Back to search

University of Nevada - Reno

Towards Scalable, Private and Practical Deep Learning

Abstract

dc:description.abstract

Deep Learning (DL) models have drastically improved the performance of Artificial Intelligence (AI) tasks such as image recognition, word prediction, translation, among many others, on which traditional Machine Learning (ML) models fall short. However, DL models are costly to design, train, and deploy due to their computing and memory demands. Designing DL models usually requires extensive expertise and significant manual tuning efforts. Even with the latest accelerators such as Graphics Processing Unit (GPU) and Tensor Processing Unit (TPU), training DL models can take prohibitively long time, therefore training large DL models in a distributed manner is a norm. Massive amount of data is made available thanks to the prevalence of mobile and internet-of-things (IoT) devices. However, regulations such as HIPAA and GDPR limit the access and transmission of personal data to protect security and privacy. Therefore, enabling DL model training in a decentralized but private fashion is urgent and critical. Deploying trained DL models in a real world environment usually requires meeting Quality of Service (QoS) standards, which makes adaptability of DL models an important yet challenging matter. In this dissertation, we aim to address the above challenges to make a step towards scalable, private, and practical deep learning. To simplify DL model design, we propose Efficient Progressive Neural-Architecture Search (EPNAS) and FedCust to automatically design model architectures and tune hyperparameters, respectively. To provide efficient and robust distributed training while preserving privacy, we design LEASGD, TiFL, and HDFL. We further conduct a study on the security aspect of distributed learning by focusing on how data heterogeneity affects backdoor attacks and how to mitigate such threats. Finally, we use super resolution (SR) as an example application to explore model adaptability for cross platform deployment and dynamic runtime environment. Specifically, we propose DySR and AdaSR frameworks which enable SR models to meet QoS by dynamically adapting to available resources instantly and seamlessly without excessive memory overheads.

Degree

thesis:*
Level thesis:degree_level
Doctorate Degree
Department thesis:degree_department
Computer Science
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zawad, Syed
Advisor dc:contributor.advisor
  • Yan, Feng
Committee members dc:contributor.committeemember
  • Yang, Lei
  • Zhao, Dongfang
  • Anwar, Ali
  • Shen, Haoting
  • Xu, Hao

Subjects

dc:subject × 5

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/11714/8356

Chain of custody

source
Harvested from
University of Nevada - Reno
Base URL
scholarwolf.unr.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Zawad, Syed. Towards Scalable, Private and Practical Deep Learning. Doctorate Degree thesis, 2022. http://hdl.handle.net/11714/8356