Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/139448
Title: Geometric and topological representations in graph neural networks
Authors: Ew, Jo Ee
Keywords: Science::Mathematics::Geometry
Science::Mathematics::Topology
Issue Date: 2020
Publisher: Nanyang Technological University
Abstract: 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.
URI: https://hdl.handle.net/10356/139448
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SPMS Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP.pdf
  Restricted Access
1.52 MBAdobe PDFView/Open

Page view(s)

241
Updated on Jun 28, 2022

Download(s) 50

58
Updated on Jun 28, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.