arXiv subjects

Xiaodan Zhang

Publications and source records attributed to Xiaodan Zhang.

26 records · Page 2Linked to original sources

arXiv2022

Emoji-based Co-attention Network for Microblog Sentiment Analysis

Emojis are widely used in online social networks to express emotions, attitudes, and opinions. As emotional-oriented characters, emojis can be modeled as important features of emotions towards the recipient or subject for sentiment analysis. However, existing methods mainly take emojis as heuristic information that fails to resolve the problem of ambiguity noise. Recent researches have utilized emojis as an independent input to classify text sentiment but they ignore the emotional impact of the interaction between text and emojis. It results that the emotional semantics of emojis cannot be fully explored. In this paper, we propose an emoji-based co-attention network that learns the mutual emotional semantics between text and emojis on microblogs. Our model adopts the co-attention mechanism based on bidirectional long short-term memory incorporating the text and emojis, and integrates a squeeze-and-excitation block in a convolutional neural network classifier to increase its sensitivity to emotional semantic features. Experimental results show that the proposed method can significantly outperform several baselines for sentiment analysis on short texts of social media.

cs.CL↗

arXiv2021

Coalition Game based User Association for mmWave Mobile Relay Systems in Rail Traffic Scenarios

Rail transportation, especially, high-speed rails (HSR), is an important infrastructure for the development of national economy and the promotion of passenger experience. Due to the large bandwidth, millimeter wave (mmWave) communication is regarded as a promising technology to meet the demand of high data rates. However, since mmWave communication has the characteristic of high attenuation, mobile relay (MR) is considered in this paper. Also, full-duplex (FD) communications have been proposed to improve the spectral efficiency. However, because of the high speed, as well as the problem of penetration loss, passengers on the train have a poor quality of service. Consequently, an effective user association scheme for HSR in mmWave band is necessary. In this paper, we investigate the user association optimization problem in mmWave mobilerelay systems where the MRs operate in the FD mode. To maximize the system capacity, we propose a cooperative user association approach based on coalition formation game, and develop a coalition formation algorithm to solve the challenging NP-hard problem. We also prove the convergence and Nashstable property of the proposed algorithm. Extensive simulations are done to show the system performance of the proposed scheme under various network settings. It is demonstrated that the proposed distributed low complexity scheme achieves a nearoptimal performance and outperforms two baseline schemes in terms of average system throughput.

cs.IT↗

arXiv2021

Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds

The existing 3D deep learning methods adopt either individual point-based features or local-neighboring voxel-based features, and demonstrate great potential for processing 3D data. However, the point based models are inefficient due to the unordered nature of point clouds and the voxel-based models suffer from large information loss. Motivated by the success of recent point-voxel representation, such as PVCNN, we propose a new convolutional neural network, called Multi Point-Voxel Convolution (MPVConv), for deep learning on point clouds. Integrating both the advantages of voxel and point-based methods, MPVConv can effectively increase the neighboring collection between point-based features and also promote independence among voxel-based features. Moreover, most of the existing approaches aim at solving one specific task, and only a few of them can handle a variety of tasks. Simply replacing the corresponding convolution module with MPVConv, we show that MPVConv can fit in different backbones to solve a wide range of 3D tasks. Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MPVConv improves the accuracy of the backbone (PointNet) by up to \textbf{36\%}, and achieves higher accuracy than the voxel-based model with up to \textbf{34}$\times$ speedups. In addition, MPVConv outperforms the state-of-the-art point-based models with up to \textbf{8}$\times$ speedups. Notably, our MPVConv achieves better accuracy than the newest point-voxel-based model PVCNN (a model more efficient than PointNet) with lower latency.

cs.CV↗

arXiv2021

Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning

We present a new convolutional neural network, called Multi Voxel-Point Neurons Convolution (MVPConv), for fast and accurate 3D deep learning. The previous works adopt either individual point-based features or local-neighboring voxel-based features to process 3D model, which limits the performance of models due to the inefficient computation. Moreover, most of the existing 3D deep learning frameworks aim at solving one specific task, and only a few of them can handle a variety of tasks. Integrating both the advantages of the voxel and point-based methods, the proposed MVPConv can effectively increase the neighboring collection between point-based features and also promote the independence among voxel-based features. Simply replacing the corresponding convolution module with MVPConv, we show that MVPConv can fit in different backbones to solve a wide range of 3D tasks. Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34 times speedup. In addition, MVPConv also outperforms the state-of-the-art point-based models with up to 8 times speedup. Notably, our MVPConv achieves better accuracy than the newest point-voxel-based model PVCNN (a model more efficient than PointNet) with lower latency.

