Efficient and reliable overlay networks for decentralized federated learning

DOI10.1137/21M1465081MaRDI QIDQ5102155zbMATH OpenOpenAlexFDO

Authors Yifan Hua, Kevin C. Miller, Chen Qian, Bao Wang, Andrea L. Bertozzi

Publication date 6 September 2022

Published in SIAM Journal on Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2112.15486

zbMATH Keywords

decentralized federated learningoverlay networksrandom graphs

Mathematics Subject Classification ID

Acceleration of convergence in numerical analysis (65B99) General topics in artificial intelligence (68T01) Computational aspects of data analysis and big data (68T09) Distributed algorithms (68W15)

Recommendations

• Distributed multi-task classification: a decentralized online learning approach
• Utility optimization of federated learning with differential privacy
• GADMM: fast and communication efficient framework for distributed machine learning
• Online learning over a decentralized network through ADMM
• Privacy-preserving federated learning on lattice quantization

Cites work

• An Elementary Construction of Constant-Degree Expanders
• Distributed Subgradient Methods for Multi-Agent Optimization
• Eigenvalues and expanders
• Expander codes
• Expander graphs and their applications
• Expander graphs in pure and applied mathematics
• Explicit expanders of every degree and size
• Fastest Mixing Markov Chain on a Graph
• scientific article; zbMATH DE number 3168330 (Why is no real title available?)
• scientific article; zbMATH DE number 2042680 (Why is no real title available?)
• scientific article; zbMATH DE number 1552123 (Why is no real title available?)
• scientific article; zbMATH DE number 3417498 (Why is no real title available?)
• scientific article; zbMATH DE number 964896 (Why is no real title available?)
• Laplacians and the Cheeger inequality for directed graphs
• Learnability, stability and uniform convergence
• On the convergence of decentralized gradient descent
• Ramanujan graphs: an introduction
• Some methods of speeding up the convergence of iteration methods
• Stability of randomized learning algorithms
• The error-feedback framework: SGD with delayed gradients

Cited in

(6)

• Over-the-Air computation for distributed machine learning and consensus in large wireless networks
• Decentralized personalized federated learning: lower bounds and optimal algorithm for all personalization modes
• Federated Optimization Under Intermittent Client Availability
• DeFTA: a plug-and-play peer-to-peer decentralized federated learning framework
• Review of mathematical optimization in federated learning
• Network alternating direction method of multipliers for ultrahigh-dimensional decentralised federated learning

This page was built for publication: Efficient and reliable overlay networks for decentralized federated learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5102155)