서브메뉴
검색
Towards Efficient Federated Learning: Overcoming Challenges in Communication, Heterogeneity, and Data Scarcity
Towards Efficient Federated Learning: Overcoming Challenges in Communication, Heterogeneity, and Data Scarcity
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152016
- ISBN
- 9798382838830
- DDC
- 004
- 저자명
- Singh, Navjot.
- 서명/저자
- Towards Efficient Federated Learning: Overcoming Challenges in Communication, Heterogeneity, and Data Scarcity
- 발행사항
- [Sl] : University of California, Los Angeles, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 186 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: A.
- 주기사항
- Advisor: Diggavi, Suhas.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2024.
- 초록/해제
- 요약The rapid growth of edge computing, 5G, and IoT technologies has led to a significant increase in distributed data, creating both opportunities and challenges for machine learning. Federated learning has emerged as a promising approach to enable collaborative model training across decentralized devices while not sharing user data. However, effectively implementing federated learning involves addressing several key challenges, including data scarcity, communication efficiency, and data heterogeneity.This dissertation addresses these challenges through three key contributions. First, to enhance communication efficiency, we develop compressed stochastic gradient descent (SGD) algorithms that incorporate techniques such as event-triggered communication and local iterations. This approach reduces the frequency and size of data exchanges, minimizing communication overhead in decentralized training environments. We provide rigorous theoretical analysis to demonstrate the convergence rates and efficiency gains of these methods.Second, to further address data heterogeneity, we consider communication efficient multi-task learning for decentralized topologies. These techniques allow for the simultaneous optimization of multiple related tasks, creating personalized models tailored to the unique data distributions and objectives of individual devices while also focusing on communication efficiency of exchanges. We formulate the multi-task learning problem in decentralized settings and provide bounds on the convergence of Gradient Descent and comment on performance improvements compared to traditional methods without compression.Third, to tackle data scarcity, we leverage transfer learning methods with a focus on linear models. By utilizing pre-trained regression models from diverse source domains, we provide a robust starting point for target models and fine-tune them on limited local data. This method improves model performance and adaptability in data-scarce environments. We offer theoretical guarantees on the excess risk bounds for these transfer learning approaches, ensuring their reliability and effectiveness.Overall, these contributions seek to enhance the robustness, scalability, and practicality of federated learning, enabling effective and collaborative learning in diverse and distributed environments. This work lays the groundwork for advanced federated learning applications, addressing critical challenges and providing a path forward for future research and development.
- 일반주제명
- Computer science
- 일반주제명
- Applied mathematics
- 일반주제명
- Information science
- 키워드
- Machine learning
- 기타저자
- University of California, Los Angeles Electrical and Computer Engineering 0333
- 기본자료저록
- Dissertations Abstracts International. 85-12A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017162469
■00520250211152016
■006m o d
■007cr#unu||||||||
■020 ▼a9798382838830
■035 ▼a(MiAaPQ)AAI31331724
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aSingh, Navjot.
■24510▼aTowards Efficient Federated Learning: Overcoming Challenges in Communication, Heterogeneity, and Data Scarcity
■260 ▼a[Sl]▼bUniversity of California, Los Angeles▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a186 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: A.
■500 ▼aAdvisor: Diggavi, Suhas.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2024.
■520 ▼aThe rapid growth of edge computing, 5G, and IoT technologies has led to a significant increase in distributed data, creating both opportunities and challenges for machine learning. Federated learning has emerged as a promising approach to enable collaborative model training across decentralized devices while not sharing user data. However, effectively implementing federated learning involves addressing several key challenges, including data scarcity, communication efficiency, and data heterogeneity.This dissertation addresses these challenges through three key contributions. First, to enhance communication efficiency, we develop compressed stochastic gradient descent (SGD) algorithms that incorporate techniques such as event-triggered communication and local iterations. This approach reduces the frequency and size of data exchanges, minimizing communication overhead in decentralized training environments. We provide rigorous theoretical analysis to demonstrate the convergence rates and efficiency gains of these methods.Second, to further address data heterogeneity, we consider communication efficient multi-task learning for decentralized topologies. These techniques allow for the simultaneous optimization of multiple related tasks, creating personalized models tailored to the unique data distributions and objectives of individual devices while also focusing on communication efficiency of exchanges. We formulate the multi-task learning problem in decentralized settings and provide bounds on the convergence of Gradient Descent and comment on performance improvements compared to traditional methods without compression.Third, to tackle data scarcity, we leverage transfer learning methods with a focus on linear models. By utilizing pre-trained regression models from diverse source domains, we provide a robust starting point for target models and fine-tune them on limited local data. This method improves model performance and adaptability in data-scarce environments. We offer theoretical guarantees on the excess risk bounds for these transfer learning approaches, ensuring their reliability and effectiveness.Overall, these contributions seek to enhance the robustness, scalability, and practicality of federated learning, enabling effective and collaborative learning in diverse and distributed environments. This work lays the groundwork for advanced federated learning applications, addressing critical challenges and providing a path forward for future research and development.
■590 ▼aSchool code: 0031.
■650 4▼aComputer science
■650 4▼aApplied mathematics
■650 4▼aInformation science
■653 ▼aDecentralized optimization
■653 ▼aMachine learning
■653 ▼aTransfer learning
■653 ▼aFederated learning
■653 ▼aData heterogeneity
■690 ▼a0984
■690 ▼a0800
■690 ▼a0723
■690 ▼a0364
■71020▼aUniversity of California, Los Angeles▼bElectrical and Computer Engineering 0333.
■7730 ▼tDissertations Abstracts International▼g85-12A.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162469▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
