students
PhD and Masters students
Current PhD students
Tianqi Zhao
Topic: Assessing Graph Machine Learning Through the Lens of Data and Task Complexity
Tianqi’s research critically assesses advancements in graph machine learning by developing methods to characterize data and task complexity. Her approach aims to identify the inherent challenges in graph-structured data, providing a deeper understanding of model robustness and reliability across diverse applications.
Topic: Assessing Graph Machine Learning Through the Lens of Data and Task Complexity
Tianqi’s research critically assesses advancements in graph machine learning by developing methods to characterize data and task complexity. Her approach aims to identify the inherent challenges in graph-structured data, providing a deeper understanding of model robustness and reliability across diverse applications.
Yuan Xue
Topic: Accelerating Deep RL
Yuan focuses on improving efficiency of deep RL algorithms. For example in this paper he addresses sample inefficiency by automatically constructing abstract Markov decision processes (AMDPs) using graph representation learning.
Topic: Accelerating Deep RL
Yuan focuses on improving efficiency of deep RL algorithms. For example in this paper he addresses sample inefficiency by automatically constructing abstract Markov decision processes (AMDPs) using graph representation learning.
Graduated PhD students
Ngan Thi Dong (Graduated July 2023)
Topic: Joint learning from multiple information sources for biological problems
To address the challenges of data scarcity and noise that hinder generalizable learning from biomedical data, Ngan developed machine learning algorithms capable of learning jointly from diverse data sources, including omics data, clinical data, and biological interaction networks.
Topic: Joint learning from multiple information sources for biological problems
To address the challenges of data scarcity and noise that hinder generalizable learning from biomedical data, Ngan developed machine learning algorithms capable of learning jointly from diverse data sources, including omics data, clinical data, and biological interaction networks.
Emmanuel Iyiola Olatunji (Graduated July 2024)
Topic: Privacy Preserving Graph Machine Learning
Emmanuel studied privacy implications of graph machine learning. He developed methods for quantifying privacy risks as well as preserving privacy in graph machine learning.
Topic: Privacy Preserving Graph Machine Learning
Emmanuel studied privacy implications of graph machine learning. He developed methods for quantifying privacy risks as well as preserving privacy in graph machine learning.
🎓 Master’s Students
- Yang Li Li (Topic: GNN-LLM Hybrids for Multi-Label Node Classification)
- Kanta Tanahashi (Topic: Self-supervised learning for privacy preserving GNNs)
- Ellemijn Vernhout