-art machine learning and deep learning techniques. Her group also establishes theoretical guarantees for high-dimensional statistical learning methods.
Fu is committed to interdisciplinary collaboration and the training of the next generation of statisticians. She works closely with researchers in Mathematics, Computer Science, Biomedicine, Anthropology, among other disciplines. Her research has been supported by the National Science Foundation and multiple internal research grants.
Statistical Machine Learning, Data Science
Statistical Shape Analysis
Functional/Longitudinal Data Analysis
High-Dimensional Statistical Inference
Biostatistics
Genome-Wide Association Studies (GWAS)
Microbiome, Neuroscience, and other Biomedical Applications
An asterisk (∗) is used to indicate corresponding author; a dagger (†) is used to indicate equally-contributing first authors. Students under my guidance have their names underlined.
Niranda P, McKenney P, and Fu G*. Enhanced Edge Selection Approaches for ODE Graph Network Construction (RECON).
Zhao G, Wang Y, Dai X, and Fu G*. An Integrated Deep Learning and Statistical Framework for Whole-Network Gene–Environment Associations with Leaf Vascular Architecture.
Wang Y, Dai X, Fu H, and Fu G*. Longitudinal Random Forests for Sparse and Irregular Response Trajectories.
Wang Y†, Thakar S†, Schick A, and Fu G*. Theoretical Properties of Multivariate Random Forest in Feature Selection and its Application to Facial Morphology-Gene Detection.
Zhao G†, Li X†, Chavoshnejad P, Razavi J, Solhtalab A, Yin L, and Fu G*. Toward High-fidelity 3D Point-Cloud Learning for Brain Folding Morphology Prediction Using Trans-Unet.
Zhao S, Shang Z, Weinberg S, Claes P, Shaffer J, and Fu G*. A Consistent Feature Screening Approach for Tensor Responses with Applications to Genome-wide Facial Shape Association.
Dai X and Fu G*. Functional Mixed-effect Model for Bilevel Repeated Measurements.
Zhao S, Qi C, Zhao G, Wang Y, and Fu G* (2024). A Model-Free and Distribution-Free Multi-omics Integration Approach for Detecting Novel Lung Adenocarcinoma Genes. Scientific Reports. 14(1), 17996.
Zhao S and Fu G* (2022). Distribution-free and Model-free Multivariate Feature Screening via Multivariate Rank Distance Correlation. Journal of Multivariate Analysis. 192, 105081.
Dai X, Fu G*, Reese R, Zhao S, and Shang Z (2022). An Approach of Bayesian Variable Selection for Ultrahigh Dimensional Multivariate Regression. Stat. 11(1), e476.
Reese R, Fu G*, Zhao G, Dai X, Li X, and Chiu K (2022). Epistasis Detection via the Joint Cumulant. Statistics in Biosciences. 14(3), 514–532.
Fu G*, Dai X, and Liang Y (2021). Functional Random Forests for Curve Response. Scientific Reports. 11(1), 24159.
NSF Award (DMS-1413366): Statistical Models for Mapping Genetic and Environmental Effects Regulating Shape Variation (sole PI)
Binghamton University Health Sciences TAE Grant: Linking the Gut Microbiome to Brain Activity in Adults at Risk for Alzheimer's Disease (Co-PI with Ian McDonough, Yanyan Li, and Tao Zhang)
Binghamton University Data Science TAE Grant: Mechanics of Brain Folding: Predicting the Cortical Folding Patterns of the Human Brain (Co-PI with Mir Jalil Razavi)
Binghamton University Data Science TAE Grant: Data Science Modeling for Shape and Genome Data (Co-PI with Lijun Yin)
Binghamton University Harpur College Faculty Research Grant: Integrating Functional Data Analysis with Modern Machine Learning Methods (sole PI)
Fu is one of the organizers of the Data Science Seminar hosted by the Department of Mathematics and Statistics at Binghamton University.