no code implementations • 3 May 2024 • Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li
Federated Reinforcement Learning (FRL) offers a promising solution to various practical challenges in resource allocation for vehicle-to-everything (V2X) networks.
no code implementations • 18 Apr 2024 • Peiwen Jiang, Chao-Kai Wen, Xiao Li, Shi Jin, Geoffrey Ye Li
Considering the high speed of satellites, an adaptive encoder-decoder is proposed to protect important features and avoid frequent retransmissions.
no code implementations • 3 Apr 2024 • Khalid Albagami, Nguyen Van Huynh, Geoffrey Ye Li
Recently, deep learning (DL) has been emerging as a promising approach for channel estimation and signal detection in wireless communications.
no code implementations • 26 Mar 2024 • Bo Lin, Chuanbin Zhao, Feifei Gao, Geoffrey Ye Li
Integrated sensing and communications (ISAC) has been deemed as a key technology for the sixth generation (6G) wireless communications systems.
no code implementations • 22 Jan 2024 • Shixiong Wang, Wei Dai, Geoffrey Ye Li
This paper investigates signal estimation in wireless transmission from the perspective of statistical machine learning, where the transmitted signals may be from an integrated sensing and communication system; that is, 1) signals may be not only discrete constellation points but also arbitrary complex values; 2) signals may be spatially correlated.
no code implementations • 18 Jan 2024 • Jie Guo, Hao Chen, Bin Song, Yuhao Chi, Chau Yuen, Fei Richard Yu, Geoffrey Ye Li, Dusit Niyato
In this article, we present a novel framework, named distributed task-oriented communication networks (DTCN), based on recent advances in multimodal semantic transmission and edge intelligence.
no code implementations • 18 Dec 2023 • Yiyu Guo, Zhijin Qin, Xiaoming Tao, Geoffrey Ye Li
With recent advances in edge intelligence and deep learning, we have developed a novel multi-view synthesizing framework that can efficiently provide computation, storage, and communication resources for wireless content delivery in the metaverse.
no code implementations • 25 Nov 2023 • Chenhao Qi, Jing Wang, Leyi Lyu, Lei Tan, Jinming Zhang, Geoffrey Ye Li
The long-distance wireless signal propagation in NTNs leads to severe path loss and large latency, where the accurate acquisition of channel state information (CSI) is another challenge, especially for fast-moving non-terrestrial base stations (NTBSs).
no code implementations • 25 Nov 2023 • Kangjian Chen, Chenhao Qi, Octavia A. Dobre, Geoffrey Ye Li
Based on the SBTTS and PAOE schemes, we further compute the angle-of-arrival and angle-of-departure for the channels between the RIS and the UTs by exploiting the geometry relationship to accomplish the beam alignment of the ISAC system.
1 code implementation • 31 Oct 2023 • Shixiong Wang, Wei Dai, Haowei Wang, Geoffrey Ye Li
Therefore, we formulate robust waveform design problems by studying the worst-case channels and prove that the robustly-estimated performance is guaranteed to be attainable in real-world operation.
no code implementations • 15 Oct 2023 • Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li
In this paper, we explore resource allocation in a V2X network under the framework of federated reinforcement learning (FRL).
no code implementations • 10 Oct 2023 • BoWen Zhang, Zhijin Qin, Geoffrey Ye Li
In this article, we also investigate the data transmission methods for programmable sensors, where the performance of communication systems is evaluated by the reconstructed images or videos rather than the transmission of sensor data itself.
no code implementations • 31 Aug 2023 • Shenglong Zhou, Kaidi Xu, Geoffrey Ye Li
Compared to the centralized version, training a shared model among a large number of nodes in DFL is more challenging, as there is no central server to coordinate the training process.
1 code implementation • 9 Aug 2023 • Weixiao Wan, Wei Chen, Shiyue Wang, Geoffrey Ye Li, Bo Ai
The proposed method corresponding to these three channel reconstruction tasks employs a common DL model, which greatly reduces the overhead of model training and storage.
no code implementations • 30 Jul 2023 • Peiwen Jiang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
Simulation results demonstrate the adaptability and efficiency of the RIS-SC framework across diverse channel conditions and user requirements.
no code implementations • 6 Jul 2023 • BoWen Zhang, Zhijin Qin, Geoffrey Ye Li
According to the base CS results, the encoder then employs a policy network to analyze the semantic information in images and determines the measurement matrix for different image areas.
no code implementations • 15 May 2023 • Qiyu Hu, Yunlong Cai, Guangyi Zhang, Guanding Yu, Geoffrey Ye Li
Then, some endeavors in applying deep-unfolding approaches in next-generation advanced transceiver design are presented.
