Research & publications
Research experience across computational graph theory, graph representation learning, molecular property prediction, knowledge graphs, and healthcare machine learning.
Selected publication
Functional-group-based molecular graph coarsening using quotient graphs, evaluated with graph neural networks for molecular property prediction.
Hajiabolhassan, H.; Taheri, Z.; Hojatnia, A.; Yeganeh, Y. T. “FunQG: Molecular Representation Learning via Quotient Graphs.” Journal of Chemical Information and Modeling 2023, 63(11), 3275–3287. Shared first author. DOI ↗ · Code ↗
Read the project case studyResearch experience
At MLGM Lab, Zahra’s work covered graph-based representation learning and molecular prediction, alongside knowledge-graph embedding and link-prediction experiments. The FunQG paper connects a mathematical quotient-graph idea to a concrete molecular learning workflow.
Earlier work at IPM focused on computational algebraic graph theory, graph invariants, and combinatorics. Postdoctoral research at Shahid Beheshti University applied GNNs and deep learning to healthcare-oriented predictive modeling and explainable AI.
Institutional context
Computational algebraic graph theory, graph invariants, and combinatorics.
Graph representation learning, molecular property prediction, knowledge-graph representation learning, and link prediction. I also served as a supervisor and advisor to multiple M.Sc. students.
Graph neural networks and deep learning for healthcare applications, representation learning, predictive modeling, and explainable AI. This period overlaps the MLGM Lab research appointment.
