Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/227617
Title: ALGORITHMIC INDUCTIVE BIASES FOR GRAPH REPRESENTATION LEARNING
Authors: MOHAMMED HAROON DUPTY
ORCID iD:   orcid.org/0000-0002-6274-7172
Keywords: Graph Representation Learning, Graph Neural Networks, GNN Expressive Power, Probabilistic Graphical Models, Deep Learning, Artificial Intelligence
Issue Date: 23-Jan-2022
Citation: MOHAMMED HAROON DUPTY (2022-01-23). ALGORITHMIC INDUCTIVE BIASES FOR GRAPH REPRESENTATION LEARNING. ScholarBank@NUS Repository.
Abstract: Deep learning has witnessed phenomenal growth in the last decade. An important factor in the success of deep learning is the ability to encode structure in the neural network that can provide useful inductive bias in learning. However, introducing useful structures in the neural network can often be non-trivial and may need significant domain knowledge. In this thesis, we propose to use the knowledge of well-known algorithms to provide the inductive bias needed for effective learning. Algorithms usually contain simple and iteratively repeated update steps which can help in capturing inherent structure of the data as well as in sharing of parameters. We focus on graph structured data and demonstrate that Algorithmic Inductive Biases are a good tool to improve the representations learnt by Graph Neural Networks (GNNs). Our models enhance the representations learnt on graphs by improving generalization to higher-order structures and increasing the expressive power of GNNs.
URI: https://scholarbank.nus.edu.sg/handle/10635/227617
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
DuptyMH.PDF3.85 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

69
checked on Sep 29, 2022

Download(s)

17
checked on Sep 29, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.