arXiv subjects

Xue Wang

Publications and source records attributed to Xue Wang.

101 records · Page 6Linked to original sources

arXiv2022

Bayesian Nonparametric Mixtures of Exponential Random Graph Models for Ensembles of Networks

Ensembles of networks arise in various fields where multiple independent networks are observed on the same set of nodes, for example, a collection of brain networks constructed on the same brain regions for different individuals. However, there are few models that describe both the variations and characteristics of networks in an ensemble at the same time. In this paper, we propose to model the ensemble of networks using a Dirichlet Process Mixture of Exponential Random Graph Models (DPM-ERGMs), which divides the ensemble into different clusters and models each cluster of networks using a separate Exponential Random Graph Model (ERGM). By employing a Dirichlet process mixture, the number of clusters can be determined automatically and changed adaptively with the data provided. Moreover, in order to perform full Bayesian inference for DPM-ERGMs, we employ the intermediate importance sampling technique inside the Metropolis-within-slice sampling scheme, which addressed the problem of sampling from the intractable ERGMs on an infinite sample space. We also demonstrate the performance of DPM-ERGMs with both simulated and real datasets.

stat.ME↗

arXiv2022

Scaled ReLU Matters for Training Vision Transformers

Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensitive to the training parameters, such as learning rate, optimizer and warmup epoch. The reasons for training difficulty are empirically analysed in ~\cite{xiao2021early}, and the authors conjecture that the issue lies with the \textit{patchify-stem} of ViT models and propose that early convolutions help transformers see better. In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the \textit{convolutional stem} (\textit{conv-stem}) matters. We verify, both theoretically and empirically, that scaled ReLU in \textit{conv-stem} not only improves training stabilization, but also increases the diversity of patch tokens, thus boosting peak performance with a large margin via adding few parameters and flops. In addition, extensive experiments are conducted to demonstrate that previous ViTs are far from being well trained, further showing that ViTs have great potential to be a better substitute of CNNs.

cs.CV↗

arXiv2021

Deep Anti-aliasing of Whole Focal Stack Using Slice Spectrum

The paper aims at removing the aliasing effects of the whole focal stack generated from a sparse-sampled {4D} light field, while keeping the consistency across all the focal layers. We first explore the structural characteristics embedded in the focal stack slice and its corresponding frequency-domain representation, i.e., the Focal Stack Spectrum (FSS). We observe that the energy distribution of the FSS always resides within the same triangular area under different angular sampling rates, additionally the continuity of the Point Spread Function (PSF) is intrinsically maintained in the FSS. Based on these two observations, we propose a learning-based FSS reconstruction approach for one-time aliasing removing over the whole focal stack. Moreover, a novel conjugate-symmetric loss function is proposed for the optimization. Compared to previous works, our method avoids an explicit depth estimation, and can handle challenging large-disparity scenarios. Experimental results on both synthetic and real light field datasets show the superiority of the proposed approach for different scenes and various angular sampling rates.

eess.IV↗

arXiv2021

Topics Emerged in the Biomedical Field and Their Characteristics

This study aims to reveal what kind of topics emerged in the biomedical domain by retrospectively analyzing newly added MeSH (Medical Subject Headings) terms from 2001 to 2010 and how they have been used for indexing since their inclusion in the thesaurus. The goal is to investigate if the future trend of a new topic depends on what kind of topic it is without relying on external indicators such as growth, citation patterns, or word co-occurrences. This topic perspective complements the traditional publication perspective in studying emerging topics. Results show that topic characteristics, including topic category, clinical significance, and if a topic has any narrower terms at the time of inclusion, influence future popularity of a new MeSH. Four emergence trend patterns are identified, including emerged and sustained, emerged not sustained, emerged and fluctuated, and not yet emerged. Predictive models using topic characteristics for emerging topic prediction show promise. This suggests that the characteristics of topics and domain should be considered when predicting future emergence of research topics. This study bridges a gap in emerging topic prediction by offering a topic perspective and advocates for considering topic and domain characteristics as well as economic, medical, and environmental impact when studying emerging topics in the biomedical domain.

cs.DL↗

arXiv2020

Research on PM emission and energy consumption of mixed traffic flow based on cellular automata FI model

Traffic congestion leads to a sharp increase in fuel consumption and exhaust emissions, which easily leads to air pollution and fuel waste. Based on Fukui-Ishibashi (FI) model, this paper studies particulate matter(PM) emission and energy dissipation of traffic flow by considering the maximum speed, mixing ratio and random slowing probability. Simulation results show that the energy dissipation of the traffic flow consisting of the same length and different maximum velocity is associated with the maximum velocity. The greater the maximum velocity, the more the energy consumes. When the maximum velocity is different, the PM emission is similar to the change of energy consumption. Moreover, for the same maximum velocity and different mixing ratio, the energy dissipation and the PM emission related to the mixing ratio. There are the maximum fuel consumption and emission value in the maximum flow. For the same maximum velocity and length of vehicles, their energy consumption and emission are determined by random slowing probability.

nlin.CG↗

arXiv2019

Gold Matrix Ghost Imaging

Light field modulation matrix is closely related to the quality of reconstructed image in ghost imaging. The orthogonality light field modulation matrix with better noise immunity and high quality reconstructed image is urgently needed in the practical application of ghost imaging. In this work, we propose a Gold matrix ghost imaging method with excellent imaging and anti-noise performance, which is proud of the pseudo-randomness and orthogonality of the deterministic Gold matrix. Numerical simulation and experimental results show that the Gold matrix has the characteristics of both random speckle and Hadamard matrix, and the reconstructed images are superior to the two modulation matrixes under the condition of noise, which shows better imaging robustness.

