Alert button
Picture for Xudong Zhang

Xudong Zhang

Alert button

Data Augmentation of Bridging the Delay Gap for DL-based Massive MIMO CSI Feedback

Aug 01, 2023
Hengyu Zhang, Zhilin Lu, Xudong Zhang, Jintao Wang

Figure 1 for Data Augmentation of Bridging the Delay Gap for DL-based Massive MIMO CSI Feedback
Figure 2 for Data Augmentation of Bridging the Delay Gap for DL-based Massive MIMO CSI Feedback
Figure 3 for Data Augmentation of Bridging the Delay Gap for DL-based Massive MIMO CSI Feedback
Figure 4 for Data Augmentation of Bridging the Delay Gap for DL-based Massive MIMO CSI Feedback

In massive multiple-input multiple-output (MIMO) systems under the frequency division duplexing (FDD) mode, the user equipment (UE) needs to feed channel state information (CSI) back to the base station (BS). Though deep learning approaches have made a hit in the CSI feedback problem, whether they can remain excellent in actual environments needs to be further investigated. In this letter, we point out that the real-time dataset in application often has the domain gap from the training dataset caused by the time delay. To bridge the gap, we propose bubble-shift (B-S) data augmentation, which attempts to offset performance degradation by changing the delay and remaining the channel information as much as possible. Moreover, random-generation (R-G) data augmentation is especially proposed for outdoor scenarios due to the complex distribution of its channels. It generalizes the characteristics of the channel matrix and alleviates the over-fitting problem. Simulation results show that the proposed data augmentation boosts the robustness of networks in both indoor and outdoor environments. The open source codes are available at https://github.com/zhanghy23/CRNet-Aug.

Viaarxiv icon

SGL: Structure Guidance Learning for Camera Localization

Apr 12, 2023
Xudong Zhang, Shuang Gao, Xiaohu Nan, Haikuan Ning, Yuchen Yang, Yishan Ping, Jixiang Wan, Shuzhou Dong, Jijunnan Li, Yandong Guo

Figure 1 for SGL: Structure Guidance Learning for Camera Localization
Figure 2 for SGL: Structure Guidance Learning for Camera Localization
Figure 3 for SGL: Structure Guidance Learning for Camera Localization
Figure 4 for SGL: Structure Guidance Learning for Camera Localization

Camera localization is a classical computer vision task that serves various Artificial Intelligence and Robotics applications. With the rapid developments of Deep Neural Networks (DNNs), end-to-end visual localization methods are prosperous in recent years. In this work, we focus on the scene coordinate prediction ones and propose a network architecture named as Structure Guidance Learning (SGL) which utilizes the receptive branch and the structure branch to extract both high-level and low-level features to estimate the 3D coordinates. We design a confidence strategy to refine and filter the predicted 3D observations, which enables us to estimate the camera poses by employing the Perspective-n-Point (PnP) with RANSAC. In the training part, we design the Bundle Adjustment trainer to help the network fit the scenes better. Comparisons with some state-of-the-art (SOTA) methods and sufficient ablation experiments confirm the validity of our proposed architecture.

Viaarxiv icon

Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help

Feb 18, 2023
Yunbo Qiu, Yue Jin, Lebin Yu, Jian Wang, Xudong Zhang

Figure 1 for Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help
Figure 2 for Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help
Figure 3 for Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help
Figure 4 for Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help

Multi-agent reinforcement learning (MARL) has achieved great progress in cooperative tasks in recent years. However, in the local reward scheme, where only local rewards for each agent are given without global rewards shared by all the agents, traditional MARL algorithms lack sufficient consideration of agents' mutual influence. In cooperative tasks, agents' mutual influence is especially important since agents are supposed to coordinate to achieve better performance. In this paper, we propose a novel algorithm Mutual-Help-based MARL (MH-MARL) to instruct agents to help each other in order to promote cooperation. MH-MARL utilizes an expected action module to generate expected other agents' actions for each particular agent. Then, the expected actions are delivered to other agents for selective imitation during training. Experimental results show that MH-MARL improves the performance of MARL both in success rate and cumulative reward.

* Accepted by 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023) 
Viaarxiv icon

Deep Learning for Hybrid Beamforming with Finite Feedback in GSM Aided mmWave MIMO Systems

Feb 15, 2023
Zhilin Lu, Xudong Zhang, Rui Zeng, Jintao Wang

Figure 1 for Deep Learning for Hybrid Beamforming with Finite Feedback in GSM Aided mmWave MIMO Systems
Figure 2 for Deep Learning for Hybrid Beamforming with Finite Feedback in GSM Aided mmWave MIMO Systems
Figure 3 for Deep Learning for Hybrid Beamforming with Finite Feedback in GSM Aided mmWave MIMO Systems
Figure 4 for Deep Learning for Hybrid Beamforming with Finite Feedback in GSM Aided mmWave MIMO Systems

Hybrid beamforming is widely recognized as an important technique for millimeter wave (mmWave) multiple input multiple output (MIMO) systems. Generalized spatial modulation (GSM) is further introduced to improve the spectrum efficiency. However, most of the existing works on beamforming assume the perfect channel state information (CSI), which is unrealistic in practical systems. In this paper, joint optimization of downlink pilot training, channel estimation, CSI feedback, and hybrid beamforming is considered in GSM aided frequency division duplexing (FDD) mmWave MIMO systems. With the help of deep learning, the GSM hybrid beamformers are designed via unsupervised learning in an end-to-end way. Experiments show that the proposed multi-resolution network named GsmEFBNet can reach a better achievable rate with fewer feedback bits compared with the conventional algorithm.

* 4 pages, 4 figures. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice 
Viaarxiv icon

Low Entropy Communication in Multi-Agent Reinforcement Learning

Feb 10, 2023
Lebin Yu, Yunbo Qiu, Qiexiang Wang, Xudong Zhang, Jian Wang

Figure 1 for Low Entropy Communication in Multi-Agent Reinforcement Learning
Figure 2 for Low Entropy Communication in Multi-Agent Reinforcement Learning
Figure 3 for Low Entropy Communication in Multi-Agent Reinforcement Learning
Figure 4 for Low Entropy Communication in Multi-Agent Reinforcement Learning

Communication in multi-agent reinforcement learning has been drawing attention recently for its significant role in cooperation. However, multi-agent systems may suffer from limitations on communication resources and thus need efficient communication techniques in real-world scenarios. According to the Shannon-Hartley theorem, messages to be transmitted reliably in worse channels require lower entropy. Therefore, we aim to reduce message entropy in multi-agent communication. A fundamental challenge is that the gradients of entropy are either 0 or infinity, disabling gradient-based methods. To handle it, we propose a pseudo gradient descent scheme, which reduces entropy by adjusting the distributions of messages wisely. We conduct experiments on two base communication frameworks with six environment settings and find that our scheme can reduce message entropy by up to 90% with nearly no loss of cooperation performance.

* Accpeted by ICC 2023 
Viaarxiv icon

SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation

Feb 08, 2023
Yuan Cao, Xudong Zhang, Fan Zhang, Feifei Kou, Josiah Poon, Xiongnan Jin, Yongheng Wang, Jinpeng Chen

Figure 1 for SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation
Figure 2 for SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation
Figure 3 for SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation
Figure 4 for SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation

Session-based recommendation (SBR) problem, which focuses on next-item prediction for anonymous users, has received increasingly more attention from researchers. Existing graph-based SBR methods all lack the ability to differentiate between sessions with the same last item, and suffer from severe popularity bias. Inspired by nowadays emerging contrastive learning methods, this paper presents a Simple Contrastive Graph Neural Network for Session-based Recommendation (SimCGNN). In SimCGNN, we first obtain normalized session embeddings on constructed session graphs. We next construct positive and negative samples of the sessions by two forward propagation and a novel negative sample selection strategy, and then calculate the constructive loss. Finally, session embeddings are used to give prediction. Extensive experiments conducted on two real-word datasets show our SimCGNN achieves a significant improvement over state-of-the-art methods.

Viaarxiv icon

Towards Efficient Subarray Hybrid Beamforming: Attention Network-based Practical Feedback in FDD Massive MU-MIMO Systems

Feb 05, 2023
Zhilin Lu, Xudong Zhang, Rui Zeng, Jintao Wang

Figure 1 for Towards Efficient Subarray Hybrid Beamforming: Attention Network-based Practical Feedback in FDD Massive MU-MIMO Systems
Figure 2 for Towards Efficient Subarray Hybrid Beamforming: Attention Network-based Practical Feedback in FDD Massive MU-MIMO Systems
Figure 3 for Towards Efficient Subarray Hybrid Beamforming: Attention Network-based Practical Feedback in FDD Massive MU-MIMO Systems
Figure 4 for Towards Efficient Subarray Hybrid Beamforming: Attention Network-based Practical Feedback in FDD Massive MU-MIMO Systems

Channel state information (CSI) feedback is necessary for the frequency division duplexing (FDD) multiple input multiple output (MIMO) systems due to the channel non-reciprocity. With the help of deep learning, many works have succeeded in rebuilding the compressed ideal CSI for massive MIMO. However, simple CSI reconstruction is of limited practicality since the channel estimation and the targeted beamforming design are not considered. In this paper, a jointly optimized network is introduced for channel estimation and feedback so that a spectral-efficient beamformer can be learned. Moreover, the deployment-friendly subarray hybrid beamforming architecture is applied and a practical lightweight end-to-end network is specially designed. Experiments show that the proposed network is over 10 times lighter at the resource-sensitive user equipment compared with the previous state-of-the-art method with only a minor performance loss.

* 4 pages, 5 figures, 1 table. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice 
Viaarxiv icon

Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction

Nov 14, 2022
Gecheng Chen, Yu Zhou, Xudong Zhang, Rui Tuo

Figure 1 for Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction
Figure 2 for Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction
Figure 3 for Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction
Figure 4 for Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction

The area of transfer learning comprises supervised machine learning methods that cope with the issue when the training and testing data have different input feature spaces or distributions. In this work, we propose a novel transfer learning algorithm called Renewing Iterative Self-labeling Domain Adaptation (Re-ISDA). In this work, we propose a novel transfer learning algorithm called Renewing Iterative Self-labeling Domain Adaptation (Re-ISDA).

Viaarxiv icon

Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback

Nov 09, 2022
Xudong Zhang, Zhilin Lu, Rui Zeng, Jintao Wang

Figure 1 for Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback
Figure 2 for Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback
Figure 3 for Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback
Figure 4 for Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI Feedback

In massive multiple-input multiple-output (MIMO) systems, the user equipment (UE) needs to feed the channel state information (CSI) back to the base station (BS) for the following beamforming. But the large scale of antennas in massive MIMO systems causes huge feedback overhead. Deep learning (DL) based methods can compress the CSI at the UE and recover it at the BS, which reduces the feedback cost significantly. But the compressed CSI must be quantized into bit streams for transmission. In this paper, we propose an adaptor-assisted quantization strategy for bit-level DL-based CSI feedback. First, we design a network-aided adaptor and an advanced training scheme to adaptively improve the quantization and reconstruction accuracy. Moreover, for easy practical employment, we introduce the expert knowledge of data distribution and propose a pluggable and cost-free adaptor scheme. Experiments show that compared with the state-of-the-art feedback quantization method, this adaptor-aided quantization strategy can achieve better quantization accuracy and reconstruction performance with less or no additional cost. The open-source codes are available at https://github.com/zhang-xd18/QCRNet.

* 9 pages, 8 figures, 5 tables. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice 
Viaarxiv icon