arXiv subjects

Tao Zhou

Publications and source records attributed to Tao Zhou.

At least 271 records · Page 15Linked to original sources

arXiv2021

Understanding User Topic Preferences across Multiple Social Networks

In recent years, social networks have shown diversity in function and applications. People begin to use multiple online social networks simultaneously for different demands. The ability to uncover a user's latent topic and social network preference is critical for community detection, recommendation, and personalized service across social networks. Unfortunately, most current works focus on the single network, necessitating new technology and models to address this issue. This paper proposes a user preference discovery model on multiple social networks. Firstly, the global and local topic concepts are defined, then a latent semantic topic discovery method is used to obtain global and local topic word distributions, along with user topic and social network preferences. After that, the topic distribution characteristics of different social networks are examined, as well as the reasons why users choose one network over another to create a post. Next, a Gibbs sampling algorithm is adopted to obtain the model parameters. In the experiment, we collect data from Twitter, Instagram, and Tumblr websites to build a dataset of multiple social networks. Finally, we compare our research to previous works, and both qualitative and quantitative evaluation results have demonstrated the effectiveness.

cs.SI↗

arXiv2021

Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models

We introduce in this work the normalizing field flows (NFF) for learning random fields from scattered measurements. More precisely, we construct a bijective transformation (a normalizing flow characterizing by neural networks) between a Gaussian random field with the Karhunen-Loève (KL) expansion structure and the target stochastic field, where the KL expansion coefficients and the invertible networks are trained by maximizing the sum of the log-likelihood on scattered measurements. This NFF model can be used to solve data-driven forward, inverse, and mixed forward/inverse stochastic partial differential equations in a unified framework. We demonstrate the capability of the proposed NFF model for learning Non Gaussian processes and different types of stochastic partial differential equations.

cs.LG↗

arXiv2021

Progresses and Challenges in Link Prediction

Link prediction is a paradigmatic problem in network science, which aims at estimating the existence likelihoods of nonobserved links, based on known topology. After a brief introduction of the standard problem and metrics of link prediction, this Perspective will summarize representative progresses about local similarity indices, link predictability, network embedding, matrix completion, ensemble learning and others, mainly extracted from thousands of related publications in the last decade. Finally, this Perspective will outline some long-standing challenges for future studies.

physics.data-an↗

arXiv2021

Representative Methods of Computational Socioeconomics

The increasing data availability and imported analyzing tools from computer science and physical science have sharply changed traditional methodologies of social sciences, leading to a new branch named computational socioeconomics that studies various phenomena in socioeconomic development by using quantitative methods based on large-scale real-world data. Sited on recent publications, this Perspective will introduce three representative methods: (i) natural data analyses, (ii) large-scale online experiments, and (iii) integration of big data and surveys. This Perspective ends up with in-depth discussion on the limitations and challenges of the above-mentioned emerging methods.

physics.soc-ph↗

arXiv2021

Light Field Salient Object Detection: A Review and Benchmark

Salient object detection (SOD) is a long-standing research topic in computer vision and has drawn an increasing amount of research interest in the past decade. This paper provides the first comprehensive review and benchmark for light field SOD, which has long been lacking in the saliency community. Firstly, we introduce preliminary knowledge on light fields, including theory and data forms, and then review existing studies on light field SOD, covering ten traditional models, seven deep learning-based models, one comparative study, and one brief review. Existing datasets for light field SOD are also summarized with detailed information and statistical analyses. Secondly, we benchmark nine representative light field SOD models together with several cutting-edge RGB-D SOD models on four widely used light field datasets, from which insightful discussions and analyses, including a comparison between light field SOD and RGB-D SOD models, are achieved. Besides, due to the inconsistency of datasets in their current forms, we further generate complete data and supplement focal stacks, depth maps and multi-view images for the inconsistent datasets, making them consistent and unified. Our supplemental data makes a universal benchmark possible. Lastly, because light field SOD is quite a special problem attributed to its diverse data representations and high dependency on acquisition hardware, making it differ greatly from other saliency detection tasks, we provide nine hints into the challenges and future directions, and outline several open issues. We hope our review and benchmarking could help advance research in this field. All the materials including collected models, datasets, benchmarking results, and supplemented light field datasets will be publicly available on our project site https://github.com/kerenfu/LFSOD-Survey.