eess.IV↗

arXiv2019

Hadamard `Pipeline' Coding Computational Ghost Imaging

The Hadamard matrix with orthogonality is a more important modulation matrix for computational ghost imaging (CGI), especially its optimized Hadamard matrix. However, as far as we know, little mention has been paid to efficient and convenient Hadamard matrix generation for CGI. The existing methods are to reconstruct any row of Hadamard matrix into two-dimensional matrix and then optimize it. In this work, we propose a Hadamard `pipeline' coding computational ghost imaging approach, which can directly generate two-dimensional Hadamard derived pattern and Hadamard optimization sequence, whereby both the memory consumption and the complexity of coding implementation for CGI can be significantly reduced. The optimization method of commonly used hadamard optimization sequence implementation is also discussed. This method provides a new approach for Hadamard sequence optimization and ghost imaging applications.

eess.IV↗

arXiv2018

Online Learning and Decision-Making under Generalized Linear Model with High-Dimensional Data

We propose a minimax concave penalized multi-armed bandit algorithm under generalized linear model (G-MCP-Bandit) for a decision-maker facing high-dimensional data in an online learning and decision-making process. We demonstrate that the G-MCP-Bandit algorithm asymptotically achieves the optimal cumulative regret in the sample size dimension T , O(log T), and further attains a tight bound in the covariate dimension d, O(log d). In addition, we develop a linear approximation method, the 2-step weighted Lasso procedure, to identify the MCP estimator for the G-MCP-Bandit algorithm under non-iid samples. Under this procedure, the MCP estimator matches the oracle estimator with high probability and converges to the true parameters with the optimal convergence rate. Finally, through experiments based on synthetic data and two real datasets (warfarin dosing dataset and Tencent search advertising dataset), we show that the G-MCP-Bandit algorithm outperforms other benchmark algorithms, especially when there is a high level of data sparsity or the decision set is large.

cs.LG↗

arXiv2017

Real-time Egocentric Gesture Recognition on Mobile Head Mounted Displays

Mobile virtual reality (VR) head mounted displays (HMD) have become popular among consumers in recent years. In this work, we demonstrate real-time egocentric hand gesture detection and localization on mobile HMDs. Our main contributions are: 1) A novel mixed-reality data collection tool to automatic annotate bounding boxes and gesture labels; 2) The largest-to-date egocentric hand gesture and bounding box dataset with more than 400,000 annotated frames; 3) A neural network that runs real time on modern mobile CPUs, and achieves higher than 76% precision on gesture recognition across 8 classes.

cs.CV↗

arXiv2017

A New Measurement of the Spectral Lag of Gamma-Ray Bursts and its Implications for Spectral Evolution Behaviors

We carry out a systematical study of the spectral lag properties of 50 single-pulsed Gamma-Ray Bursts (GRBs) detected by Fermi/GBM. By dividing the light curves into multiple consecutive energy channels we provide a new measurement of the spectral lag which is independent on energy channel selections. We perform a detailed statistical study of our new measurements. We find two similar power-law energy dependencies of both the pulse arrival time and pulse width. Our new results on the power-law indices would favor the relativistic geometric effects for the origin of spectral lag. However, a complete theoretical framework that can fully account for the diverse energy dependencies of both arrival time and pulse width revealed in this work is still missing. We also study the spectral evolution behaviors of the GRB pulses. We find that the GRB pulse with negligible spectral lag would usually have a shorter pulse duration and would appear to have a "hardness-intensity tracking" (HIT) behavior and the GRB pulse with a significant spectral lag would usually have a longer pulse duration and would appear to have a "hard-to-soft" (HTS) behavior.

astro-ph.HE↗

arXiv2013

Discriminative Feature Selection for Uncertain Graph Classification

Mining discriminative features for graph data has attracted much attention in recent years due to its important role in constructing graph classifiers, generating graph indices, etc. Most measurement of interestingness of discriminative subgraph features are defined on certain graphs, where the structure of graph objects are certain, and the binary edges within each graph represent the "presence" of linkages among the nodes. In many real-world applications, however, the linkage structure of the graphs is inherently uncertain. Therefore, existing measurements of interestingness based upon certain graphs are unable to capture the structural uncertainty in these applications effectively. In this paper, we study the problem of discriminative subgraph feature selection from uncertain graphs. This problem is challenging and different from conventional subgraph mining problems because both the structure of the graph objects and the discrimination score of each subgraph feature are uncertain. To address these challenges, we propose a novel discriminative subgraph feature selection method, DUG, which can find discriminative subgraph features in uncertain graphs based upon different statistical measures including expectation, median, mode and phi-probability. We first compute the probability distribution of the discrimination scores for each subgraph feature based on dynamic programming. Then a branch-and-bound algorithm is proposed to search for discriminative subgraphs efficiently. Extensive experiments on various neuroimaging applications (i.e., Alzheimer's Disease, ADHD and HIV) have been performed to analyze the gain in performance by taking into account structural uncertainties in identifying discriminative subgraph features for graph classification.

cs.LG↗