<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T22:28:00Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/19244" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/19244</identifier><datestamp>2025-03-26T23:34:23Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9930</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Ghodsi, Ali</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="06371784-64fe-4da1-bfc0-76ca4e5dbc39" confidence="600">Saheb Pasand, Ali</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2023-03-31T19:51:01Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-03-31T04:50:07Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2023-03-31</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2023-03-29</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/19244</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Self-supervised learning (SSL) methods have gained considerable attention in recent years&#xd;
due to their ability to learn useful representations of data without relying on labels during&#xd;
training. These methods have revolutionized research across various domains, including&#xd;
Natural Language Processing, Computer Vision, and Graph Deep Learning. SSL methods&#xd;
can be classified into three categories: Generative, Predictive, and Dual-Encoder. Among&#xd;
these, Dual-Encoder methods have gained significant popularity in many applications as, in&#xd;
contrast with generative methods, they do not require training a powerful decoder. Also, in&#xd;
contrast with predictive SSL methods, they do not need a careful design of the pre-training&#xd;
task. However, Dual-Encoder techniques suffer from collapse in representation space, since&#xd;
mapping all the samples into the same point in the embedding space is the trivial solution&#xd;
to their optimization problem. Based on their mechanisms for preventing this issue, those&#xd;
can be further divided into two classes: Contrastive and Non-Contrastive. Contrastive&#xd;
techniques prevent representation collapse using negative sampling, while Non-Contrastive&#xd;
techniques employ asymmetries such as stop-gradient or information maximization through&#xd;
Covariance/Cross-Covariance matrices whitening.&#xd;
This thesis aims to enhance two classes of Non-Contrastive Dual-Encoder SSL methods&#xd;
- Asymmetry-Based and Covariance-Based. The proposed improvements are as follows:&#xd;
&#xd;
• Covariance-Based methods: This thesis proposes techniques to enhance the effi-&#xd;
ciency and performance of Covariance-Based methods. Specifically, the invariance&#xd;
loss term’s efficiency is improved through various data sampling techniques, and&#xd;
the covariance whitening term’s efficiency is enhanced through random dimension&#xd;
selection, LSH bucketing, Nystrom approximation, and random projection. These&#xd;
techniques are thoroughly tested and validated.&#xd;
&#xd;
• Asymmetry-Based methods: This thesis enhances the performance of Asymmetry-&#xd;
Based methods by preventing rank degradation and early termination of the update&#xd;
procedure for the target network.&#xd;
&#xd;
Overall, this thesis proposes novel techniques to enhance the efficiency and performance&#xd;
of Non-Contrastive Dual-Encoder SSL methods. Proposed ideas tested and validated for&#xd;
benchmark static graph datasets. However, those are applicable to other applications and&#xd;
modalities as well.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">non-contrastive SSL</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">self-supervised learning</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Approaches and Techniques to Enhance Efficiency and Performance of Non-Contrastive Self-Supervised Learning Methods</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">David R. Cheriton School of Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Master of Mathematics</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms" lang="en">1 year</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Ghodsi, Ali</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1" lang="en">Faculty of Mathematics</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>