자료유형  

 학위논문

Control Number  

0017165081

International Standard Book Number  

9798346813828

Dewey Decimal Classification Number  

004

Main Entry-Personal Name  

Yang, Yu.

Publication, Distribution, etc. (Imprint  

[S.l.] : University of California, Los Angeles., 2024

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2024

Physical Description  

265 p.

General Note  

Source: Dissertations Abstracts International, Volume: 86-06, Section: A.

General Note  

Advisor: Mirzasoleiman, Baharan.

Dissertation Note  

Thesis (Ph.D.)--University of California, Los Angeles, 2024.

Summary, Etc.  

요약Deep learning has revolutionized fields like computer vision, natural language processing, and multimodal learning, but its reliance on large datasets brings challenges such as rising computational costs, vulnerability to data poisoning attacks, and difficulty achieving robustness against spurious correlations.My research addresses these challenges through a data-centric approach, improving data selection, curriculum design, and weighting strategies. This dissertation is organized into three parts. First, for efficient training, CREST identifies coresets for deep vision models with theoretical guarantees, and S2L reduces fine-tuning costs for large language models by prioritizing subsets based on proxy model loss trajectories. Second, for robust training against data poisoning, EPIC iteratively detects and excludes malicious examples during training, effectively mitigating the attacks. Finally, to address spurious correlations, SPARE mitigates these biases early in training by separating and rebalancing biased groups, PDE progressively expands balanced subsets to guide models toward learning core features, and a multimodal fine-tuning method enhances robustness in vision-language models like CLIP by reducing reliance on spurious features, achieving significant gains in worst-group accuracy.Together, my research demonstrates how focusing on the properties and selection of data helps address core limitations in deep learning, providing scalable and effective solutions that bridge theoretical insights with practical needs across diverse real-world applications.

Subject Added Entry-Topical Term  

Computer science.

Subject Added Entry-Topical Term  

Computer engineering.

Subject Added Entry-Topical Term  

Information science.

Index Term-Uncontrolled  

Deep learning

Index Term-Uncontrolled  

Data poisoning

Index Term-Uncontrolled  

Robust training

Index Term-Uncontrolled  

Vision-language models

Added Entry-Corporate Name  

University of California, Los Angeles Computer Science 0201

Host Item Entry  

Dissertations Abstracts International. 86-06A.

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:657862