no code implementations • 6 May 2024 • Nan Xue, Yaping Sun, Zhiyong Chen, Meixia Tao, Xiaodong Xu, Liang Qian, Shuguang Cui, Ping Zhang
In this paper, we propose a wireless distributed LLMs paradigm based on Mixture of Experts (MoE), named WDMoE, deploying LLMs collaboratively across edge servers of base station (BS) and mobile devices in the wireless communications system.
no code implementations • 10 Dec 2023 • Junyi Yang, Weifeng Zhu, Shu Sun, Xiaofeng Li, Xingqin Lin, Meixia Tao
This letter considers the transceiver design in frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems for high-quality data transmission.
no code implementations • 6 Nov 2023 • Xingchen Liu, Liuxun Xue, Shu Sun, Meixia Tao
In satellite-to-ground communication, ensuring reliable and efficient connectivity poses significant challenges.
no code implementations • 23 Sep 2023 • Shu Sun, Renwang Li, Xingchen Liu, Liuxun Xue, Chong Han, Meixia Tao
Future wireless communication systems are likely to adopt extremely large aperture arrays and millimeter-wave/sub-THz frequency bands to achieve higher throughput, lower latency, and higher energy efficiency.
no code implementations • 23 Aug 2023 • Junyi Yang, Weifeng Zhu, Meixia Tao, Shu Sun
Fast and precise beam alignment is crucial for high-quality data transmission in millimeter-wave (mmWave) communication systems, where large-scale antenna arrays are utilized to overcome the severe propagation loss.
no code implementations • 4 May 2023 • Yuanming Shi, Shuhao Xia, Yong Zhou, Yijie Mao, Chunxiao Jiang, Meixia Tao
To improve the learning performance, we establish a system optimization framework by joint transceiver and fronthaul quantization design, for which successive convex approximation and alternate convex search based system optimization algorithms are developed.
no code implementations • 19 Apr 2023 • Weifeng Zhu, Meixia Tao, Xiaojun Yuan, Fan Xu, Yunfeng Guan
This paper investigates the problem of activity detection and channel estimation in cooperative multi-cell massive access systems with temporally correlated activity, where all access points (APs) are connected to a central unit via fronthaul links.
no code implementations • 8 Sep 2022 • Junyi Yang, Weifeng Zhu, Meixia Tao
In this work, we propose a novel deep learning based hierarchical beam alignment method that learns two tiers of probing codebooks (PCs) and uses their measurements to predict the optimal beam in a coarse-to-fine searching manner.
no code implementations • 2 Sep 2022 • Benshun Yin, Zhiyong Chen, Meixia Tao
In contrast, split learning (SL) can reduce the computing load of devices by using model splitting and assignment, but increase the communication burden to transmit intermediate results.
no code implementations • 11 Aug 2022 • Yufei Bo, Yiheng Duan, Shuo Shao, Meixia Tao
The intrinsic mechanism of neural network based digital modulation is mapping continuous output of the neural network encoder into discrete constellation symbols, which is a non-differentiable function that cannot be trained with existing gradient descend algorithms.
no code implementations • 28 Jun 2022 • Naifu Zhang, Meixia Tao, Jia Wang, Fan Xu
One of the main focuses in distributed learning is communication efficiency, since model aggregation at each round of training can consist of millions to billions of parameters.
no code implementations • 16 May 2022 • Weifeng Zhu, Meixia Tao, Yunfeng Guan
This letter considers temporal-correlated massive access, where each device, once activated, is likely to transmit continuously over several consecutive frames.
1 code implementation • 30 Apr 2022 • Hongwei Zhang, Shuo Shao, Meixia Tao, Xiaoyan Bi, Khaled B. Letaief
In practice, the semantic information is defined by the pragmatic task of the receiver and cannot be known to the transmitter.
no code implementations • 21 Jan 2021 • Naifu Zhang, Meixia Tao, Jia Wang
In FL, however, the model update is an indirect multi-terminal source coding problem, also called as the CEO problem where each edge device cannot observe directly the gradient that is to be reconstructed at the decoder, but is rather provided only with a noisy version.
no code implementations • 21 Aug 2020 • Zhe Zhang, Meixia Tao
This approach, on one hand, can learn the caching policy in continuous action space by using the actor-critic architecture.
no code implementations • 4 Mar 2020 • Naifu Zhang, Meixia Tao
We obtain the optimal policy in closed form when gradient statistics are given.