arXiv subjects

Lin Wang

Publications and source records attributed to Lin Wang.

At least 379 records · Page 21Linked to original sources

arXiv2021

Hamilton-Jacobi equations with their Hamiltonians depending Lipschitz continuously on the unknown

We study the Hamilton-Jacobi equations $H(x,Du,u)=0$ in $M$ and $\partial u/\partial t +H(x,D_xu,u)=0$ in $M\times(0,\infty)$, where the Hamiltonian $H=H(x,p,u)$ depends Lipschitz continuously on the variable $u$. In the framework of the semicontinuous viscosity solutions due to Barron-Jensen, we establish the comparison principle, existence theorem, and representation formula as value functions for extended real-valued, lower semicontinuous solutions for the Cauchy problem. We also establish some results on the long-time behavior of solutions for the Cauchy problem and classification of solutions for the stationary problem.

math.AP↗

arXiv2021

DQN Control Solution for KDD Cup 2021 City Brain Challenge

We took part in the city brain challenge competition and achieved the 8th place. In this competition, the players are provided with a real-world city-scale road network and its traffic demand derived from real traffic data. The players are asked to coordinate the traffic signals with a self-designed agent to maximize the number of vehicles served while maintaining an acceptable delay. In this abstract paper, we present an overall analysis and our detailed solution to this competition. Our approach is mainly based on the adaptation of the deep Q-network (DQN) for real-time traffic signal control. From our perspective, the major challenge of this competition is how to extend the classical DQN framework to traffic signals control in real-world complex road network and traffic flow situation. After trying and implementing several classical reward functions, we finally chose to apply our newly-designed reward in our agent. By applying our newly-proposed reward function and carefully tuning the control scheme, an agent based on a single DQN model can rank among the top 15 teams. We hope this paper could serve, to some extent, as a baseline solution to traffic signal control of real-world road network and inspire further attempts and researches.

cs.LG↗

arXiv2021

Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization

Retinal vessel segmentation plays a key role in computer-aided screening, diagnosis, and treatment of various cardiovascular and ophthalmic diseases. Recently, deep learning-based retinal vessel segmentation algorithms have achieved remarkable performance. However, due to the domain shift problem, the performance of these algorithms often degrades when they are applied to new data that is different from the training data. Manually labeling new data for each test domain is often a time-consuming and laborious task. In this work, we explore unsupervised domain adaptation in retinal vessel segmentation by using entropy-based adversarial learning and transfer normalization layer to train a segmentation network, which generalizes well across domains and requires no annotation of the target domain. Specifically, first, an entropy-based adversarial learning strategy is developed to reduce the distribution discrepancy between the source and target domains while also achieving the objective of entropy minimization on the target domain. In addition, a new transfer normalization layer is proposed to further boost the transferability of the deep network. It normalizes the features of each domain separately to compensate for the domain distribution gap. Besides, it also adaptively selects those feature channels that are more transferable between domains, thus further enhancing the generalization performance of the network. We conducted extensive experiments on three regular fundus image datasets and an ultra-widefield fundus image dataset, and the results show that our approach yields significant performance gains compared to other state-of-the-art methods.

eess.IV↗

arXiv2021

Aubry-Mather theory for contact Hamiltonian systems II

In this paper, we continue to develop Aubry-Mather and weak KAM theories for contact Hamiltonian systems $H(x,u,p)$ with certain dependence on the contact variable $u$. For the Lipschitz dependence case, we obtain some properties of the Mañé set. For the non-decreasing case, we provide some information on the Aubry set, such as the comparison property, graph property and a partially ordered relation for the collection of all projected Aubry sets with respect to backward weak KAM solutions. Moreover, we find a new flow-invariant set $\tilde{\mathcal{S}}_s$ consists of strongly static orbits, which coincides with the Aubry set $\tilde{\mathcal{A}}$ in classical Hamiltonian systems. Nevertheless, a class of examples are constructed to show $\tilde{\mathcal{S}}_s\subsetneqq\tilde{\mathcal{A}}$ in the contact case. As their applications, we find some new phenomena appear even if the strictly increasing dependence of $H$ on $u$ fails at only one point, and we show that there is a difference for the vanishing discount problem from the negative direction between the minimal viscosity solution and non-minimal ones.

math.DS↗

arXiv2021

Prediction of high-Tc superconductivity in ternary lanthanum borohydrides

The study of superconductivity in compressed hydrides is of great interest due to measurements of high critical temperatures (Tc) in the vicinity of room temperature, beginning with the observations of LaH10 at 170-190 GPa. However, the pressures required for synthesis of these high Tc superconducting hydrides currently remain extremely high. Here we show the investigation of crystal structures and superconductivity in the La-B-H system under pressure with particle-swarm intelligence structure searches methods in combination with first-principles calculations. Structures with six stoichiometries, LaBH, LaBH3, LaBH4, LaBH6, LaBH7 and LaBH8, were predicted to become stable under pressure. Remarkably, the hydrogen atoms in LaBH8 were found to bond with B atoms in a manner that is similar to that in H3S. Lattice dynamics calculations indicate that LaBH7 and LaBH8 become dynamically stable at pressures as low as 109.2 and 48.3 GPa, respectively. Moreover, the two phases were predicted to be superconducting with a critical temperature (Tc) of 93 K and 156 K at 110 GPa and 55 GPa, respectively. Our results provide guidance for future experiments targeting new hydride superconductors with both low synthesis pressures and high Tc.

cond-mat.mtrl-sci↗

arXiv2021

Operator as a Service: Stateful Serverless Complex Event Processing

Complex Event Processing (CEP) is a powerful paradigm for scalable data management that is employed in many real-world scenarios such as detecting credit card fraud in banks. The so-called complex events are expressed using a specification language that is typically implemented and executed on a specific runtime system. While the tight coupling of these two components has been regarded as the key for supporting CEP at high performance, such dependencies pose several inherent challenges as follows. (1) Application development atop a CEP system requires extensive knowledge of how the runtime system operates, which is typically highly complex in nature. (2) The specification language dependence requires the need of domain experts and further restricts and steepens the learning curve for application developers. In this paper, we propose CEPLESS, a scalable data management system that decouples the specification from the runtime system by building on the principles of serverless computing. CEPLESS provides operator as a service and offers flexibility by enabling the development of CEP application in any specification language while abstracting away the complexity of the CEP runtime system. As part of CEPLESS, we designed and evaluated novel mechanisms for in-memory processing and batching that enables the stateful processing of CEP operators even under high rates of ingested events. Our evaluation demonstrates that CEPLESS can be easily integrated into existing CEP systems like Apache Flink while attaining similar throughput under a high scale of events (up to 100K events per second) and dynamic operator update in up to 238 ms.

cs.NI↗

arXiv2021

Multi-Granularity Network with Modal Attention for Dense Affective Understanding

Video affective understanding, which aims to predict the evoked expressions by the video content, is desired for video creation and recommendation. In the recent EEV challenge, a dense affective understanding task is proposed and requires frame-level affective prediction. In this paper, we propose a multi-granularity network with modal attention (MGN-MA), which employs multi-granularity features for better description of the target frame. Specifically, the multi-granularity features could be divided into frame-level, clips-level and video-level features, which corresponds to visual-salient content, semantic-context and video theme information. Then the modal attention fusion module is designed to fuse the multi-granularity features and emphasize more affection-relevant modals. Finally, the fused feature is fed into a Mixtures Of Experts (MOE) classifier to predict the expressions. Further employing model-ensemble post-processing, the proposed method achieves the correlation score of 0.02292 in the EEV challenge.

cs.CV↗

arXiv2021

Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called `Student-Teacher' (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically for vision tasks. In general, we consider some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning.

cs.CV↗

arXiv2021

FAST Globular Cluster Pulsar Survey: Twenty-Four Pulsars Discovered in Fifteen Globular Clusters

We present the discovery of 24 pulsars in 15 Globular Clusters (GCs) using the Five-hundred-meter Aperture Spherical radio Telescope (FAST). These include the first pulsar discoveries in M2, M10, and M14. Most of the new systems are either confirmed or likely members of binary systems. M53C, NGC6517H and I are the only three pulsars confirmed to be isolated. M14A is a black widow pulsar with an orbital period of 5.5 hours and a minimum companion mass of 0.016 \Ms. M14E is an eclipsing binary pulsar with an orbital period of 20.3 hours. With the other 8 discoveries that have been reported elsewhere, in total 32 GC pulsars have been discovered by FAST so far. In addition, We detected M3A twice. This was enough to determine that it is a black widow pulsar with an orbital period of 3.3 hours and a minimum companion mass of 0.0125 \Ms.

astro-ph.HE↗

arXiv2021

Orthogonal Subsampling for Big Data Linear Regression

The dramatic growth of big datasets presents a new challenge to data storage and analysis. Data reduction, or subsampling, that extracts useful information from datasets is a crucial step in big data analysis. We propose an orthogonal subsampling (OSS) approach for big data with a focus on linear regression models. The approach is inspired by the fact that an orthogonal array of two levels provides the best experimental design for linear regression models in the sense that it minimizes the average variance of the estimated parameters and provides the best predictions. The merits of OSS are three-fold: (i) it is easy to implement and fast; (ii) it is suitable for distributed parallel computing and ensures the subsamples selected in different batches have no common data points; and (iii) it outperforms existing methods in minimizing the mean squared errors of the estimated parameters and maximizing the efficiencies of the selected subsamples. Theoretical results and extensive numerical results show that the OSS approach is superior to existing subsampling approaches. It is also more robust to the presence of interactions among covariates and, when they do exist, OSS provides more precise estimates of the interaction effects than existing methods. The advantages of OSS are also illustrated through analysis of real data.

stat.ME↗

arXiv2021

DEFT: Distilling Entangled Factors by Preventing Information Diffusion

Disentanglement is a highly desirable property of representation owing to its similarity to human understanding and reasoning. Many works achieve disentanglement upon information bottlenecks (IB). Despite their elegant mathematical foundations, the IB branch usually exhibits lower performance. In order to provide an insight into the problem, we develop an annealing test to calculate the information freezing point (IFP), which is a transition state to freeze information into the latent variables. We also explore these clues or inductive biases for separating the entangled factors according to the differences in the IFP distributions. We found the existing approaches suffer from the information diffusion problem, according to which the increased information diffuses in all latent variables. Based on this insight, we propose a novel disentanglement framework, termed the distilling entangled factor (DEFT), to address the information diffusion problem by scaling backward information. DEFT applies a multistage training strategy, including multigroup encoders with different learning rates and piecewise disentanglement pressure, to disentangle the factors stage by stage. We evaluate DEFT on three variants of dSprite and SmallNORB, which show low-variance and high-level disentanglement scores. Furthermore, the experiment under the correlative factors shows incapable of TC-based approaches. DEFT also exhibits a competitive performance in the unsupervised setting.

cs.LG↗

arXiv2021

Large depth of range Maxwellian-viewing SMV near-eye display based on a Pancharatnam-Berry optical element

In order to overcome the accommodation and convergence (A-C) conflict that commonly causes visual fatigue in AR display, we propose a Maxwellian-viewing-super-multi-view (MV-SMV) near-eye display system based on a Pancharatnam-Berry optical element (PBOE). The PBOE, which is constituted with an array of high-efficiency polarization gratings, is implemented to direct different views to different directions simultaneously, constructing the 3D light field. Meanwhile, each view is like a Maxwellian view display that possesses a small viewpoint and a large depth of field (DOF). Hence, the MV-SMV display can display virtual images with correct accommodation depth cue within a large DOF. We implement a proof-of-concept MV-SMV display prototype with 3 x 1 and 3 x 2 viewpoints using a 1D PBOE and a 2D PBOE, respectively, and achieve a DOF of 4.37 diopters experimentally.

physics.optics↗

arXiv2021

Knowledge-Based Prediction of Network Controllability Robustness

Network controllability robustness reflects how well a networked system can maintain its controllability against destructive attacks. Its measure is quantified by a sequence of values that record the remaining controllability of the network after a sequence of node-removal or edge-removal attacks. Traditionally, the controllability robustness is determined by attack simulations, which is computationally time consuming or even infeasible. In the present paper, an improved method for predicting the network controllability robustness is developed based on machine learning using a group of convolutional neural networks (CNNs). In this scheme, a number of training data generated by simulations are used to train the group of CNNs for classification and prediction, respectively. Extensive experimental studies are carried out, which demonstrate that 1) the proposed method predicts more precisely than the classical single-CNN predictor; 2) the proposed CNN-based predictor provides a better predictive measure than the traditional spectral measures and network heterogeneity.

physics.soc-ph↗

arXiv2021

Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy most of the data, while most classes have rarely few samples), which results in a challenging imbalance learning scenario. For example, there are estimated more than 40 different kinds of retinal diseases with variable morbidity, however with more than 30+ conditions are very rare from the global patient cohorts, which results in a typical long-tailed learning problem for deep learning-based screening models. In this study, we propose class subset learning by dividing the long-tailed data into multiple class subsets according to prior knowledge, such as regions and phenotype information. It enforces the model to focus on learning the subset-specific knowledge. More specifically, there are some relational classes that reside in the fixed retinal regions, or some common pathological features are observed in both the majority and minority conditions. With those subsets learnt teacher models, then we are able to distill the multiple teacher models into a unified model with weighted knowledge distillation loss. The proposed framework proved to be effective for the long-tailed retinal diseases recognition task. The experimental results on two different datasets demonstrate that our method is flexible and can be easily plugged into many other state-of-the-art techniques with significant improvements.

cs.CV↗

arXiv2021

A Novel Neural Network-Based Symbolic Regression Method: Neuro-Encoded Expression Programming

