arXiv subjects

Shuguang Cui

Publications and source records attributed to Shuguang Cui.

At least 235 records · Page 13Linked to original sources

arXiv2021

From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting

Despite video forecasting has been a widely explored topic in recent years, the mainstream of the existing work still limits their models with a single prediction space but completely neglects the way to leverage their model with multi-prediction spaces. This work fills this gap. For the first time, we deeply study numerous strategies to perform video forecasting in multi-prediction spaces and fuse their results together to boost performance. The prediction in the pixel space usually lacks the ability to preserve the semantic and structure content of the video however the prediction in the high-level feature space is prone to generate errors in the reduction and recovering process. Therefore, we build a recurrent connection between different feature spaces and incorporate their generations in the upsampling process. Rather surprisingly, this simple idea yields a much more significant performance boost than PhyDNet (performance improved by 32.1% MAE on MNIST-2 dataset, and 21.4% MAE on KTH dataset). Both qualitative and quantitative evaluations on four datasets demonstrate the generalization ability and effectiveness of our approach. We show that our model significantly reduces the troublesome distortions and blurry artifacts and brings remarkable improvements to the accuracy in long term video prediction. The code will be released soon.

cs.CV↗

arXiv2021

Towards Heterogeneous Clients with Elastic Federated Learning

Federated learning involves training machine learning models over devices or data silos, such as edge processors or data warehouses, while keeping the data local. Training in heterogeneous and potentially massive networks introduces bias into the system, which is originated from the non-IID data and the low participation rate in reality. In this paper, we propose Elastic Federated Learning (EFL), an unbiased algorithm to tackle the heterogeneity in the system, which makes the most informative parameters less volatile during training, and utilizes the incomplete local updates. It is an efficient and effective algorithm that compresses both upstream and downstream communications. Theoretically, the algorithm has convergence guarantee when training on the non-IID data at the low participation rate. Empirical experiments corroborate the competitive performance of EFL framework on the robustness and the efficiency.

cs.LG↗

arXiv2021

RevCore: Review-augmented Conversational Recommendation

Existing conversational recommendation (CR) systems usually suffer from insufficient item information when conducted on short dialogue history and unfamiliar items. Incorporating external information (e.g., reviews) is a potential solution to alleviate this problem. Given that reviews often provide a rich and detailed user experience on different interests, they are potential ideal resources for providing high-quality recommendations within an informative conversation. In this paper, we design a novel end-to-end framework, namely, Review-augmented Conversational Recommender (RevCore), where reviews are seamlessly incorporated to enrich item information and assist in generating both coherent and informative responses. In detail, we extract sentiment-consistent reviews, perform review-enriched and entity-based recommendations for item suggestions, as well as use a review-attentive encoder-decoder for response generation. Experimental results demonstrate the superiority of our approach in yielding better performance on both recommendation and conversation responding.

cs.CL↗

arXiv2021

Recent Advances in Data-Driven Wireless Communication Using Gaussian Processes: A Comprehensive Survey

Data-driven paradigms are well-known and salient demands of future wireless communication. Empowered by big data and machine learning, next-generation data-driven communication systems will be intelligent with the characteristics of expressiveness, scalability, interpretability, and especially uncertainty modeling, which can confidently involve diversified latent demands and personalized services in the foreseeable future. In this paper, we review a promising family of nonparametric Bayesian machine learning methods, i.e., Gaussian processes (GPs), and their applications in wireless communication. Since GPs achieve the expressive and interpretable learning ability with uncertainty, it is particularly suitable for wireless communication. Moreover, it provides a natural framework for collaborating data and empirical models (DEM). Specifically, we first envision three-level motivations of data-driven wireless communication using GPs. Then, we present the background of the GPs in terms of covariance structure and model inference. The expressiveness of the GP model using various interpretable kernel designs is surveyed, namely, stationary, non-stationary, deep, and multi-task kernels. Furthermore, we review the distributed GPs with promising scalability, which is suitable for applications in wireless networks with a large number of distributed edge devices. Finally, we list representative solutions and promising techniques that adopt GPs in wireless communication systems.

