About Me

I am Qiang Yang, a Postdoctoral Associate at the Department of Health Outcomes & Biomedical Informatics, University of Florida, where I am fortunate to be supervised by Prof. Rui Yin. My research lies at the intersection of graph neural networks (GNNs), interpretable machine learning, and their applications on heterogeneous graphs in biomedical informatics. I am also deeply engaged in leveraging large language models (LLMs) to address complex challenges in biomedical science and healthcare.

I earned my Ph.D. in Computer Science from King Abdullah University of Science and Technology (KAUST) in 2023, under the supervision of Prof. Xiangliang Zhang and Prof. Xin Gao at the lab of Machine Intelligence and kNowledge Engineering (MINE) and Structural and Functional Bioinformatics Group (SFB). My dissertation focused on interpretable learning for heterogeneous graphs, aiming to demystify the decision-making processes of GNN models through the generation of interpretable graph structures.

Prior to my Ph.D., I obtained my Master’s degree from Soochow University, where I was honored with the Outstanding Master Student Award. Under the guidance of Prof. Zhixu Li, I worked on database systems, with a focus on data quality improvement through techniques such as record matching and data cleaning. I also explored knowledge graphs (KGs), contributing to areas such as KG construction and representation learning.

Academic Background

November 2023 - Now: University of Florida (Postdoctoral Associate)
January 2019 - November 2023: King Abdullah University of Science and Technology (Ph.D Degree)
December 2022 - March 2023: Fudan University (Visiting Student)
May 2016 - November 2016: King Abdullah University of Science and Technology (Visiting Student)
September 2014 - June 2017: Soochow University (Master Degree)

Research Interests

AI for Biomedical Science

Bioinformatics – Computational modeling of protein interactions
Protein Language Models – Deep learning for protein structure, function, and interaction prediction
Biomedical Informatics – Deep learning models for AD/ADRD, liver-relevant diseases, and cancers
Large Language Models (LLMs) – Domain-specific fine-tuning for biomedical text and clinical notes
Multimodal Learning – Integrating heterogeneous biomedical data (e.g., text, sequence, and imaging) for predictive modeling

Machine Learning & Data Science

Machine Learning – Supervised, unsupervised, and self-supervised learning for health data
Data Mining – Large-scale data processing, pattern discovery, and anomaly detection
Interpretable Learning – Building explainable models to uncover actionable insights in healthcare and science

Graph-based Learning

Graph Representation Learning – Representation learning on networks, including biological, clinical, and knowledge graphs
Heterogeneous Graph Neural Networks – Modeling multi-relational and typed-entity graphs for interpretability and prediction
Interpretable Graph Learning – Generate the interpretable subgrph for the graph predictions, such as link prediction and graph classificaiton

Selected Publications (Read More)

Qiang Yang, Changsheng Ma, Qiannan Zhang, Xin Gao, Chuxu Zhang, and Xiangliang Zhang. 2023. Greedy Policy-based Perturbation for Counterfactual Learning on Heterogeneous Graphs. in KDD.
Qiannan Zhang, Shichao Pei, Qiang Yang, Chuxu Zhang, Nitesh V Chawla, and Xiangliang Zhang. 2023. Cross-domain Few-shot Graph Classification with a Reinforced Task Coordinator. In AAAI.
Qiang Yang, Changsheng Ma, Qiannan Zhang, Xin Gao, Chuxu Zhang, and Xiangliang Zhang. 2023. Interpretable Research Interest Shift with Temporal Heterogeneous Graphs Detection. in WSDM.
Xiuying Chen, Mingzhe Li, Shen Gao, Xin Cheng, Qiang Yang, Qishen Zhang, Xin Gao, and Xiangliang Zhang. 2023. A Topic-aware Summarization Framework with Different Modal Side Information. In SIGIR.

News

Our paper “AutoRADP: An Interpretable Deep Learning Framework to Predict Rapid Progression for Alzheimer’s Disease and Related Dementias Using Electronic Health Records” has been accepted as a full paper in ICIBM 2025.
Our paper “FCFNets: A Factual and Counterfactual Learning Framework for Enhanced Hepatic Fibrosis Prediction in Young Adults with T2D” has been accepted as a full paper in AMIA 2025.