cs.CV↗

arXiv2021

Link Prediction via controlling the leading eigenvector

Link prediction is a fundamental challenge in network science. Among various methods, similarity-based algorithms are popular for their simplicity, interpretability, high efficiency and good performance. In this paper, we show that the most elementary local similarity index Common Neighbor (CN) can be linearly decomposed by eigenvectors of the adjacency matrix of the target network, with each eigenvector's contribution being proportional to the square of the corresponding eigenvalue. As in many real networks, there is a huge gap between the largest eigenvalue and the second largest eigenvalue, the CN index is thus dominated by the leading eigenvector and much useful information contained in other eigenvectors may be overlooked. Accordingly, we propose a parameter-free algorithm that ensures the contributions of the leading eigenvector and the secondary eigenvector the same. Extensive experiments on real networks demonstrate that the prediction performance of the proposed algorithm is remarkably better than well-performed local similarity indices in the literature. A further proposed algorithm that can adjust the contribution of leading eigenvector shows the superiority over state-of-the-art algorithms with tunable parameters for its competitive accuracy and lower computational complexity.

cs.SI↗

arXiv2021

Dyonic Born-Infeld black hole in four-dimensional Horndeski gravity

The action of four-dimensional Horndeski gravity coupled to Born-Infeld electromagnetic fields is given via the Kaluza-Klein process. Dyonic black hole solution of the theory is constructed. The metric is devoid of singularity at the origin independent of the parameter selections, this property is different from the one of Einstein-Born-Infeld black holes. Thermodynamics of the black hole is studied, thermodynamic quantities are calculated and the first law is checked to be satisfied. Thermodynamic phase transitions of the black holes are studied in extended phase space.

gr-qc↗

arXiv2021

Context-aware Cross-level Fusion Network for Camouflaged Object Detection

Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape, aggravating the difficulties of accurate COD. In this paper, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net) to address the challenging COD task. Specifically, we propose an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with informative attention coefficients. The fused features are then fed to the proposed Dual-branch Global Context Module (DGCM), which yields multi-scale feature representations for exploiting rich global context information. In C2F-Net, the two modules are conducted on high-level features using a cascaded manner. Extensive experiments on three widely used benchmark datasets demonstrate that our C2F-Net is an effective COD model and outperforms state-of-the-art models remarkably. Our code is publicly available at: https://github.com/thograce/C2FNet.

cs.CV↗

arXiv2021

Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation

Accurate segmentation of brain tumors from multi-modal Magnetic Resonance (MR) images is essential in brain tumor diagnosis and treatment. However, due to the existence of domain shifts among different modalities, the performance of networks decreases dramatically when training on one modality and performing on another, e.g., train on T1 image while performing on T2 image, which is often required in clinical applications. This also prohibits a network from being trained on labeled data and then transferred to unlabeled data from a different domain. To overcome this, unsupervised domain adaptation (UDA) methods provide effective solutions to alleviate the domain shift between labeled source data and unlabeled target data. In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme. Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor using the intermediate data distributions generated for the two domains, which includes an image-to-image translator and a shared-weighted segmentation network. Further, a global-to-local consistency learning module is proposed to build robust representation alignments in an integrated way. Extensive experiments on a multi-modal brain MR benchmark dataset demonstrate that the proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin, while a comprehensive ablation study validates the effectiveness of each key component. The implementation code of our method will be released at \url{https://github.com/KeleiHe/BiGL}.

cs.CV↗

arXiv2021

Spin excitations in the heavily overdoped monolayer graphene superconductor: an analog to the cuprates

Recently it was reported experimentally that the monolayer graphene can be doped to beyond the Van Hove singularity. We study theoretically the possible superconductivity and the corresponding spin excitations of the monolayer graphene in this doping region. A static spin-density-wave state is favorable due to the nested Fermi surface as the Fermi level is doped to the Van Hove singularity point. Superconductivity may be realized upon further doping. The spin excitations in the superconducting state are studied theoretically based on the random phase approximation. The overall features are qualitatively the same with those in cuprate superconductors. Thus we have proposed an exciting possibility, namely, the heavily overdoped monolayer graphene can become a novel platform to study the unconventional superconductivity.