cs.LG↗

arXiv2021

PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

Point Cloud Sampling and Recovery (PCSR) is critical for massive real-time point cloud collection and processing since raw data usually requires large storage and computation. In this paper, we address a fundamental problem in PCSR: How to downsample the dense point cloud with arbitrary scales while preserving the local topology of discarding points in a case-agnostic manner (i.e. without additional storage for point relationship)? We propose a novel Locally Invertible Embedding for point cloud adaptive sampling and recovery (PointLIE). Instead of learning to predict the underlying geometry details in a seemingly plausible manner, PointLIE unifies point cloud sampling and upsampling to one single framework through bi-directional learning. Specifically, PointLIE recursively samples and adjusts neighboring points on each scale. Then it encodes the neighboring offsets of sampled points to a latent space and thus decouples the sampled points and the corresponding local geometric relationship. Once the latent space is determined and that the deep model is optimized, the recovery process could be conducted by passing the recover-pleasing sampled points and a randomly-drawn embedding to the same network through an invertible operation. Such a scheme could guarantee the fidelity of dense point recovery from sampled points. Extensive experiments demonstrate that the proposed PointLIE outperforms state-of-the-arts both quantitatively and qualitatively. Our code is released through https://github.com/zwb0/PointLIE.

cs.CV↗

arXiv2021

Convergence Time Optimization for Federated Learning over Wireless Networks

In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, a wireless network is considered in which wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step. Moreover, since each user has unique training data samples, the BS prefers to include all local user FL models to generate a converged global FL model. Hence, the FL performance and convergence time will be significantly affected by the user selection scheme. Therefore, it is necessary to design an appropriate user selection scheme that enables users of higher importance to be selected more frequently. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time while optimizing the FL performance. To solve this problem, a probabilistic user selection scheme is proposed such that the BS is connected to the users whose local FL models have significant effects on its global FL model with high probabilities. Given the user selection policy, the uplink RB allocation can be determined. To further reduce the FL convergence time, artificial neural networks (ANNs) are used to estimate the local FL models of the users that are not allocated any RBs for local FL model transmission at each given learning step, which enables the BS to enhance its global FL model and improve the FL convergence speed and performance.

cs.LG↗

arXiv2021

Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images

Grounding referring expressions in RGBD image has been an emerging field. We present a novel task of 3D visual grounding in single-view RGBD image where the referred objects are often only partially scanned due to occlusion. In contrast to previous works that directly generate object proposals for grounding in the 3D scenes, we propose a bottom-up approach to gradually aggregate context-aware information, effectively addressing the challenge posed by the partial geometry. Our approach first fuses the language and the visual features at the bottom level to generate a heatmap that coarsely localizes the relevant regions in the RGBD image. Then our approach conducts an adaptive feature learning based on the heatmap and performs the object-level matching with another visio-linguistic fusion to finally ground the referred object. We evaluate the proposed method by comparing to the state-of-the-art methods on both the RGBD images extracted from the ScanRefer dataset and our newly collected SUNRefer dataset. Experiments show that our method outperforms the previous methods by a large margin (by 11.2% and 15.6% Acc@0.5) on both datasets.

cs.CV↗

arXiv2021

Optimization of User Selection and Bandwidth Allocation for Federated Learning in VLC/RF Systems

Limited radio frequency (RF) resources restrict the number of users that can participate in federated learning (FL) thus affecting FL convergence speed and performance. In this paper, we first introduce visible light communication (VLC) as a supplement to RF in FL and build a hybrid VLC/RF communication system, in which each indoor user can use both VLC and RF to transmit its FL model parameters. Then, the problem of user selection and bandwidth allocation is studied for FL implemented over a hybrid VLC/RF system aiming to optimize the FL performance. The problem is first separated into two subproblems. The first subproblem is a user selection problem with a given bandwidth allocation, which is solved by a traversal algorithm. The second subproblem is a bandwidth allocation problem with a given user selection, which is solved by a numerical method. The final user selection and bandwidth allocation are obtained by iteratively solving these two subproblems. Simulation results show that the proposed FL algorithm that efficiently uses VLC and RF for FL model transmission can improve the prediction accuracy by up to 10% compared with a conventional FL system using only RF.

eess.SP↗

arXiv2021

Learning to Decode Protograph LDPC Codes

The recent development of deep learning methods provides a new approach to optimize the belief propagation (BP) decoding of linear codes. However, the limitation of existing works is that the scale of neural networks increases rapidly with the codelength, thus they can only support short to moderate codelengths. From the point view of practicality, we propose a high-performance neural min-sum (MS) decoding method that makes full use of the lifting structure of protograph low-density parity-check (LDPC) codes. By this means, the size of the parameter array of each layer in the neural decoder only equals the number of edge-types for arbitrary codelengths. In particular, for protograph LDPC codes, the proposed neural MS decoder is constructed in a special way such that identical parameters are shared by a bundle of edges derived from the same edge-type. To reduce the complexity and overcome the vanishing gradient problem in training the proposed neural MS decoder, an iteration-by-iteration (i.e., layer-by-layer in neural networks) greedy training method is proposed. With this, the proposed neural MS decoder tends to be optimized with faster convergence, which is aligned with the early termination mechanism widely used in practice. To further enhance the generalization ability of the proposed neural MS decoder, a codelength/rate compatible training method is proposed, which randomly selects samples from a set of codes lifted from the same base code. As a theoretical performance evaluation tool, a trajectory-based extrinsic information transfer (T-EXIT) chart is developed for various decoders. Both T-EXIT and simulation results show that the optimized MS decoding can provide faster convergence and up to 1dB gain compared with the plain MS decoding and its variants with only slightly increased complexity. In addition, it can even outperform the sum-product algorithm for some short codes.

