Back to search

Georgia Institute of Technology

Lifelong Machine Learning without Lifelong Data Retention

Abstract

dc:description.abstract

Machine learning models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive replay of previously seen data, which increases memory costs and may violate data privacy. To address these challenges, we first explore replacing this replay data with alternatives: (i) unlabeled data “from the wild” and (ii) synthetic data generated via model inversion. Our work using this alternative replay data boasts strong performance on replay-free continual learning for image classification. Next, we consider an alternative solution to entirely replace replay data: pre-training. Specifically, we leverage strongly pre-trained models and continuously edit them with prompts and low-rank adapters for both (i) image classification and (ii) natural-language visual reasoning. Finally, we extend the idea of continual learning using pre-trained models to the proposed setting of continual customization of text-to-image diffusion models. We hope that our work on enabling models to learn from evolving data distributions and adapt to new tasks will help unlock the full potential of machine learning in addressing emerging real-world challenges.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Interactive Computing
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Smith, James Seale
Advisor dc:contributor.advisor
  • Kira, Zsolt
Committee members dc:contributor.committeemember
  • Hays, James
  • Heck, Larry
  • Hoffman, Judy
  • Karlinsky, Leonid

Subjects

dc:subject × 4

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/73194

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Smith, James Seale. Lifelong Machine Learning without Lifelong Data Retention. Doctoral thesis, Georgia Institute of Technology, 2023. https://hdl.handle.net/1853/73194