arXiv subjects

Bin Wang

Publications and source records attributed to Bin Wang.

At least 703 records · Page 39Linked to original sources

arXiv2021

GraphHop: An Enhanced Label Propagation Method for Node Classification

A scalable semi-supervised node classification method on graph-structured data, called GraphHop, is proposed in this work. The graph contains attributes of all nodes but labels of a few nodes. The classical label propagation (LP) method and the emerging graph convolutional network (GCN) are two popular semi-supervised solutions to this problem. The LP method is not effective in modeling node attributes and labels jointly or facing a slow convergence rate on large-scale graphs. GraphHop is proposed to its shortcoming. With proper initial label vector embeddings, each iteration of GraphHop contains two steps: 1) label aggregation and 2) label update. In Step 1, each node aggregates its neighbors' label vectors obtained in the previous iteration. In Step 2, a new label vector is predicted for each node based on the label of the node itself and the aggregated label information obtained in Step 1. This iterative procedure exploits the neighborhood information and enables GraphHop to perform well in an extremely small label rate setting and scale well for very large graphs. Experimental results show that GraphHop outperforms state-of-the-art graph learning methods on a wide range of tasks (e.g., multi-label and multi-class classification on citation networks, social graphs, and commodity consumption graphs) in graphs of various sizes. Our codes are publicly available on GitHub (https://github.com/TianXieUSC/GraphHop).

cs.LG↗

arXiv2020

Phase transitions in four-dimensional AdS black holes with a nonlinear electrodynamics source

In this work we consider black hole solutions to Einstein theory coupled to a nonlinear power-law electromagnetic field with a fixed exponent value. We study the extended phase space thermodynamics in canonical and grand canonical ensembles where the varying cosmological constant plays the role of an effective thermodynamic pressure. We examine thermodynamical phase transitions in such black hols and find that both first and second order phase transitions can occur in the canonical ensemble, while for the grand canonical ensemble the Hawking-Page and second order phase transitions are allowed.

gr-qc↗

arXiv2020

Object picture of scalar field perturbation on Kerr black hole in scalar-Einstein-Gauss-Bonnet theory

Scalar perturbations around the Kerr black hole in scalar-Einstein-Gauss-Bonnet (sEGB) theory are studied in the time domain. To overcome the "outer boundary problem" that usually encountered in traditional numerical calculations, we apply the hyperboloidal compactification technique to perform a $(2+1)$-dimensional simulation aiming to obtain a precise object picture of the wave propagation under the scalar field perturbation. We find that the big enough coupling constant between the scalar field and the Gauss-Bonnet curvature is responsible to destroy the original Kerr black hole. The breakdown of the Kerr spacetime happens earlier and the instability becomes more violent when the coupling becomes stronger. We further present object confirmations on the special case for the negative coupling where there exists a minimum rotation and below which the instability can never happen no matter how strong the coupling is. We also illustrate the fine structure property in the quasinormal ringing frequency once there is the coupling, and present the characteristic imprint of the sEGB theory. We expect that such a fine structure can be detected in the future gravitational wave observation to test the sEGB theory.

gr-qc↗

arXiv2020

Accelerating linear solvers for Stokes problems with C++ metaprogramming

The efficient solution of large sparse saddle point systems is very important in computational fluid mechanics. The discontinuous Galerkin finite element methods have become increasingly popular for incompressible flow problems but their application is limited due to high computational cost. We describe the C++ programming techniques that may help to accelerate linear solvers for such problems. The approach is based on the policy-based design pattern and partial template specialization, and is implemented in the open source AMGCL library. The efficiency is demonstrated with the example of accelerating an iterative solver of a discontinuous Galerkin finite element method for the Stokes problem. The implementation allows selecting algorithmic components of the solver by adjusting template parameters without any changes to the codebase. It is possible to switch the system matrix to use small statically sized blocks to store the nonzero values, or use a mixed precision solution, which results in up to 4 times speedup, and reduces the memory footprint of the algorithm by about 40\%. We evaluate both monolithic and composite preconditioning strategies for the 3 benchmark problems. The performance of the proposed solution is compared with a multithreaded direct Pardiso solver and a parallel iterative PETSc solver.