cs.IT↗

arXiv2021

Artificial Intelligence Driven UAV-NOMA-MEC in Next Generation Wireless Networks

Driven by the unprecedented high throughput and low latency requirements in next-generation wireless networks, this paper introduces an artificial intelligence (AI) enabled framework in which unmanned aerial vehicles (UAVs) use non-orthogonal multiple access (NOMA) and mobile edge computing (MEC) techniques to service terrestrial mobile users (MUs). The proposed framework enables the terrestrial MUs to offload their computational tasks simultaneously, intelligently, and flexibly, thus enhancing their connectivity as well as reducing their transmission latency and their energy consumption. To this end, the fundamentals of this framework are first introduced. Then, a number of communication and AI techniques are proposed to improve the quality of experiences of terrestrial MUs. To this end, federated learning and reinforcement learning are introduced for intelligent task offloading and computing resource allocation. For each learning technique, motivations, challenges, and representative results are introduced. Finally, several key technical challenges and open research issues of the proposed framework are summarized.

eess.SP↗

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

UVeQFed: Universal Vector Quantization for Federated Learning

Traditional deep learning models are trained at a centralized server using labeled data samples collected from end devices or users. Such data samples often include private information, which the users may not be willing to share. Federated learning (FL) is an emerging approach to train such learning models without requiring the users to share their possibly private labeled data. In FL, each user trains its copy of the learning model locally. The server then collects the individual updates and aggregates them into a global model. A major challenge that arises in this method is the need of each user to efficiently transmit its learned model over the throughput limited uplink channel. In this work, we tackle this challenge using tools from quantization theory. In particular, we identify the unique characteristics associated with conveying trained models over rate-constrained channels, and propose a suitable quantization scheme for such settings, referred to as universal vector quantization for FL (UVeQFed). We show that combining universal vector quantization methods with FL yields a decentralized training system in which the compression of the trained models induces only a minimum distortion. We then theoretically analyze the distortion, showing that it vanishes as the number of users grows. We also characterize the convergence of models trained with the traditional federated averaging method combined with UVeQFed to the model which minimizes the loss function. Our numerical results demonstrate the gains of UVeQFed over previously proposed methods in terms of both distortion induced in quantization and accuracy of the resulting aggregated model.

cs.LG↗

arXiv2020

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.

cs.CV↗

arXiv2020

Distributed Multi-agent Meta Learning for Trajectory Design in Wireless Drone Networks

In this paper, the problem of the trajectory design for a group of energy-constrained drones operating in dynamic wireless network environments is studied. In the considered model, a team of drone base stations (DBSs) is dispatched to cooperatively serve clusters of ground users that have dynamic and unpredictable uplink access demands. In this scenario, the DBSs must cooperatively navigate in the considered area to maximize coverage of the dynamic requests of the ground users. This trajectory design problem is posed as an optimization framework whose goal is to find optimal trajectories that maximize the fraction of users served by all DBSs. To find an optimal solution for this non-convex optimization problem under unpredictable environments, a value decomposition based reinforcement learning (VDRL) solution coupled with a meta-training mechanism is proposed. This algorithm allows the DBSs to dynamically learn their trajectories while generalizing their learning to unseen environments. Analytical results show that, the proposed VD-RL algorithm is guaranteed to converge to a local optimal solution of the non-convex optimization problem. Simulation results show that, even without meta-training, the proposed VD-RL algorithm can achieve a 53.2% improvement of the service coverage and a 30.6% improvement in terms of the convergence speed, compared to baseline multi-agent algorithms. Meanwhile, the use of meta-learning improves the convergence speed of the VD-RL algorithm by up to 53.8% when the DBSs must deal with a previously unseen task.