cond-mat.supr-con↗

arXiv2021

Traveling fronts for Fisher-KPP lattice equations in almost periodic media

This paper investigates the existence of almost periodic traveling fronts for Fisher-KPP lattice equations in one-dimensional almost periodic media. By the Lyapunov exponent of the linearized operator near the unstable steady state, we give sufficient condition of the existence of minimal speed of traveling fronts. Furthermore, it is showed that almost periodic traveling fronts share the same recurrence property as the structure of the media. As applications, we give some typical examples which have minimal speed, and the proof of this depends on dynamical system approach to almost periodic Schrodinger operator.

math.AP↗

arXiv2021

Characterizing cycle structure in complex networks

Cycle is the simplest structure that brings redundant paths in network connectivity and feedback effects in network dynamics. Focusing on cycle structure, this paper defines a new matrix, named cycle number matrix, to represent cycle information of a network, and an index, named cycle ratio, to quantify the node importance. Experiments on real networks suggest that cycle ratio contains rich information in addition to well-known benchmark indices, for example, the node rankings by cycle ratio are largely different from rankings by degree, H-index, coreness, betweenness and articulation ranking, while the rankings by degree, H-index, coreness are very similar to each other. Extensive experiments on identifying vital nodes that maintain network connectivity, facilitate network synchronization and maximize the early reach of spreading show that cycle ratio is competitive to betweenness and overall better than other benchmarks. We believe the in-depth analyses on cycle structure may yield novel insights, metrics, models and algorithms for network science.

physics.soc-ph↗

arXiv2021

ParaDiag: parallel-in-time algorithms based on the diagonalization technique

In 2008, Maday and Ronquist introduced an interesting new approach for the direct parallel-in-time (PinT) solution of time-dependent PDEs. The idea is to diagonalize the time stepping matrix, keeping the matrices for the space discretization unchanged, and then to solve all time steps in parallel. Since then, several variants appeared, and we call these closely related algorithms ParaDiag algorithms. ParaDiagalgorithms in the literature can be classified into two groups: ParaDiag-I: direct standalone solvers, ParaDiag-II: iterative solvers. We will explain the basic features of each group in this note. To have concrete examples, we will introduce ParaDiag-I and ParaDiag-II for the advection-diffusion equation. We will also introduce ParaDiag-II for the wave equation and an optimal control problem for the wave equation. We could have used the advection-diffusion equation as well to illustrate ParaDiag-II, but wave equations are known to cause problems for certain PinT algorithms and thus constitute an especially interesting example for which ParaDiag algorithms were tested. We show the main known theoretical results in each case, and also provide Matlab codes for testing. The goal of the Matlab codes is to help the interested reader understand the key features of the ParaDiag algorithms, without intention to be highly tuned for efficiency and/or low memory use. We also provide speedup measurements of ParaDiag algorithms for a 2D linear advection-diffusion equation. These results are obtained on the Tianhe-1 supercomputer in China and the SIUE Campus Cluster in the US and and we compare these results to the performance of parareal and MGRiT, two widely used PinT algorithms.

math.NA↗

arXiv2021

Stability implies robust convergence of a class of preconditioned parallel-in-time iterative algorithms

Solving evolutionary equations in a parallel-in-time manner is an attractive topic and many algorithms are proposed in recent two decades. The algorithm based on the block $α$-circulant preconditioning technique has shown promising advantages, especially for wave propagation problems. By fast Fourier transform for factorizing the involved circulant matrices, the preconditioned iteration can be computed efficiently via the so-called diagonalization technique, which yields a direct parallel implementation across all time levels. In recent years, considerable efforts have been devoted to exploring the convergence of the preconditioned iteration by studying the spectral radius of the iteration matrix, and this leads to many case-by-case studies depending on the used time-integrator. In this paper, we propose a unified convergence analysis for the algorithm applied to $u'+Au=f$, where $σ(A)\subset\mathbb{C}^+$ with $σ(A)$ being the spectrum of $A\in\mathbb{C}^{m\times m}$. For any one-step method (such as the Runge-Kutta methods) with stability function $\mathcal{R}(z)$, we prove that the decay rate of the global error is bounded by $α/(1-α)$, provided the method is stable, i.e., $\max_{λ\inσ(A)}|\mathcal{R}(Δtλ)|\leq1$. For any linear multistep method, such a bound becomes $cα/(1-cα)$, where $c\geq1$ is a constant specified by the multistep method itself. Our proof only relies on the stability of the time-integrator and the estimate is independent of the step size $Δt$ and the spectrum $σ(A)$.