1 code implementation • 22 Mar 2023 • Kaiwen Yu, Chonghao Zhao, Gang Wu, Geoffrey Ye Li
Intelligent wireless networks have long been expected to have self-configuration and self-optimization capabilities to adapt to various environments and demands.
no code implementations • 22 Mar 2023 • Huiqiang Xie, Zhijin Qin, Geoffrey Ye Li
While semantic communication succeeds in efficiently transmitting due to the strong capability to extract the essential semantic information, it is still far from the intelligent or human-like communications.
no code implementations • 17 Feb 2023 • BoWen Zhang, Zhijin Qin, Geoffrey Ye Li
Wireless extended reality (XR) has attracted wide attentions as a promising technology to improve users' mobility and quality of experience.
no code implementations • 16 Dec 2022 • BoWen Zhang, Zhijin Qin, Yiyu Guo, Geoffrey Ye Li
In particular, semantic sensing is used to improve the sensing efficiency by exploring the spatial-temporal distributions of semantic information.
1 code implementation • 15 Dec 2022 • Kaidi Xu, Nguyen Van Huynh, Geoffrey Ye Li
To overcome these limitations, we propose a multi-agent deep reinforcement learning (MADRL) based power control scheme for the HetNet, where each access point makes power control decisions independently based on local information.
no code implementations • 13 Dec 2022 • Houssem Sifaou, Geoffrey Ye Li
Cell-free massive MIMO is emerging as a promising technology for future wireless communication systems, which is expected to offer uniform coverage and high spectral efficiency compared to classical cellular systems.
no code implementations • 8 Dec 2022 • Mengyuan Lee, Guanding Yu, Huaiyu Dai, Geoffrey Ye Li
As an efficient graph analytical tool, graph neural networks (GNNs) have special properties that are particularly fit for the characteristics and requirements of wireless communications, exhibiting good potential for the advancement of next-generation wireless communications.
no code implementations • 29 Nov 2022 • Wei Chen, Weixiao Wan, Shiyue Wang, Peng Sun, Geoffrey Ye Li, Bo Ai
The CSI is compressed via linear projections at the UE, and is recovered at the BS using deep learning (DL) with plug-and-play priors (PPP).
no code implementations • 2 Oct 2022 • Peiwen Jiang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
Therefore, the novel semantic-based coding methods and performance metrics have been investigated and the designed semantic systems consist of various modules as in the conventional communications but with improved functions.
no code implementations • 2 Sep 2022 • Ouya Wang, Jiabao Gao, Geoffrey Ye Li
Most of the existing works are based on data-driven deep learning, which requires a significant amount of training data for the communication model to adapt to new environments and results in huge computing resources for collecting data and retraining the model.
no code implementations • 29 Jun 2022 • Jiajia Guo, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
Many performance gains achieved by massive multiple-input and multiple-output depend on the accuracy of the downlink channel state information (CSI) at the transmitter (base station), which is usually obtained by estimating at the receiver (user terminal) and feeding back to the transmitter.
no code implementations • 19 Jun 2022 • HUI ZHANG, Shenglong Zhou, Geoffrey Ye Li, Naihua Xiu
The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs).
1 code implementation • 8 Jun 2022 • Qiyu Hu, Guangyi Zhang, Zhijin Qin, Yunlong Cai, Guanding Yu, Geoffrey Ye Li
Although semantic communications have exhibited satisfactory performance for a large number of tasks, the impact of semantic noise and the robustness of the systems have not been well investigated.
no code implementations • 28 May 2022 • Lei Yan, Zhijin Qin, Rui Zhang, Yongzhao Li, Geoffrey Ye Li
Specifically, an approximate measure of semantic entropy is first developed to quantify the semantic information for different tasks, based on which a novel quality-of-experience (QoE) model is proposed.
1 code implementation • IEEE Wireless Communications and Networking Conference (WCNC) 2022 • Haoran Peng, Li-Chun Wang, Geoffrey Ye Li, Ang-Hsun Tsai
Reconfigurable intelligent surface (RIS) is a promising technology for energy efficient wireless communications and has drawn significant attention recently.
no code implementations • 11 May 2022 • BoWen Zhang, Houssem Sifaou, Geoffrey Ye Li
On the other hand, considering the generality of a tracking system, we decouple the tracking system from the CSI environments so that one tracking system for all environments becomes possible.