cs.LG↗

arXiv2020

From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation

Graph convolutional networks (GCN) have been recently utilized to extract the underlying structures of datasets with some labeled data and high-dimensional features. Existing GCNs mostly rely on a first-order Chebyshev approximation of graph wavelet-kernels. Such a generic propagation model does not always suit the various datasets and their features. This work revisits the fundamentals of graph wavelet and explores the utility of signal propagation in the vertex domain to approximate the spectral wavelet-kernels. We first derive the conditions for representing the graph wavelet-kernels via vertex propagation. We next propose alternative propagation models for GCN layers based on Taylor expansions. We further analyze the choices of detailed graph representations for TGCNs. Experiments on citation networks, multimedia datasets and synthetic graphs demonstrate the advantage of Taylor-based GCN (TGCN) in the node classification problems over the traditional GCN methods.

eess.SP↗

arXiv2020

Over-the-Air Computing for Wireless Data Aggregation in Massive IoT

Wireless data aggregation (WDA), referring to aggregating data distributed at devices (e.g., sensors and smartphone), is a common operation in 5G-and-beyond machine-type communications to support Internet-of-Things (IoT), which lays the foundation for diversified applications such as distributed sensing, learning, and control. Conventional WDA techniques that are designed based on a separated-communication-and-computation principle encounter difficulty in accommodating the massive access under the limited radio resource and stringent latency constraints imposed by emerging applications (e.g, auto-driving). To address this issue, over-the-air computation (AirComp) is being developed as a new WDA solution by seamlessly integrating computation and communication. By exploiting the waveform superposition property of a multiple-access channel, AirComp turns the air into a computer for computing and communicating functions of distributed data at many devices, thereby allowing low-latency WDA over massive devices. In view of growing interests on AirComp, this article provides a timely overview of the technology by introducing basic principles, discussing advanced techniques and applications, and identifying promising research opportunities.

cs.NI↗

arXiv2020

Optimized Power Control for Over-the-Air Federated Edge Learning

Over-the-air federated edge learning (Air-FEEL) is a communication-efficient solution for privacy-preserving distributed learning over wireless networks. Air-FEEL allows "one-shot" over-the-air aggregation of gradient/model-updates by exploiting the waveform superposition property of wireless channels, and thus promises an extremely low aggregation latency that is independent of the network size. However, such communication efficiency may come at a cost of learning performance degradation due to the aggregation error caused by the non-uniform channel fading over devices and noise perturbation. Prior work adopted channel inversion power control (or its variants) to reduce the aggregation error by aligning the channel gains, which, however, could be highly suboptimal in deep fading scenarios due to the noise amplification. To overcome this issue, we investigate the power control optimization for enhancing the learning performance of Air-FEEL. Towards this end, we first analyze the convergence behavior of the Air-FEEL by deriving the optimality gap of the loss-function under any given power control policy. Then we optimize the power control to minimize the optimality gap for accelerating convergence, subject to a set of average and maximum power constraints at edge devices. The problem is generally non-convex and challenging to solve due to the coupling of power control variables over different devices and iterations. To tackle this challenge, we develop an efficient algorithm by jointly exploiting the successive convex approximation (SCA) and trust region methods. Numerical results show that the optimized power control policy achieves significantly faster convergence than the benchmark policies such as channel inversion and uniform power transmission.

cs.IT↗

arXiv2020

Asymmetric Interference Cancellation for 5G Non-Public Network with Uplink-Downlink Spectrum Sharing

Different from public 4G/5G networks that are dominated by downlink traffic, emerging 5G non-public networks (NPNs) need to support significant uplink traffic to enable emerging applications such as industrial Internet of things (IIoT). The uplink-and-downlink spectrum sharing is becoming a viable solution to enhance the uplink throughput of NPNs, which allows the NPNs to perform the uplink transmission over the time-frequency resources configured for downlink transmission in coexisting public networks. To deal with the severe interference from the downlink public base station (BS) transmitter to the coexisting uplink non-public BS receiver, we propose an adaptive asymmetric successive interference cancellation (SIC) approach, in which the non-public BS receiver is enabled to have the capability of decoding the downlink signals transmitted from the public BS and successively cancelling them for interference mitigation. In particular, this paper studies a basic uplink-and-downlink spectrum sharing scenario when an uplink non-public BS and a downlink public BS coexist in the same area, each communicating with multiple users via orthogonal frequency-division multiple access (OFDMA). Under this setup, we aim to maximize the common uplink throughput of all non-public users, under the condition that the downlink throughput of each public user is above a certain threshold. The decision variables include the subcarrier allocation and user scheduling for both non-public (uplink) and public (downlink) BSs, the decoding mode of the non-public BS over each subcarrier (i.e., with or without SIC), as well as the rate and power control over subcarriers. Numerical results show that the proposed adaptive asymmetric SIC design significantly improves the common uplink throughput as compared to benchmark schemes without such design.

cs.IT↗