Sample-Based and Feature-Based Federated Learning for Unconstrained and Constrained Nonconvex Optimization via Mini-batch SSCA

Article Computer Science, Artificial Intelligence

A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection

Qinbin Li et al.

Summary: With increasing concern about data privacy, federated learning has become a popular research topic for collaborative training of machine learning models under privacy restrictions. This survey provides a comprehensive review of federated learning systems, introducing key system components and analyzing their design. It also presents a categorization of federated learning systems based on six aspects, including data distribution, machine learning model, privacy mechanism, communication architecture, scale of federation, and motivation. The categorization can guide the design of federated learning systems, as demonstrated by the case studies. The survey summarizes existing federated learning systems and offers insights into design factors, case studies, and future research opportunities.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2023)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Optimization-Based GenQSGD for Federated Edge Learning

Yangchen Li et al.

Summary: The paper explores optimal algorithm design for federated learning in edge computing systems and introduces GenQSGD algorithm, optimizing its parameters to minimize energy cost. Numerical results demonstrate significant gains of GenQSGD over existing FL algorithms.

2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) (2021)

添加到收藏夹

Proceedings Paper Telecommunications

Sample-based Federated Learning via Mini-batch SSCA

Chencheng Ye et al.

Summary: This paper proposes privacy-preserving algorithms using stochastic successive convex approximation techniques for unconstrained and constrained sample-based federated optimization. The algorithms show inherent advantages in terms of convergence speed, communication cost, and model specification.

IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021) (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic