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
id sg-ntu-dr.10356-139448
record_format dspace
spelling sg-ntu-dr.10356-1394482023-02-28T23:16:22Z Geometric and topological representations in graph neural networks Ew, Jo Ee Xia Kelin School of Physical and Mathematical Sciences xiakelin@ntu.edu.sg Science::Mathematics::Geometry Science::Mathematics::Topology 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. Bachelor of Science in Mathematical Sciences 2020-05-19T08:51:36Z 2020-05-19T08:51:36Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/139448 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Science::Mathematics::Geometry
Science::Mathematics::Topology
spellingShingle Science::Mathematics::Geometry
Science::Mathematics::Topology
Ew, Jo Ee
Geometric and topological representations in graph neural networks
description 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.
author2 Xia Kelin
author_facet Xia Kelin
Ew, Jo Ee
format Final Year Project
author Ew, Jo Ee
author_sort Ew, Jo Ee
title Geometric and topological representations in graph neural networks
title_short Geometric and topological representations in graph neural networks
title_full Geometric and topological representations in graph neural networks
title_fullStr Geometric and topological representations in graph neural networks
title_full_unstemmed Geometric and topological representations in graph neural networks
title_sort geometric and topological representations in graph neural networks
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/139448
_version_ 1759856417847640064