cs.MS↗

arXiv2020

Overcoming Language Priors with Self-supervised Learning for Visual Question Answering

Most Visual Question Answering (VQA) models suffer from the language prior problem, which is caused by inherent data biases. Specifically, VQA models tend to answer questions (e.g., what color is the banana?) based on the high-frequency answers (e.g., yellow) ignoring image contents. Existing approaches tackle this problem by creating delicate models or introducing additional visual annotations to reduce question dependency while strengthening image dependency. However, they are still subject to the language prior problem since the data biases have not been even alleviated. In this paper, we introduce a self-supervised learning framework to solve this problem. Concretely, we first automatically generate labeled data to balance the biased data, and propose a self-supervised auxiliary task to utilize the balanced data to assist the base VQA model to overcome language priors. Our method can compensate for the data biases by generating balanced data without introducing external annotations. Experimental results show that our method can significantly outperform the state-of-the-art, improving the overall accuracy from 49.50% to 57.59% on the most commonly used benchmark VQA-CP v2. In other words, we can increase the performance of annotation-based methods by 16% without using external annotations.

cs.CV↗

arXiv2020

Modeling Homophone Noise for Robust Neural Machine Translation

In this paper, we propose a robust neural machine translation (NMT) framework. The framework consists of a homophone noise detector and a syllable-aware NMT model to homophone errors. The detector identifies potential homophone errors in a textual sentence and converts them into syllables to form a mixed sequence that is then fed into the syllable-aware NMT. Extensive experiments on Chinese->English translation demonstrate that our proposed method not only significantly outperforms baselines on noisy test sets with homophone noise, but also achieves a substantial improvement on clean text.

cs.CL↗

arXiv2020

Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension

In multi-turn dialog, utterances do not always take the full form of sentences \cite{Carbonell1983DiscoursePA}, which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog context to generate a reasonable response. Hence, in this paper, we propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog. Enlightened by the multi-task learning scheme, we propose a joint framework that unifies these two tasks, sharing the same encoder to extract the common and task-invariant features with different decoders to learn task-specific features. To better fusing information from the question and the dialog history in the encoding part, we propose to augment the Transformer architecture with a memory updater, which is designed to selectively store and update the history dialog information so as to support downstream tasks. For the experiment, we employ human annotators to write and examine a large-scale dialog reading comprehension dataset. Extensive experiments are conducted on this dataset, and the results show that the proposed model brings substantial improvements over several strong baselines on both tasks. In this way, we demonstrate that reasoning can indeed help better response generation and vice versa. We release our large-scale dataset for further research.

cs.CL↗

arXiv2020

Acoustic black hole in Schwarzschild spacetime: quasi-normal modes, analogous Hawking radiation and shadows

Various properties of acoustic black holes constructed in Minkowski spacetime have been widely studied in the past decades. Recently the acoustic black holes in general spacetime were proposed . In this paper, we first investigate the basic characteristics of `curved' acoustic black hole in Schwarzschild spacetime, including the quasi-normal modes, grey-body factor and analogous Hawking radiation. We find that the signal of quasi-normal mode is weaker than that of Schwarzschild black hole. Moreover, as the tuning parameter increases, both the positive real part and negative imaginal part of the quasi-normal frequency approach to the horizonal axis, but they will not change sign. This means that all the perturbations could die off and the system is stable under those perturbations. Since the larger tuning parameter suppresses the effective potential barrier, so it enhances the grey-body factor. The energy emission rate of Hawking radiation does not monotonically increase of the tuning parameter because of the non-monotonicity of the Hawking temperature. Finally, as a first attempt, we study the acoustic black hole shadow. The radius of acoustic shadow becomes larger as the tuning parameter increases, because both the related acoustic horizon and the acoustic sphere become larger. Our studies could help us to further understand the near horizon geometrical features of the black hole. We also expect that our observations could be detected experimentally in the near future.

gr-qc↗

arXiv2020

Bipartite Graph Embedding via Mutual Information Maximization

Bipartite graph embedding has recently attracted much attention due to the fact that bipartite graphs are widely used in various application domains. Most previous methods, which adopt random walk-based or reconstruction-based objectives, are typically effective to learn local graph structures. However, the global properties of bipartite graph, including community structures of homogeneous nodes and long-range dependencies of heterogeneous nodes, are not well preserved. In this paper, we propose a bipartite graph embedding called BiGI to capture such global properties by introducing a novel local-global infomax objective. Specifically, BiGI first generates a global representation which is composed of two prototype representations. BiGI then encodes sampled edges as local representations via the proposed subgraph-level attention mechanism. Through maximizing the mutual information between local and global representations, BiGI enables nodes in bipartite graph to be globally relevant. Our model is evaluated on various benchmark datasets for the tasks of top-K recommendation and link prediction. Extensive experiments demonstrate that BiGI achieves consistent and significant improvements over state-of-the-art baselines. Detailed analyses verify the high effectiveness of modeling the global properties of bipartite graph.

cs.SI↗

arXiv2020

EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attacks

With the boom of edge intelligence, its vulnerability to adversarial attacks becomes an urgent problem. The so-called adversarial example can fool a deep learning model on the edge node to misclassify. Due to the property of transferability, the adversary can easily make a black-box attack using a local substitute model. Nevertheless, the limitation of resource of edge nodes cannot afford a complicated defense mechanism as doing on the cloud data center. To overcome the challenge, we propose a dynamic defense mechanism, namely EI-MTD. It first obtains robust member models with small size through differential knowledge distillation from a complicated teacher model on the cloud data center. Then, a dynamic scheduling policy based on a Bayesian Stackelberg game is applied to the choice of a target model for service. This dynamic defense can prohibit the adversary from selecting an optimal substitute model for black-box attacks. Our experimental result shows that this dynamic scheduling can effectively protect edge intelligence against adversarial attacks under the black-box setting.

cs.CR↗

arXiv2020

Detection of Cyber Attacks in Renewable-rich Microgrids Using Dynamic Watermarking

This paper presents the first demonstration of using an active mechanism to defend renewable-rich microgrids against cyber attacks. Cyber vulnerability of the renewable-rich microgrids is identified. The defense mechanism based on dynamic watermarking is proposed for detecting cyber anomalies in microgrids. The proposed mechanism is easily implementable and it has theoretically provable performance in term of detecting cyber attacks. The effectiveness of the proposed mechanism is tested and validated in a renewable-rich microgrid.

eess.SY↗

arXiv2020

Electric Vehicle Charging Infrastructure Planning: A Scalable Computational Framework

The optimal charging infrastructure planning problem over a large geospatial area is challenging due to the increasing network sizes of the transportation system and the electric grid. The coupling between the electric vehicle travel behaviors and charging events is therefore complex. This paper focuses on the demonstration of a scalable computational framework for the electric vehicle charging infrastructure planning over the tightly integrated transportation and electric grid networks. On the transportation side, a charging profile generation strategy is proposed leveraging the EV energy consumption model, trip routing, and charger selection methods. On the grid side, a genetic algorithm is utilized within the optimal power flow program to solve the optimal charger placement problem with integer variables by adaptively evaluating candidate solutions in the current iteration and generating new solutions for the next iterations.

cs.AI↗

arXiv2020

Exploring non-singular black holes in gravitational perturbations

We calculate gravitational perturbation quasinormal modes (QNMs) of non-singular Bardeen black holes (BHs) and singularity-free BHs in conformal gravity and examine their spectra in wave dynamics comparing with standard BHs in general relativity. After testing the validity of the approximate signal-to-noise ratio (SNR) calculation for different space based interferometers, we discuss the SNR of non-singular BHs in single-mode gravitational waveform detections in LISA, TianQin and TaiJi. We explore the impact of the Bardeen parameter and the conformal factor on the behavior of the SNR and find that in comparison with the standard Schwarzschild BHs, the increase of non-singular parameters leads to higher SNR for more massive non-singular BHs. We also examine the effect of the galactic confusion noise on the SNR and find that a dip appears in SNR due to such noise. For non-singular BHs, with the increase of the non-singular parameters the dip emerges for more massive BHs. It suggests a wider range of mass of non-singular black holes whose SNR will not be lowered by galactic noise, which implies the SNR for the super massive black holes centered at our galaxy will less likely to be influenced by galactic noise in non-singular black holes models than singular case in general relativity. We conduct Fisher analysis which suggests that the non-singular black holes parameters can be detected accurately with measurement errors as small as $\sim10^{-4}-10^{-5}$. The detections of non-singular BHs are expected to be realized more likely by LISA or TaiJi.

gr-qc↗

arXiv2020

Entanglement Entropy Inequalities in BCFT by Holography

We study entanglement entropy inequalities in boundary conformal field theory (BCFT) by holographic correspondence. By carefully classifying all the configurations for different phases, we prove the strong subadditiviy and the monogamy of mutual information for holographic entanglement entropy in BCFT at both zero and finite temperatures

hep-th↗

arXiv2020

Echoes from phantom wormholes

We study the time evolution of the test scalar and electromagnetic fields perturbations in configurations of phantom wormholes surrounded by dark energy with state parameter $ω< -1$. We observe obvious signals of echoes reflecting wormholes properties and disclose the physical reasons behind such phenomena. In particular, we find that the dark energy equation of state has a clear imprint in echoes in wave perturbations. When $ω$ approaches the phantom divide $ω=-1$ from below, the delay time of echoes becomes longer. The echo of gravitational wave is likely to be detected in the near future, the signature of the dark energy equation of state in the echo spectrum can serve as a local measurement of the dark energy.

gr-qc↗

arXiv2020

Curvature Scalarization of Black Holes in f(R) Gravity

We consider f(R) gravity theories in the presence of a scalar field minimally coupled to gravity with a self-interacting potential. When the scalar field backreacts to the metric we find at large distances scalarized Schwarzschild-AdS and Schwarzschild-AdS-like black hole solutions. At small distances due to strong curvature effects and the scalar dynamis we find a rich structure of scalarized black hole solutions. When the scalar field is conformally coupled to gravity we also find scalarized black hole solutions at small distances.

gr-qc↗

arXiv2020

Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism

Non-autoregressive models generate target words in a parallel way, which achieve a faster decoding speed but at the sacrifice of translation accuracy. To remedy a flawed translation by non-autoregressive models, a promising approach is to train a conditional masked translation model (CMTM), and refine the generated results within several iterations. Unfortunately, such approach hardly considers the \textit{sequential dependency} among target words, which inevitably results in a translation degradation. Hence, instead of solely training a Transformer-based CMTM, we propose a Self-Review Mechanism to infuse sequential information into it. Concretely, we insert a left-to-right mask to the same decoder of CMTM, and then induce it to autoregressively review whether each generated word from CMTM is supposed to be replaced or kept. The experimental results (WMT14 En$\leftrightarrow$De and WMT16 En$\leftrightarrow$Ro) demonstrate that our model uses dramatically less training computations than the typical CMTM, as well as outperforms several state-of-the-art non-autoregressive models by over 1 BLEU. Through knowledge distillation, our model even surpasses a typical left-to-right Transformer model, while significantly speeding up decoding.

cs.CL↗

arXiv2020

Learning Elastic Constitutive Material and Damping Models

Commonly used linear and nonlinear constitutive material models in deformation simulation contain many simplifications and only cover a tiny part of possible material behavior. In this work we propose a framework for learning customized models of deformable materials from example surface trajectories. The key idea is to iteratively improve a correction to a nominal model of the elastic and damping properties of the object, which allows new forward simulations with the learned correction to more accurately predict the behavior of a given soft object. Space-time optimization is employed to identify gentle control forces with which we extract necessary data for model inference and to finally encapsulate the material correction into a compact parametric form. Furthermore, a patch based position constraint is proposed to tackle the challenge of handling incomplete and noisy observations arising in real-world examples. We demonstrate the effectiveness of our method with a set of synthetic examples, as well with data captured from real world homogeneous elastic objects.

cs.GR↗