Ph.D. Research Proficiency Exam: Zhaoning Yu

Zhaoning Yu
Thursday, February 22, 2024 - 1:00pm
Atanasoff 223
Event Type: 

Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks


Graph Neural Networks have been widely used in feature representation learning of molecular graphs. However, most existing methods deal with molecular graphs individually while neglecting their connections, such as motif-level relationships. We propose a novel molecular graph representation learning method by constructing a heterogeneous motif graph to address this issue. In particular, we build a heterogeneous motif graph that contains motif nodes and molecular nodes. Each motif node corresponds

to a motif extracted from molecules. Then, we propose a Heterogeneous Motif Graph Neural Network (HM-GNN) to learn feature representations for each node in the heterogeneous motif graph. Our heterogeneous motif graph also enables effective multi-task learning, especially for small molecular datasets. To address the potential efficiency issue, we propose to use an edge sampler, which can significantly reduce computational resource usage.

Committee: Hongyang Gao (major professor), Ali Jannesari, Wei Le, Qi Li, and Wensheng Zhang