Geometric and topological representations in graph neural networks

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...

Full description

Saved in:
Bibliographic Details
Main Author: Ew, Jo Ee
Other Authors: Xia Kelin
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2020
Subjects:
Online Access:https://hdl.handle.net/10356/139448
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary: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 Network (GCN), Graph SAmple and aggreGatE (Graph SAGE), and Gated GNN are investigated. Interpretation and comparison between these models are made to provide better comprehension. Sub-graph embedding which is a relatively recent approach is also mentioned in the paper. In particular, two GCN models, i.e. Decagon and convolution spatial graph embedding network (C-SGEN), are studied. In order to enhance the models mentioned, some future works are suggested.