activity
20242026
collaborators
Showing eess.SPShow all

5 papers · 1 filter

eess.SP2026

Event-Triggered Gossip for Distributed Learning

Zhiyuan Zhai, Xiaojun Yuan, Wei Ni +3

While distributed learning offers a new learning paradigm for distributed network with no central coordination, it is constrained by communication bottleneck between nodes. We deve…

eess.SP2025

Learning Performance Optimization for Edge AI System with Time and Energy Constraints

Zhiyuan Zhai, Wei Ni, Xin Wang

Edge AI, which brings artificial intelligence to the edge of the network for real-time processing and decision-making, has emerged as a transformative technology across various app…

eess.SP2025

Spectral-Convergent Decentralized Machine Learning: Theory and Application in Space Networks

Zhiyuan Zhai, Shuyan Hu, Wei Ni +2

Decentralized machine learning (DML) supports collaborative training in large-scale networks with no central server. It is sensitive to the quality and reliability of inter-device…

eess.SP2025

Integrated Sensing and Communication with UAV Swarms via Decentralized Consensus ADMM

Zhiyuan Zhai, Wei Ni, Xin Wang +2

UAV swarms can form virtual antenna arrays to exploit additional spatial degrees of freedom and enhance integrated sensing and communication (ISAC). The optimization of UAV positio…

eess.SP2024

FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks

Bingnan Xiao, Jingjing Zhang, Wei Ni +1

Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper pre…