Neuro-encoded expression programming(NEEP) that aims to offer a novel continuous representation of combinatorial encoding for genetic programming methods is proposed in this paper. Genetic programming with linear representation uses nature-inspired operators (e.g., crossover, mutation) to tune expressions and finally search out the best explicit function to simulate data. The encoding mechanism is essential for genetic programmings to find a desirable solution efficiently. However, the linear representation methods manipulate the expression tree in discrete solution space, where a small change of the input can cause a large change of the output. The unsmooth landscapes destroy the local information and make difficulty in searching. The neuro-encoded expression programming constructs the gene string with recurrent neural network (RNN) and the weights of the network are optimized by powerful continuous evolutionary algorithms. The neural network mappings smoothen the sharp fitness landscape and provide rich neighborhood information to find the best expression. The experiments indicate that the novel approach improves training efficiency and reduces test errors on several well-known symbolic regression problems.

cs.NE↗

arXiv2021

Conspiracy vs science: A large-scale analysis of online discussion cascades

With the emergence and rapid proliferation of social media platforms and social networking sites, recent years have witnessed a surge of misinformation spreading in our daily life. Drawing on a large-scale dataset which covers more than 1.4M posts and 18M comments, we investigate the propagation of two distinct narratives--(i) conspiracy information, whose claims are generally unsubstantiated and thus referred as misinformation to some extent, and (ii) scientific information, whose origins are generally readily identifiable and verifiable--in an online social media platform. We find that conspiracy cascades tend to propagate in a multigenerational branching process while science cascades are more likely to grow in a breadth-first manner. Specifically, conspiracy information triggers larger cascades, involves more users and generations, persists longer, is more viral and bursty than science information. Content analysis reveals that conspiracy cascades contain more negative words and emotional words which convey anger, fear, disgust, surprise and trust. We also find that conspiracy cascades are more concerned with political and controversial topics. After applying machine learning models, we achieve an AUC score of nearly 90% in discriminating conspiracy from science narratives. We find that conspiracy cascades are more likely to be controlled by a broader set of users than science cascades, imposing new challenges on the management of misinformation. Although political affinity is thought to affect the consumption of misinformation, there is very little evidence that political orientation of the information source plays a role during the propagation of conspiracy information. Our study provides complementing evidence to current misinformation research and has practical policy implications to stem the propagation and mitigate the influence of misinformation online.

cs.SI↗

arXiv2021

Three Pulsars Discovered by FAST in the Globular Cluster NGC 6517 with a Pulsar Candidate Sifting Code Based on Dispersion Measure to Signal-to-Noise Ratio Plots

We report the discovery of three new pulsars in the Globular Cluster (GC) NGC6517, namely NGC 6517 E, F, and G, made with the Five-hundred-meter Aperture Spherical radio Telescope (FAST). The spin periods of NGC 6517 E, F, and G are 7.60~ms, 24.89~ms, and 51.59~ms, respectively. Their dispersion measures are 183.29, 183.713, and 185.3~pc~cm$^{-3}$, respectively, all slightly larger than those of the previously known pulsars in this cluster. The spin period derivatives are at the level of 1$\times$10$^{-18}$~s~s$^{-1}$, which suggests these are recycled pulsars. In addition to the discovery of these three new pulsars, we updated the timing solutions of the known isolated pulsars, NGC 6517 A, C, and D. The solutions are consistent with those from Lynch et al. (2011) and with smaller timing residuals. From the timing solution, NGC 6517 A, B (position from Lynch et al. 2011), C, E, and F are very close to each other on the sky and only a few arcseconds from the optical core of NGC 6517. With currently published and unpublished discoveries, NGC6517 now has 9 pulsars, ranking 5$^{th}$ of the GCs with the most pulsars. The discoveries take advantage of the high sensitivity of FAST and a new algorithm used to check and filter possible candidate signals.

astro-ph.HE↗

arXiv2021

Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation

Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications, learning from datasets with label noise is more challenging since medical imaging datasets tend to have asymmetric (class-dependent) noise and suffer from high observer variability. In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record. We then propose an uncertainty estimation-based framework to handle these two label noise amid the medical image classification task. We design a dual-uncertainty estimation approach to measure the disagreement label noise and single-target label noise via Direct Uncertainty Prediction and Monte-Carlo-Dropout. A boosting-based curriculum training procedure is later introduced for robust learning. We demonstrate the effectiveness of our method by conducting extensive experiments on three different diseases: skin lesions, prostate cancer, and retinal diseases. We also release a large re-engineered database that consists of annotations from more than ten ophthalmologists with an unbiased golden standard dataset for evaluation and benchmarking.

cs.CV↗