math.NA↗

arXiv2021

An acceleration strategy for randomize-then-optimize sampling via deep neural networks

Randomize-then-optimize (RTO) is widely used for sampling from posterior distributions in Bayesian inverse problems. However, RTO may be computationally intensive for complexity problems due to repetitive evaluations of the expensive forward model and its gradient. In this work, we present a novel strategy to substantially reduce the computation burden of RTO by using a goal-oriented deep neural networks (DNN) surrogate approach. In particular, the training points for the DNN-surrogate are drawn from a local approximated posterior distribution, and it is shown that the resulting algorithm can provide a flexible and efficient sampling algorithm, which converges to the direct RTO approach. We present a Bayesian inverse problem governed by a benchmark elliptic PDE to demonstrate the computational accuracy and efficiency of our new algorithm (i.e., DNN-RTO). It is shown that with our algorithm, one can significantly outperform the traditional RTO.

math.NA↗

arXiv2021

Optimal design for kernel interpolation: applications to uncertainty quantification

The paper is concerned with classic kernel interpolation methods, in addition to approximation methods that are augmented by gradient measurements. To apply kernel interpolation using radial basis functions (RBFs) in a stable way, we propose a type of quasi-optimal interpolation points, searching from a large set of \textit{candidate} points, using a procedure similar to designing Fekete points or power function maximizing points that use pivot from a Cholesky decomposition. The proposed quasi-optimal points result in a smaller condition number, and thus mitigates the instability of the interpolation procedure when the number of points becomes large. Applications to parametric uncertainty quantification are presented, and it is shown that the proposed interpolation method can outperform sparse grid methods in many interesting cases. We also demonstrate the new procedure can be applied to constructing gradient-enhanced Gaussian process emulators.

math.NA↗

arXiv2021

Stein variational gradient descent with local approximations

Bayesian computation plays an important role in modern machine learning and statistics to reason about uncertainty. A key computational challenge in Bayesian inference is to develop efficient techniques to approximate, or draw samples from posterior distributions. Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for this issue. However, the vanilla SVGD requires calculating the gradient of the target density and cannot be applied when the gradient is unavailable or too expensive to evaluate. In this paper we explore one way to address this challenge by the construction of a local surrogate for the target distribution in which the gradient can be obtained in a much more computationally feasible manner. More specifically, we approximate the forward model using a deep neural network (DNN) which is trained on a carefully chosen training set, which also determines the quality of the surrogate. To this end, we propose a general adaptation procedure to refine the local approximation online without destroying the convergence of the resulting SVGD. This significantly reduces the computational cost of SVGD and leads to a suite of algorithms that are straightforward to implement. The new algorithm is illustrated on a set of challenging Bayesian inverse problems, and numerical experiments demonstrate a clear improvement in performance and applicability of standard SVGD.

math.NA↗

arXiv2021

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation

It has been found that residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODEs). In this paper, we explore a deeper relationship between Transformer and numerical methods of ODEs. We show that a residual block of layers in Transformer can be described as a higher-order solution to ODEs. This leads us to design a new architecture (call it ODE Transformer) analogous to the Runge-Kutta method that is well motivated in ODEs. As a natural extension to Transformer, ODE Transformer is easy to implement and parameter efficient. Our experiments on three WMT tasks demonstrate the genericity of this model, and large improvements in performance over several strong baselines. It achieves 30.76 and 44.11 BLEU scores on the WMT'14 En-De and En-Fr test data. This sets a new state-of-the-art on the WMT'14 En-Fr task.

cs.CL↗