cs.CV↗

arXiv2020

DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction

Information diffusion prediction is a fundamental task for understanding the information propagation process. It has wide applications in such as misinformation spreading prediction and malicious account detection. Previous works either concentrate on utilizing the context of a single diffusion sequence or using the social network among users for information diffusion prediction. However, the diffusion paths of different messages naturally constitute a dynamic diffusion graph. For one thing, previous works cannot jointly utilize both the social network and diffusion graph for prediction, which is insufficient to model the complexity of the diffusion process and results in unsatisfactory prediction performance. For another, they cannot learn users' dynamic preferences. Intuitively, users' preferences are changing as time goes on and users' personal preference determines whether the user will repost the information. Thus, it is beneficial to consider users' dynamic preferences in information diffusion prediction. In this paper, we propose a novel dynamic heterogeneous graph convolutional network (DyHGCN) to jointly learn the structural characteristics of the social graph and dynamic diffusion graph. Then, we encode the temporal information into the heterogeneous graph to learn the users' dynamic preferences. Finally, we apply multi-head attention to capture the context-dependency of the current diffusion path to facilitate the information diffusion prediction task. Experimental results show that DyHGCN significantly outperforms the state-of-the-art models on three public datasets, which shows the effectiveness of the proposed model.

cs.SI↗

arXiv2019

On the Distribution of the Ratio of Products of Fisher-Snedecor $\mathcal{F}$ Random Variables and Its Applications

The Fisher-Snedecor $\mathcal{F}$ distribution has been recently proposed as a more accurate and mathematically tractable composite fading model than traditional established models in some practical cases. In this paper, we firstly derive exact closed-form expressions for the main statistical characterizations of the ratio of products of $\mathcal{F}$-distributed random variables, including the probability density function, the cumulative distribution function and the moment generating function. Secondly, simple and tight approximations to the distribution of products and ratio of products of $\mathcal{F}$-distributed random variables are presented. These analytical results can be readily employed to evaluate the performance of several emerging system configurations, including full-duplex relaying systems operating in the presence of co-channel interference and wireless communication systems enhanced with physical-layer security. The proposed mathematical analysis is substantiated by numerically evaluated results, accompanied by equivalent ones obtained using Monte Carlo simulations.

cs.IT↗

arXiv2019

A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction

Learning fine-grained details is a key issue in image aesthetic assessment. Most of the previous methods extract the fine-grained details via random cropping strategy, which may undermine the integrity of semantic information. Extensive studies show that humans perceive fine-grained details with a mixture of foveal vision and peripheral vision. Fovea has the highest possible visual acuity and is responsible for seeing the details. The peripheral vision is used for perceiving the broad spatial scene and selecting the attended regions for the fovea. Inspired by these observations, we propose a Gated Peripheral-Foveal Convolutional Neural Network (GPF-CNN). It is a dedicated double-subnet neural network, i.e. a peripheral subnet and a foveal subnet. The former aims to mimic the functions of peripheral vision to encode the holistic information and provide the attended regions. The latter aims to extract fine-grained features on these key regions. Considering that the peripheral vision and foveal vision play different roles in processing different visual stimuli, we further employ a gated information fusion (GIF) network to weight their contributions. The weights are determined through the fully connected layers followed by a sigmoid function. We conduct comprehensive experiments on the standard AVA and Photo.net datasets for unified aesthetic prediction tasks: (i) aesthetic quality classification; (ii) aesthetic score regression; and (iii) aesthetic score distribution prediction. The experimental results demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2014

Dynamic synchrotron X-ray imaging study of effective temperature in a vibrated granular medium

We present a dynamic synchrotron X-ray imaging study of the effective temperature $T_{eff}$ in a vibrated granular medium. By tracking the directed motion and the fluctuation dynamics of the tracers inside, we obtained $T_{eff}$ of the system using Einstein relation. We found that as the system unjams with increasing vibration intensities $Γ$, the structural relaxation time $τ$ increases substantially which can be fitted by an Arrhenius law using $T_{eff}$. And the characteristic energy scale of structural relaxation yielded by the Arrhenius fitting is $E = 0.21 \pm 0.02$ $pd^3$, where $p$ is the pressure and $d$ is the background particle diameter, which is consistent with those from hard sphere simulations in which the structural relaxation happens via the opening up of free volume against pressure.

cond-mat.soft↗