Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction

no code implementations • 2 Jan 2025 • Xi Yu, Tiejun Lv, Weicai Li, Wei Ni, Dusit Niyato, Ekram Hossain

The key idea is that we interpret the outputs of the intermediate feature extraction blocks of the encoder as the nodes of a graph to capture the correlations of the intermediate features.

Feature Correlation Graph Attention +1

Decentralized Federated Learning Over Imperfect Communication Channels

no code implementations • 21 May 2024 • Weicai Li, Tiejun Lv, Wei Ni, Jingbo Zhao, Ekram Hossain, H. Vincent Poor

With this knowledge, the impact of communication errors can be alleviated, allowing the convergence upper bound to decrease throughout aggregations.

Federated Learning Image Classification

Performance Bounds for Passive Sensing in Asynchronous ISAC Systems -- Appendices

no code implementations • 9 Mar 2024 • Jingbo Zhao, Zhaoming Lu, J. Andrew Zhang, Weicai Li, Yifeng Xiong, Zijun Han, Xiangming Wen, Tao Gu

This document contains the appendices for our paper titled ``Performance Bounds for Passive Sensing in Asynchronous ISAC Systems."

Multi-Carrier NOMA-Empowered Wireless Federated Learning with Optimal Power and Bandwidth Allocation

no code implementations • 13 Feb 2023 • Weicai Li, Tiejun Lv, Yashuai Cao, Wei Ni, Mugen Peng

Wireless federated learning (WFL) undergoes a communication bottleneck in uplink, limiting the number of users that can upload their local models in each global aggregation round.

Federated Learning