A prototype-oriented framework for deep transfer learning applications

Simple item page
dc.contributor.advisorZhou, Mingyuan (Assistant professor)
dc.contributor.committeeMemberMueller, Peter
dc.contributor.committeeMemberHo, Nhat
dc.contributor.committeeMemberQian, Xiaoning
dc.creatorTanwisuth, Korawat
dc.creator.orcid0009-0003-5875-5414
dc.date.accessioned2023-07-12T03:54:44Z
dc.date.available2023-07-12T03:54:44Z
dc.date.created2023-05
dc.date.issued2023-04-05
dc.date.submittedMay 2023
dc.date.updated2023-07-12T03:54:45Z
dc.description.abstractDeep learning models achieve state-of-the-art performance in many applications but often require large-scale data. Deep transfer learning studies the ability of deep learning models to transfer knowledge from source tasks to related target tasks, enabling data-efficient learning. This dissertation develops novel methodologies that tackle three different transfer learning applications for deep learning models: unsupervised domain adaptation, unsupervised fine-tuning, and source-private clustering. The key idea behind the proposed methods relies on minimizing the distributional discrepancy between the prototypes and target data with the transport framework. For each scenario, we design our algorithms to suit different data and model requirements. In unsupervised domain adaptation, we leverage the source domain data to construct class prototypes and minimize the transport cost between the prototypes and target data. In unsupervised fine-tuning, we apply our framework to prompt-based zero-shot learning to adapt large pre-trained models directly on the target data, bypassing the source data requirement. In source-private clustering, we incorporate a knowledge distillation framework with our prototype-oriented clustering to address the problem of data and model privacy. All three approaches show consistent performance gains over the baselines.
dc.description.departmentStatistics
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/2152/120443
dc.identifier.urihttp://dx.doi.org/10.26153/tsw/47308
dc.language.isoen
dc.subjectDeep learning
dc.subjectTransfer learning
dc.subjectDomain adaptation
dc.subjectDistribution matching
dc.subjectPre-trained model
dc.subjectOptimal transport
dc.subjectClassification
dc.subjectClustering
dc.titleA prototype-oriented framework for deep transfer learning applications
dc.typeThesis
dc.type.materialtext
thesis.degree.departmentStatistics
thesis.degree.disciplineStatistics
thesis.degree.grantorThe University of Texas at Austin
thesis.degree.levelDoctoral
thesis.degree.nameDoctor of Philosophy

Access full-text files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
TANWISUTH-DISSERTATION-2023.pdf
Size:
9.56 MB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.46 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.85 KB
Format:
Plain Text
Description:
Download

Collections

UT Electronic Theses and Dissertations