Geometric and topological representations in graph neural networks

• Main Author: Ew, Jo Ee
• Other Authors: Xia Kelin
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Science::Mathematics::Geometry; Science::Mathematics::Topology
• Online Access: https://hdl.handle.net/10356/139448
• Institution: Nanyang Technological University

Graph Neural Networks (GNNs) show impressive performance in link-prediction analysis and node classification problems as compared to other neural network approaches. In this paper, the geometric and topological structures of various kinds of node embedding GNNs such as basic GNN, Graph Convolutional...