| Proj No. | A3182-251 |
| Title | Interpretable explanations for graph neural networks |
| Summary | Graph neural network (GNN) is a class of machine learning algorithms designed to handle data with an underlying graph structure. Examples include data from sensor networks, social networks, and transportation networks. Each agent in a network is represented by a vertex in a graph and connected by an edge to another agent if they are correlated. In this project, we study GNN Explainer to produce interpretable explanations for GNN-based machine learning tasks. The project will require Python implementation and testing using public datasets. |
| Supervisor | Prof Tay Wee Peng (Loc:S1 > S1 B1A > S1 B1A 01, Ext: +65 67906280) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Information System Research Lab (Loc: S2-B3a-06) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |