arXiv subjects

Zhaohui Yang

Publications and source records attributed to Zhaohui Yang.

At least 235 records · Page 13Linked to original sources

arXiv2021

JMSNAS: Joint Model Split and Neural Architecture Search for Learning over Mobile Edge Networks

The main challenge to deploy deep neural network (DNN) over a mobile edge network is how to split the DNN model so as to match the network architecture as well as all the nodes' computation and communication capacity. This essentially involves two highly coupled procedures: model generating and model splitting. In this paper, a joint model split and neural architecture search (JMSNAS) framework is proposed to automatically generate and deploy a DNN model over a mobile edge network. Considering both the computing and communication resource constraints, a computational graph search problem is formulated to find the multi-split points of the DNN model, and then the model is trained to meet some accuracy requirements. Moreover, the trade-off between model accuracy and completion latency is achieved through the proper design of the objective function. The experiment results confirm the superiority of the proposed framework over the state-of-the-art split machine learning design methods.

cs.AI↗

arXiv2021

Distributed Reinforcement Learning for Age of Information Minimization in Real-Time IoT Systems

In this paper, the problem of minimizing the weighted sum of age of information (AoI) and total energy consumption of Internet of Things (IoT) devices is studied. In the considered model, each IoT device monitors a physical process that follows nonlinear dynamics. As the dynamics of the physical process vary over time, each device must find an optimal sampling frequency to sample the real-time dynamics of the physical system and send sampled information to a base station (BS). Due to limited wireless resources, the BS can only select a subset of devices to transmit their sampled information. Thus, edge devices must cooperatively sample their monitored dynamics based on the local observations and the BS must collect the sampled information from the devices immediately, hence avoiding the additional time and energy used for sampling and information transmission. To this end, it is necessary to jointly optimize the sampling policy of each device and the device selection scheme of the BS so as to accurately monitor the dynamics of the physical process using minimum energy. This problem is formulated as an optimization problem whose goal is to minimize the weighted sum of AoI cost and energy consumption. To solve this problem, we propose a novel distributed reinforcement learning (RL) approach for the sampling policy optimization. The proposed algorithm enables edge devices to cooperatively find the global optimal sampling policy using their own local observations. Given the sampling policy, the device selection scheme can be optimized thus minimizing the weighted sum of AoI and energy consumption of all devices. Simulations with real data of PM 2.5 pollution show that the proposed algorithm can reduce the sum of AoI by up to 17.8% and 33.9% and the total energy consumption by up to 13.2% and 35.1%, compared to a conventional deep Q network method and a uniform sampling policy.

cs.IT↗

arXiv2021

Neural Architecture Dilation for Adversarial Robustness

With the tremendous advances in the architecture and scale of convolutional neural networks (CNNs) over the past few decades, they can easily reach or even exceed the performance of humans in certain tasks. However, a recently discovered shortcoming of CNNs is that they are vulnerable to adversarial attacks. Although the adversarial robustness of CNNs can be improved by adversarial training, there is a trade-off between standard accuracy and adversarial robustness. From the neural architecture perspective, this paper aims to improve the adversarial robustness of the backbone CNNs that have a satisfactory accuracy. Under a minimal computational overhead, the introduction of a dilation architecture is expected to be friendly with the standard performance of the backbone CNN while pursuing adversarial robustness. Theoretical analyses on the standard and adversarial error bounds naturally motivate the proposed neural architecture dilation algorithm. Experimental results on real-world datasets and benchmark neural networks demonstrate the effectiveness of the proposed algorithm to balance the accuracy and adversarial robustness.

cs.CV↗

arXiv2021

Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an object detector from one or few images with image-level labels and a larger set of completely unlabeled images. This is an extreme case of semi-supervised learning where the labeled data are not enough to bootstrap the learning of a detector. Our solution is to train a weakly-supervised student detector model from image-level pseudo-labels generated on the unlabeled set by a teacher classifier model, bootstrapped by region-level similarities to labeled images. Building upon the recent representative weakly-supervised pipeline PCL, our method can use more unlabeled images to achieve performance competitive or superior to many recent weakly-supervised detection solutions.

cs.CV↗

arXiv2021

Federated Learning in Multi-RIS Aided Systems

This paper investigates the problem of model aggregation in federated learning systems aided by multiple reconfigurable intelligent surfaces (RISs). The effective integration of computation and communication is achieved by over-the-air computation (AirComp). Since all local parameters are transmitted over shared wireless channels, the undesirable propagation error inevitably deteriorates the performance of global aggregation. The objective of this work is to 1) reduce the signal distortion of AirComp; 2) enhance the convergence rate of federated learning. Thus, the mean-square-error and the device set are optimized by designing the transmit power, controlling the receive scalar, tuning the phase shifts, and selecting participants in the model uploading process. The formulated mixed-integer non-linear problem (P0) is decomposed into a non-convex problem (P1) with continuous variables and a combinatorial problem (P2) with integer variables. To solve subproblem (P1), the closed-form expressions for transceivers are first derived, then the multi-antenna cases are addressed by the semidefinite relaxation. Next, the problem of phase shifts design is tackled by invoking the penalty-based successive convex approximation method. In terms of subproblem (P2), the difference-of-convex programming is adopted to optimize the device set for convergence acceleration, while satisfying the aggregation error demand. After that, an alternating optimization algorithm is proposed to find a suboptimal solution for problem (P0). Finally, simulation results demonstrate that i) the designed algorithm can converge faster and aggregate model more accurately compared to baselines; ii) the training loss and prediction accuracy of federated learning can be improved significantly with the aid of multiple RISs.

cs.IT↗

arXiv2021

Energy Efficient Reconfigurable Intelligent Surface Enabled Mobile Edge Computing Networks with NOMA

Reconfigurable intelligent surface (RIS) has emerged as a promising technology for achieving high spectrum and energy efficiency in future wireless communication networks. In this paper, we investigate an RIS-aided single-cell multi-user mobile edge computing (MEC) system where an RIS is deployed to support the communication between a base station (BS) equipped with MEC servers and multiple single-antenna users. To utilize the scarce frequency resource efficiently, we assume that users communicate with BS based on a non-orthogonal multiple access (NOMA) protocol. Each user has a computation task which can be computed locally or partially/fully offloaded to the BS. We aim to minimize the sum energy consumption of all users by jointly optimizing the passive phase shifters, the size of transmission data, transmission rate, power control, transmission time and the decoding order. Since the resulting problem is non-convex, we use the block coordinate descent method to alternately optimize two separated subproblems. More specifically, we use the dual method to tackle a subproblem with given phase shift and obtain the closed-form solution; and then we utilize penalty method to solve another subproblem for given power control. Moreover, in order to demonstrate the effectiveness of our proposed algorithm, we propose three benchmark schemes: the time-division multiple access (TDMA)-MEC scheme, the full local computing scheme and the full offloading scheme. We use an alternating 1-D search method and the dual method that can solve the TDMA-based transmission problem well. Numerical results demonstrate that the proposed scheme can increase the energy efficiency and achieve significant performance gains over the three benchmark schemes.

cs.IT↗

arXiv2021

Learning Rate Optimization for Federated Learning Exploiting Over-the-air Computation

Federated learning (FL) as a promising edge-learning framework can effectively address the latency and privacy issues by featuring distributed learning at the devices and model aggregation in the central server. In order to enable efficient wireless data aggregation, over-the-air computation (AirComp) has recently been proposed and attracted immediate attention. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. To combat this effect, the concept of dynamic learning rate (DLR) is proposed in this work. We begin our discussion by considering multiple-input-single-output (MISO) scenario, since the underlying optimization problem is convex and has closed-form solution. We then extend our studies to more general multiple-input-multiple-output (MIMO) case and an iterative method is derived. Extensive simulation results demonstrate the effectiveness of the proposed scheme in reducing the aggregate distortion and guaranteeing the testing accuracy using the MNIST and CIFAR10 datasets. In addition, we present the asymptotic analysis and give a near-optimal receive beamforming design solution in closed form, which is verified by numerical simulations.

cs.IT↗

arXiv2021

Joint Location, Bandwidth and Power Optimization for THz-enabled UAV Communications

In this paper, the problem of unmanned aerial vehicle (UAV) deployment, power allocation, and bandwidth allocation is investigated for a UAV-assisted wireless system operating at terahertz (THz) frequencies. In the studied model, one UAV can service ground users using the THz frequency band. However, the highly uncertain THz channel will introduce new challenges to the UAV location, user power, and bandwidth allocation optimization problems. Therefore, it is necessary to design a novel framework to deploy UAVs in the THz wireless systems. This problem is formally posed as an optimization problem whose goal is to minimize the total delays of the uplink and downlink transmissions between the UAV and the ground users by jointly optimizing the deployment of the UAV, the transmit power and the bandwidth of each user. The communication delay is crucial for emergency communications. To tackle this nonconvex delay minimization problem, an alternating algorithm is proposed while iteratively solving three subproblems: location optimization subproblem, power control subproblem, and bandwidth allocation subproblem. Simulation results show that the proposed algorithm can reduce the transmission delay by up to $59.3\%$, $49.8\%$ and $75.5\%$ respectively compared to baseline algorithms that optimize only UAV location, bandwidth allocation or transmit power control.

cs.IT↗

arXiv2021

Federated Learning for 6G: Applications, Challenges, and Opportunities

Traditional machine learning is centralized in the cloud (data centers). Recently, the security concern and the availability of abundant data and computation resources in wireless networks are pushing the deployment of learning algorithms towards the network edge. This has led to the emergence of a fast growing area, called federated learning (FL), which integrates two originally decoupled areas: wireless communication and machine learning. In this paper, we provide a comprehensive study on the applications of FL for sixth generation (6G) wireless networks. First, we discuss the key requirements in applying FL for wireless communications. Then, we focus on the motivating application of FL for wireless communications. We identify the main problems, challenges, and provide a comprehensive treatment of implementing FL techniques for wireless communications.

cs.IT↗

arXiv2020

Optimal Resource Allocation for Multi-UAV Assisted Visible Light Communication

In this paper, the optimization of deploying unmanned aerial vehicles (UAVs) over a reconfigurable intelligent surfaces (RISs)-assisted visible light communication (VLC) system is studied. In the considered model, UAVs are required to simultaneously provide wireless services as well as illumination for ground users. To meet the traffic and illumination demands of the ground users while minimizing the energy consumption of the UAVs, one must optimize UAV deployment, phase shift of RISs, user association and RIS association. This problem is formulated as an optimization problem whose goal is to minimize the transmit power of UAVs via adjusting UAV deployment, phase shift of RISs, user association and RIS association. To solve this problem, the original optimization problem is divided into four subproblems and an alternating algorithm is proposed. Specifically, phases alignment method and semidefinite program (SDP) algorithm are proposed to optimize the phase shift of RISs. Then, the UAV deployment optimization is solved by the successive convex approximation (SCA) algorithm. Since the problems of user association and RIS association are integer programming, the fraction relaxation method is adopted before using dual method to find the optimal solution. For simplicity, a greedy algorithm is proposed as an alternative to optimize RIS association. The proposed two schemes demonstrate the superior performance of 34:85% and 32:11% energy consumption reduction over the case without RIS, respectively, through extensive numerical study.

cs.IT↗

arXiv2020

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

Neural Architecture Search (NAS) refers to automatically design the architecture. We propose an hourglass-inspired approach (HourNAS) for this problem that is motivated by the fact that the effects of the architecture often proceed from the vital few blocks. Acting like the narrow neck of an hourglass, vital blocks in the guaranteed path from the input to the output of a deep neural network restrict the information flow and influence the network accuracy. The other blocks occupy the major volume of the network and determine the overall network complexity, corresponding to the bulbs of an hourglass. To achieve an extremely fast NAS while preserving the high accuracy, we propose to identify the vital blocks and make them the priority in the architecture search. The search space of those non-vital blocks is further shrunk to only cover the candidates that are affordable under the computational resource constraints. Experimental results on the ImageNet show that only using 3 hours (0.1 days) with one GPU, our HourNAS can search an architecture that achieves a 77.0% Top-1 accuracy, which outperforms the state-of-the-art methods.

cs.CV↗

arXiv2020

Joint Channel Estimation and Signal Recovery in RIS-Assisted Multi-User MISO Communications

Reconfigurable Intelligent Surfaces (RISs) have been recently considered as an energy-efficient solution for future wireless networks. Their dynamic and low-power configuration enables coverage extension, massive connectivity, and low-latency communications. Channel estimation and signal recovery in RISbased systems are among the most critical technical challenges, due to the large number of unknown variables referring to the RIS unit elements and the transmitted signals. In this paper, we focus on the downlink of a RIS-assisted multi-user Multiple Input Single Output (MISO) communication system and present a joint channel estimation and signal recovery scheme based on the PARAllel FACtor (PARAFAC) decomposition. This decomposition unfolds the cascaded channel model and facilitates signal recovery using the Bilinear Generalized Approximate Message Passing (BiG-AMP) algorithm. The proposed method includes an alternating least squares algorithm to iteratively estimate the equivalent matrix, which consists of the transmitted signals and the channels between the base station and RIS, as well as the channels between the RIS and the multiple users. Our selective simulation results show that the proposed scheme outperforms a benchmark scheme that uses genie-aided information knowledge. We also provide insights on the impact of different RIS parameter settings on the proposed scheme.

cs.IT↗

arXiv2020

Energy Efficient Federated Learning Over Wireless Communication Networks

In this paper, the problem of energy efficient transmission and computation resource allocation for federated learning (FL) over wireless communication networks is investigated. In the considered model, each user exploits limited local computational resources to train a local FL model with its collected data and, then, sends the trained FL model to a base station (BS) which aggregates the local FL model and broadcasts it back to all of the users. Since FL involves an exchange of a learning model between users and the BS, both computation and communication latencies are determined by the learning accuracy level. Meanwhile, due to the limited energy budget of the wireless users, both local computation energy and transmission energy must be considered during the FL process. This joint learning and communication problem is formulated as an optimization problem whose goal is to minimize the total energy consumption of the system under a latency constraint. To solve this problem, an iterative algorithm is proposed where, at every step, closed-form solutions for time allocation, bandwidth allocation, power control, computation frequency, and learning accuracy are derived. Since the iterative algorithm requires an initial feasible solution, we construct the completion time minimization problem and a bisection-based algorithm is proposed to obtain the optimal solution, which is a feasible solution to the original energy minimization problem. Numerical results show that the proposed algorithms can reduce up to 59.5% energy consumption compared to the conventional FL method.

cs.IT↗

arXiv2020

Beamforming Design for Multiuser Transmission Through Reconfigurable Intelligent Surface

This paper investigates the problem of resource allocation for multiuser communication networks with a reconfigurable intelligent surface (RIS)-assisted wireless transmitter. In this network, the sum transmit power of the network is minimized by controlling the phase beamforming of the RIS and transmit power of the BS. This problem is posed as a joint optimization problem of transmit power and RIS control, whose goal is to minimize the sum transmit power under signal-to-interference-plus-noise ratio (SINR) constraints of the users. To solve this problem, a dual method is proposed, where the dual problem is obtained as a semidefinite programming problem. After solving the dual problem, the phase beamforming of the RIS is obtained in the closed form, while the optimal transmit power is obtained by using the standard interference function. Simulation results show that the proposed scheme can reduce up to 94% and 27% sum transmit power compared to the maximum ratio transmission (MRT) beamforming and zero-forcing (ZF) beamforming techniques, respectively.

eess.SP↗

arXiv2020

Hybrid Beamforming for RIS-Empowered Multi-hop Terahertz Communications: A DRL-based Method

Wireless communication in the TeraHertz band (0.1--10 THz) is envisioned as one of the key enabling technologies for the future six generation (6G) wireless communication systems. However, very high propagation attenuations and molecular absorptions of THz frequencies often limit the signal transmission distance and coverage range. Benefited from the recent breakthrough on the reconfigurable intelligent surfaces (RIS) for realizing smart radio propagation environment, we propose a novel hybrid beamforming scheme for the multi-hop RIS-assisted communication networks to improve the coverage range at THz-band frequencies. We investigate the joint design of digital beamforming matrix at the BS and analog beamforming matrices at the RISs, by leveraging the recent advances in deep reinforcement learning (DRL) to combat the propagation loss. Simulation results show that our proposed scheme is able to improve 50\% more coverage range of THz communications compared with the benchmarks. Furthermore, it is also shown that our proposed DRL-based method is a state-of-the-art method to solve the NP-bard beamforming problem, especially when the signals at RIS-empowered THz communication networks experience multiple hops.

eess.SP↗

arXiv2020

Searching for Low-Bit Weights in Quantized Neural Networks

Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators. However, the quantization functions used in most conventional quantization methods are non-differentiable, which increases the optimization difficulty of quantized networks. Compared with full-precision parameters (i.e., 32-bit floating numbers), low-bit values are selected from a much smaller set. For example, there are only 16 possibilities in 4-bit space. Thus, we present to regard the discrete weights in an arbitrary quantized neural network as searchable variables, and utilize a differential method to search them accurately. In particular, each weight is represented as a probability distribution over the discrete value set. The probabilities are optimized during training and the values with the highest probability are selected to establish the desired quantized network. Experimental results on benchmarks demonstrate that the proposed method is able to produce quantized neural networks with higher performance over the state-of-the-art methods on both image classification and super-resolution tasks.

cs.CV↗

arXiv2020

Discernible Image Compression

Image compression, as one of the fundamental low-level image processing tasks, is very essential for computer vision. Tremendous computing and storage resources can be preserved with a trivial amount of visual information. Conventional image compression methods tend to obtain compressed images by minimizing their appearance discrepancy with the corresponding original images, but pay little attention to their efficacy in downstream perception tasks, e.g., image recognition and object detection. Thus, some of compressed images could be recognized with bias. In contrast, this paper aims to produce compressed images by pursuing both appearance and perceptual consistency. Based on the encoder-decoder framework, we propose using a pre-trained CNN to extract features of the original and compressed images, and making them similar. Thus the compressed images are discernible to subsequent tasks, and we name our method as Discernible Image Compression (DIC). In addition, the maximum mean discrepancy (MMD) is employed to minimize the difference between feature distributions. The resulting compression network can generate images with high image quality and preserve the consistent perception in the feature domain, so that these images can be well recognized by pre-trained machine learning models. Experiments on benchmarks demonstrate that images compressed by using the proposed method can also be well recognized by subsequent visual recognition and detection models. For instance, the mAP value of compressed images by DIC is about 0.6% higher than that of using compressed images by conventional methods.

cs.CV↗

arXiv2020

Machine Learning for Predictive Deployment of UAVs with Multiple Access

In this paper, a machine learning based deployment framework of unmanned aerial vehicles (UAVs) is studied. In the considered model, UAVs are deployed as flying base stations (BS) to offload heavy traffic from ground BSs. Due to time-varying traffic distribution, a long short-term memory (LSTM) based prediction algorithm is introduced to predict the future cellular traffic. To predict the user service distribution, a KEG algorithm, which is a joint K-means and expectation maximization (EM) algorithm based on Gaussian mixture model (GMM), is proposed for determining the service area of each UAV. Based on the predicted traffic, the optimal UAV positions are derived and three multi-access techniques are compared so as to minimize the total transmit power. Simulation results show that the proposed method can reduce up to 24\% of the total power consumption compared to the conventional method without traffic prediction. Besides, rate splitting multiple access (RSMA) has the lower required transmit power compared to frequency domain multiple access (FDMA) and time domain multiple access (TDMA).

eess.SP↗