1 code implementation • 9 May 2022 • Zhenzi Weng, Zhijin Qin, Xiaoming Tao, Chengkang Pan, Guangyi Liu, Geoffrey Ye Li
In this paper, we develop a deep learning based semantic communication system for speech transmission, named DeepSC-ST. We take the speech recognition and speech synthesis as the transmission tasks of the communication system, respectively.
no code implementations • 5 May 2022 • Houssem Sifaou, Geoffrey Ye Li
One of the main challenges of FL is the communication overhead, where the model updates of the participating clients are sent to the central server at each global training round.
1 code implementation • 3 May 2022 • Shenglong Zhou, Geoffrey Ye Li
Federated learning has shown its advances recently but is still facing many challenges, such as how algorithms save communication resources and reduce computational costs, and whether they converge.
1 code implementation • 22 Apr 2022 • Shenglong Zhou, Geoffrey Ye Li
One of the crucial issues in federated learning is how to develop efficient optimization algorithms.
no code implementations • 20 Apr 2022 • Zhixiong Chen, Wenqiang Yi, Arumugam Nallanathan, Geoffrey Ye Li
On this basis, we maximize the scheduled data size to minimize the global loss function through jointly optimize the device scheduling, bandwidth allocation, computation and communication time division policies with the assistance of Lyapunov optimization.
no code implementations • 16 Apr 2022 • Peiwen Jiang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
In this paper, we initially establish a basal semantic video conferencing (SVC) network, which dramatically reduces transmission resources while only losing detailed expressions.
no code implementations • 12 Mar 2022 • Zhaohui Li, Chenhao Qi, Geoffrey Ye Li
To develop a low-complexity multicast beamforming method for millimeter wave communications, we first propose a channel gain estimation method in this article.
no code implementations • 7 Feb 2022 • Qiyu Hu, Guangyi Zhang, Zhijin Qin, Yunlong Cai, Guanding Yu, Geoffrey Ye Li
In this paper, we first propose a framework for the robust end-to-end semantic communication systems to combat the semantic noise.
1 code implementation • 16 Jan 2022 • Lei Yan, Zhijin Qin, Rui Zhang, Yongzhao Li, Geoffrey Ye Li
Semantic communications have shown its great potential to improve the transmission reliability, especially in the low signal-to-noise regime.
no code implementations • 30 Dec 2021 • Zhijin Qin, Xiaoming Tao, Jianhua Lu, Wen Tong, Geoffrey Ye Li
Semantic communication, regarded as the breakthrough beyond the Shannon paradigm, aims at the successful transmission of semantic information conveyed by the source rather than the accurate reception of each single symbol or bit regardless of its meaning.
no code implementations • 4 Dec 2021 • Yanzhen Liu, Qiyu Hu, Yunlong Cai, Guanding Yu, Geoffrey Ye Li
Moreover, due to the high computational complexity caused by the matrix inversion computation in the SSCA-based optimization algorithm, we further develop a deep-unfolding neural network (NN) to address this issue.
no code implementations • 21 Nov 2021 • Xinyu Wei, Biing-Hwang Fred Juang, Ouya Wang, Shenglong Zhou, Geoffrey Ye Li
In this paper, we propose a new learning method named Accretionary Learning (AL) to emulate human learning, in that the set of objects to be recognized may not be pre-specified.
no code implementations • 1 Nov 2021 • Houssem Sifaou, Geoffrey Ye Li
This paper investigates the robustness of over-the-air federated learning to Byzantine attacks.
1 code implementation • 28 Oct 2021 • Shenglong Zhou, Geoffrey Ye Li
Federated learning has shown its advances over the last few years but is facing many challenges, such as how algorithms save communication resources, how they reduce computational costs, and whether they converge.
no code implementations • 16 Aug 2021 • Huiqiang Xie, Zhijin Qin, Geoffrey Ye Li
In this letter, we consider a task-oriented multi-user semantic communication system for multimodal data transmission.
no code implementations • 22 Jul 2021 • Zhenzi Weng, Zhijin Qin, Geoffrey Ye Li
The traditional communications transmit all the source data represented by bits, regardless of the content of source and the semantic information required by the receiver.
no code implementations • 6 Jun 2021 • Peiwen Jiang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
Even if semantic communication has been successfully applied in the sentence transmission to reduce semantic errors, existing architecture is usually fixed in the codeword length and is inefficient and inflexible for the varying sentence length.
no code implementations • 21 May 2021 • Muhan Chen, Jiajia Guo, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li, Ang Yang
By using environment information, the NNs can achieve a more refined mapping between the precoding matrix and the PMI compared with codebooks.
