Towards Data-efficient Graph Learning

dc.contributor.advisorMoshkov, Mikhail
dc.contributor.advisorZhang, Xiangliang
dc.contributor.authorZhang, Qiannan
dc.contributor.committeememberKeyes, David E.
dc.contributor.committeememberElhoseiny, Mohamed
dc.contributor.committeememberLiu, Huan
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.date.accessioned2023-05-18T13:22:07Z
dc.date.available2023-05-18T13:22:07Z
dc.date.issued2023-05
dc.description.abstractGraphs are commonly employed to model complex data and discover latent patterns and relationships between entities in the real world. Canonical graph learning models have achieved remarkable progress in modeling and inference on graph-structured data that consists of nodes connected by edges. Generally, they leverage abundant labeled data for model training and thus inevitably suffer from the label scarcity issue due to the expense and hardship of data annotation in practice. Data-efficient graph learning attempts to address the prevailing data scarcity issue in graph mining problems, of which the key idea is to transfer knowledge from the related resources to obtain the models with good generalizability to the target graph-related tasks with mere annotations. However, the generalization of the models to data-scarce scenarios is faced with challenges including 1) dealing with graph structure and structural heterogeneity to extract transferable knowledge; 2) selecting beneficial and fine-grained knowledge for effective transfer; 3) addressing the divergence across different resources to promote knowledge transfer. Motivated by the aforementioned challenges, the dissertation mainly focuses on three perspectives, i.e., knowledge extraction with graph heterogeneity, knowledge selection, and knowledge transfer. The purposed models are applied to various node classification and graph classification tasks in the low-data regimes, evaluated on a variety of datasets, and have shown their effectiveness compared with the state-of-the-art baselines.
dc.identifier.citationZhang, Q. (2023). Towards Data-efficient Graph Learning [KAUST Research Repository]. https://doi.org/10.25781/KAUST-3T559
dc.identifier.doi10.25781/KAUST-3T559
dc.identifier.orcid0000-0003-1601-1217
dc.identifier.urihttp://hdl.handle.net/10754/691807
dc.language.isoen
dc.person.id155686
dc.relation.issupplementedbyN/A
dc.rights.accessrightsAt the time of archiving, the student author of this dissertation opted to temporarily restrict access to it. The full text of this dissertation will become available to the public after the expiration of the embargo on 2024-05-18.
dc.rights.embargodate2024-05-18
dc.subjectGraph learning
dc.subjectfew-shot learning
dc.subjectheterogeneous graph learning
dc.titleTowards Data-efficient Graph Learning
dc.typeDissertation
display.details.left<span><h5>Embargo End Date</h5>2024-05-18<br><br><h5>Type</h5>Dissertation<br><br><h5>Authors</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0003-1601-1217&spc.sf=dc.date.issued&spc.sd=DESC">Zhang, Qiannan</a> <a href="https://orcid.org/0000-0003-1601-1217" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>Advisors</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0003-0085-9483&spc.sf=dc.date.issued&spc.sd=DESC">Moshkov, Mikhail</a> <a href="https://orcid.org/0000-0003-0085-9483" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-3574-5665&spc.sf=dc.date.issued&spc.sd=DESC">Zhang, Xiangliang</a> <a href="https://orcid.org/0000-0002-3574-5665" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>Committee Members</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-4052-7224&spc.sf=dc.date.issued&spc.sd=DESC">Keyes, David E.</a> <a href="https://orcid.org/0000-0002-4052-7224" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0001-9659-1551&spc.sf=dc.date.issued&spc.sd=DESC">Elhoseiny, Mohamed</a> <a href="https://orcid.org/0000-0001-9659-1551" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br>Liu, Huan<br><br><h5>Program</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.program=Computer Science,equals">Computer Science</a><br><br><h5>KAUST Department</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division,equals">Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division</a><br><br><h5>Date</h5>2023-05</span>
display.details.right<span><h5>Access Restrictions</h5>At the time of archiving, the student author of this dissertation opted to temporarily restrict access to it. The full text of this dissertation will become available to the public after the expiration of the embargo on 2024-05-18.<br><br><h5>Abstract</h5>Graphs are commonly employed to model complex data and discover latent patterns and relationships between entities in the real world. Canonical graph learning models have achieved remarkable progress in modeling and inference on graph-structured data that consists of nodes connected by edges. Generally, they leverage abundant labeled data for model training and thus inevitably suffer from the label scarcity issue due to the expense and hardship of data annotation in practice. Data-efficient graph learning attempts to address the prevailing data scarcity issue in graph mining problems, of which the key idea is to transfer knowledge from the related resources to obtain the models with good generalizability to the target graph-related tasks with mere annotations. However, the generalization of the models to data-scarce scenarios is faced with challenges including 1) dealing with graph structure and structural heterogeneity to extract transferable knowledge; 2) selecting beneficial and fine-grained knowledge for effective transfer; 3) addressing the divergence across different resources to promote knowledge transfer. Motivated by the aforementioned challenges, the dissertation mainly focuses on three perspectives, i.e., knowledge extraction with graph heterogeneity, knowledge selection, and knowledge transfer. The purposed models are applied to various node classification and graph classification tasks in the low-data regimes, evaluated on a variety of datasets, and have shown their effectiveness compared with the state-of-the-art baselines.<br><br><h5>Citation</h5>Zhang, Q. (2023). Towards Data-efficient Graph Learning [KAUST Research Repository]. https://doi.org/10.25781/KAUST-3T559<br><br><h5>DOI</h5><a href="https://doi.org/10.25781/KAUST-3T559">10.25781/KAUST-3T559</a></span>
kaust.availability.selectionEmbargo the work for one year and then release for public access* on the internet through the KAUST Repository.
kaust.gpcaida.hoteit@kaust.edu.sa
kaust.request.doiyes
kaust.thesis.readyToSubmitYes, I confirm that I am ready to upload the following 3 documents (in PDF format): 1) Final thesis or dissertation. 2) Completed Defense Results form showing “pass” or “pass with conditions”. 3) Final Advisor Approval confirmation email (received after advisor completed the digital form).
orcid.id0000-0001-9659-1551
orcid.id0000-0002-4052-7224
orcid.id0000-0002-3574-5665
orcid.id0000-0003-0085-9483
orcid.id0000-0003-1601-1217
thesis.degree.disciplineComputer Science
thesis.degree.grantorKing Abdullah University of Science and Technology
thesis.degree.nameDoctor of Philosophy
Files
Original bundle
Now showing 1 - 3 of 3
Name:
Final Approval Form 155686 Qiannan Zhang PhD.pdf
Size:
103.51 KB
Format:
Adobe Portable Document Format
Description:
Final Advisor Approval Confirmation Email
Name:
signed_qiannan_m-sc-thesis-and-ph-d-result-form-1.pdf
Size:
367.68 KB
Format:
Adobe Portable Document Format
Description:
Defense Results Form
Name:
Formatted_Thesis_QZ.pdf
Size:
3.31 MB
Format:
Adobe Portable Document Format
Description:
PhD Dissertation
License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
919 B
Format:
Item-specific license agreed upon to submission
Description: