Masked autoencoders for contrastive learning of heterogenous graphs

In this data driven society, information networks are mostly heterogenous which consists of different types of entities and relationships. Heterogenous Graph Neural Networks utilize Heterogenous graphs to study and understand the data. Since Heterogenous Graph Neural Network uses semi-supervised lea...

Full description

Saved in:
Bibliographic Details
Main Author: Srinthi Nachiyar D/O Thangamuthu
Other Authors: Lihui Chen
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/176838
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-176838
record_format dspace
spelling sg-ntu-dr.10356-1768382024-05-24T15:43:31Z Masked autoencoders for contrastive learning of heterogenous graphs Srinthi Nachiyar D/O Thangamuthu Lihui Chen School of Electrical and Electronic Engineering ELHCHEN@ntu.edu.sg Engineering Heterogenous graph masked autoencoder In this data driven society, information networks are mostly heterogenous which consists of different types of entities and relationships. Heterogenous Graph Neural Networks utilize Heterogenous graphs to study and understand the data. Since Heterogenous Graph Neural Network uses semi-supervised learning or supervised learning, it is not ideal for real-life scenarios and therefore, certain part of the data will be masked when training. Generating data specific models makes studying these models relatively easier. This allows model to be more robust, capable to work for various datasets. Therefore, it is ideal to receive ideal accuracy for this model to verify the working condition of this model. Modifying various parameters allows the accuracy to differ and knowing the right parameters is ideal. Bachelor's degree 2024-05-20T07:12:36Z 2024-05-20T07:12:36Z 2024 Final Year Project (FYP) Srinthi Nachiyar D/O Thangamuthu (2024). Masked autoencoders for contrastive learning of heterogenous graphs. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/176838 https://hdl.handle.net/10356/176838 en A3035-231 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 Engineering
Heterogenous graph masked autoencoder
spellingShingle Engineering
Heterogenous graph masked autoencoder
Srinthi Nachiyar D/O Thangamuthu
Masked autoencoders for contrastive learning of heterogenous graphs
description In this data driven society, information networks are mostly heterogenous which consists of different types of entities and relationships. Heterogenous Graph Neural Networks utilize Heterogenous graphs to study and understand the data. Since Heterogenous Graph Neural Network uses semi-supervised learning or supervised learning, it is not ideal for real-life scenarios and therefore, certain part of the data will be masked when training. Generating data specific models makes studying these models relatively easier. This allows model to be more robust, capable to work for various datasets. Therefore, it is ideal to receive ideal accuracy for this model to verify the working condition of this model. Modifying various parameters allows the accuracy to differ and knowing the right parameters is ideal.
author2 Lihui Chen
author_facet Lihui Chen
Srinthi Nachiyar D/O Thangamuthu
format Final Year Project
author Srinthi Nachiyar D/O Thangamuthu
author_sort Srinthi Nachiyar D/O Thangamuthu
title Masked autoencoders for contrastive learning of heterogenous graphs
title_short Masked autoencoders for contrastive learning of heterogenous graphs
title_full Masked autoencoders for contrastive learning of heterogenous graphs
title_fullStr Masked autoencoders for contrastive learning of heterogenous graphs
title_full_unstemmed Masked autoencoders for contrastive learning of heterogenous graphs
title_sort masked autoencoders for contrastive learning of heterogenous graphs
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/176838
_version_ 1800916389306826752