no code implementations • 28 Apr 2021 • Weijie Jin, Hengtao He, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
Channel estimation in wideband millimeter-wave (mmWave) systems is very challenging due to the beam squint effect.
no code implementations • 23 Apr 2021 • Shen Gao, Peihao Dong, Zhiwen Pan, Geoffrey Ye Li
This article aims to reduce huge pilot overhead when estimating the reconfigurable intelligent surface (RIS) relayed wireless channel.
no code implementations • 5 Mar 2021 • Wankai Tang, Xiangyu Chen, Ming Zheng Chen, Jun Yan Dai, Yu Han, Shi Jin, Qiang Cheng, Geoffrey Ye Li, Tie Jun Cui
Channel reciprocity greatly facilitates downlink precoding in time-division duplexing (TDD) multiple-input multiple-output (MIMO) communications without the need for channel state information (CSI) feedback.
Information Theory Information Theory
1 code implementation • 12 Jan 2021 • Chang-Jen Wang, Chao-Kai Wen, Shang-Ho, Tsai, Shi Jin, Geoffrey Ye Li
In particular, we introduce a hypernetwork to generate the damping factors for GEC-SR.
no code implementations • 9 Dec 2020 • Zhenzi Weng, Zhijin Qin, Geoffrey Ye Li
We consider a semantic communication system for speech signals, named DeepSC-S.
no code implementations • 6 Sep 2020 • Chenghong Bian, Yuwen Yang, Feifei Gao, Geoffrey Ye Li
In this paper, we propose a new downlink beamforming strategy for mmWave communications using uplink sub-6GHz channel information and a very few mmWave pilots.
no code implementations • 17 Aug 2020 • Yuyao Sun, Wei Xu, Lisheng Fan, Geoffrey Ye Li, George K. Karagiannidis
Accurate channel state information (CSI) feedback plays a vital role in improving the performance gain of massive multiple-input multiple-output (m-MIMO) systems, where the dilemma is excessive CSI overhead versus limited feedback bandwith.
no code implementations • 3 Jul 2020 • Ying-Chang Liang, Qianqian Zhang, Erik G. Larsson, Geoffrey Ye Li
To exploit the full potential of SR, in this paper, we address three fundamental tasks in SR: (1) enhancing the backscattering link via active load; (2) achieving highly reliable communications through joint decoding; and (3) capturing PTx's RF signals using reconfigurable intelligent surfaces.
no code implementations • 30 Jun 2020 • Hengtao He, Rui Wang, Weijie Jin, Shi Jin, Chao-Kai Wen, Geoffrey Ye Li
By utilizing the Stein's unbiased risk estimator loss, the LDGEC network can be trained only with limited measurements corresponding to the pilot symbols, instead of the real channel data.
no code implementations • 18 Jun 2020 • Huiqiang Xie, Zhijin Qin, Geoffrey Ye Li, Biing-Hwang Juang
To justify the performance of semantic communications accurately, we also initialize a new metric, named sentence similarity.
no code implementations • 16 Jun 2020 • Chenhao Qi, Peihao Dong, Wenyan Ma, Hua Zhang, Zaichen Zhang, Geoffrey Ye Li
The accuracy of channel state information (CSI) acquisition directly affects the performance of millimeter wave (mmWave) communications.
no code implementations • 16 Jun 2020 • Yunfeng He, Jing Zhang, Shi Jin, Chao-Kai Wen, Geoffrey Ye Li
The TurboNet inherits the superiority of the max-log-MAP algorithm and DL tools and thus presents excellent error-correction capability with low training cost.
1 code implementation • 5 Jun 2020 • Peihao Dong, Hua Zhang, Geoffrey Ye Li
For millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid processing architecture is essential to significantly reduce the complexity and cost but is quite challenging to be jointly optimized over the transmitter and receiver.
no code implementations • 11 May 2020 • Zhijin Qin, Geoffrey Ye Li, Hao Ye
In contrast to other machine learning tools that require no communication resources, federated learning exploits communications between the central server and the distributed local clients to train and optimize a machine learning model.
Information Theory Signal Processing Information Theory
no code implementations • 2 May 2020 • Mohamed A. ElMossallamy, Hongliang Zhang, Lingyang Song, Karim G. Seddik, Zhu Han, Geoffrey Ye Li
Recently there has been a flurry of research on the use of reconfigurable intelligent surfaces (RIS) in wireless networks to create smart radio environments.
no code implementations • 8 Mar 2020 • Shen Gao, Peihao Dong, Zhiwen Pan, Geoffrey Ye Li
For ultra-dense networks with wireless backhaul, caching strategy at small base stations (SBSs), usually with limited storage, is critical to meet massive high data rate requests.
no code implementations • 6 Mar 2020 • Jiajia Guo, Xi Yang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
These enhancements are tasked with the precise retrieval and fusion of shared and individual data.
