| Proj No. | A3184-251 |
| Title | Adversarial attacks on graph neural contrastive representation learning |
| Summary | A graph neural network (GNN) is a class of machine learning algorithms designed to handle data with an underlying graph structure. Graph representation learning has many applications, including in sensor networks, social networks, and transportation networks. GNN contrastive representation learning learns unsupervised node embedding. In this project, we study different adversarial attack mechanisms and their impact on GNN contrastive representation learning. The project requires software implementation and familiarity with Python frameworks for deep learning. |
| 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?: |