Information Theory Signal Processing Information Theory
no code implementations • 12 Aug 2019 • Liang Wang, Hao Ye, Le Liang, Geoffrey Ye Li
The centralized decision unit employs a deep Q-network to allocate resources and then sends the decision results to all vehicles.
no code implementations • 31 Jul 2019 • Jiajia Guo, Jinghe Wang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
Deep learning (DL) has achieved great success in signal processing and communications and has become a promising technology for future wireless communications.
Information Theory Signal Processing Information Theory
no code implementations • 30 Jul 2019 • Liang Wang, Hao Ye, Le Liang, Geoffrey Ye Li
Meanwhile, there exists an optimal number of continuous feedback and binary feedback, respectively.
no code implementations • 22 Jul 2019 • Hengtao He, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
In this paper, we investigate the model-driven deep learning (DL) for MIMO detection.
no code implementations • 7 Jul 2019 • Le Liang, Hao Ye, Guanding Yu, Geoffrey Ye Li
The traditional wisdom is to explicitly formulate resource allocation as an optimization problem and then exploit mathematical programming to solve the problem to a certain level of optimality.
1 code implementation • 14 Jun 2019 • Jiajia Guo, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
Massive multiple-input multiple-output (MIMO) is a promising technology to increase link capacity and energy efficiency.
Signal Processing Information Theory Information Theory
1 code implementation • 7 Jun 2019 • Mengyuan Lee, Guanding Yu, Geoffrey Ye Li
In this paper, we propose a novel graph embedding based method for link scheduling in D2D networks.
1 code implementation • 8 May 2019 • Le Liang, Hao Ye, Geoffrey Ye Li
This paper investigates the spectrum sharing problem in vehicular networks based on multi-agent reinforcement learning, where multiple vehicle-to-vehicle (V2V) links reuse the frequency spectrum preoccupied by vehicle-to-infrastructure (V2I) links.
Information Theory Information Theory
no code implementations • 4 May 2019 • Jing Zhang, Hengtao He, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
The DL-OAMP receiver includes a channel estimation neural network (CE-Net) and a signal detection neural network based on OAMP, called OAMP-Net.
no code implementations • 12 Mar 2019 • Jing Zhang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
The AI receiver includes a channel estimation neural network (CE-NET) and a signal detection neural network based on orthogonal approximate message passing (OAMP), called OAMP-NET.
Information Theory Information Theory
no code implementations • 6 Mar 2019 • Hao Ye, Le Liang, Geoffrey Ye Li, Biing-Hwang Fred Juang
We propose to use a conditional generative adversarial net (GAN) to represent channel effects and to bridge the transmitter DNN and the receiver DNN so that the gradient of the transmitter DNN can be back-propagated from the receiver DNN.
Information Theory Information Theory
1 code implementation • 5 Mar 2019 • Mengyuan Lee, Guanding Yu, Geoffrey Ye Li
Moreover, we develop a mixed training strategy to further reinforce the generalization ability and a deep neural network (DNN) with a novel loss function to achieve better dynamic control over optimality and computational complexity.
Information Theory Information Theory
no code implementations • 17 Dec 2018 • Peiwen Jiang, Tianqi Wang, Bin Han, Xuanxuan Gao, Jing Zhang, Chao-Kai Wen, Shi Jin, Geoffrey Ye Li
From the OTA test, the AI-aided OFDM receivers, especially the SwitchNet receiver, are robust to real environments and promising for future communication systems.
no code implementations • 17 Sep 2018 • Hengtao He, Shi Jin, Chao-Kai Wen, Feifei Gao, Geoffrey Ye Li, Zongben Xu
Intelligent communication is gradually considered as the mainstream direction in future wireless communications.
no code implementations • 2 Jul 2018 • Hao Ye, Geoffrey Ye Li, Biing-Hwang Fred Juang, Kathiravetpillai Sivanesan
In this article, we use deep neural networks (DNNs) to develop a wireless end-to-end communication system, in which DNNs are employed for all signal-related functionalities, such as encoding, decoding, modulation, and equalization.
Information Theory Information Theory
no code implementations • 1 Apr 2018 • Le Liang, Hao Ye, Geoffrey Ye Li
As wireless networks evolve towards high mobility and providing better support for connected vehicles, a number of new challenges arise due to the resulting high dynamics in vehicular environments and thus motive rethinking of traditional wireless design methodologies.