arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 793 records · Page 44Linked to original sources

arXiv2020

Memory-Gated Recurrent Networks

The essence of multivariate sequential learning is all about how to extract dependencies in data. These data sets, such as hourly medical records in intensive care units and multi-frequency phonetic time series, often time exhibit not only strong serial dependencies in the individual components (the "marginal" memory) but also non-negligible memories in the cross-sectional dependencies (the "joint" memory). Because of the multivariate complexity in the evolution of the joint distribution that underlies the data generating process, we take a data-driven approach and construct a novel recurrent network architecture, termed Memory-Gated Recurrent Networks (mGRN), with gates explicitly regulating two distinct types of memories: the marginal memory and the joint memory. Through a combination of comprehensive simulation studies and empirical experiments on a range of public datasets, we show that our proposed mGRN architecture consistently outperforms state-of-the-art architectures targeting multivariate time series.

cs.LG↗

arXiv2020

Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach

The proliferation of massive open online courses (MOOCs) demands an effective way of course recommendation for jobs posted in recruitment websites, especially for the people who take MOOCs to find new jobs. Despite the advances of supervised ranking models, the lack of enough supervised signals prevents us from directly learning a supervised ranking model. This paper proposes a general automated weak supervision framework AutoWeakS via reinforcement learning to solve the problem. On the one hand, the framework enables training multiple supervised ranking models upon the pseudo labels produced by multiple unsupervised ranking models. On the other hand, the framework enables automatically searching the optimal combination of these supervised and unsupervised models. Systematically, we evaluate the proposed model on several datasets of jobs from different recruitment websites and courses from a MOOCs platform. Experiments show that our model significantly outperforms the classical unsupervised, supervised and weak supervision baselines.

cs.DB↗

arXiv2020

Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation

Cold-start problem is a fundamental challenge for recommendation tasks. Despite the recent advances on Graph Neural Networks (GNNs) incorporate the high-order collaborative signal to alleviate the problem, the embeddings of the cold-start users and items aren't explicitly optimized, and the cold-start neighbors are not dealt with during the graph convolution in GNNs. This paper proposes to pre-train a GNN model before applying it for recommendation. Unlike the goal of recommendation, the pre-training GNN simulates the cold-start scenarios from the users/items with sufficient interactions and takes the embedding reconstruction as the pretext task, such that it can directly improve the embedding quality and can be easily adapted to the new cold-start users/items. To further reduce the impact from the cold-start neighbors, we incorporate a self-attention-based meta aggregator to enhance the aggregation ability of each graph convolution step, and an adaptive neighbor sampler to select the effective neighbors according to the feedbacks from the pre-training GNN model. Experiments on three public recommendation datasets show the superiority of our pre-training GNN model against the original GNN models on user/item embedding inference and the recommendation task.

cs.IR↗

arXiv2020

Uncertainty-Aware Deep Calibrated Salient Object Detection

Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. However, those methods overlook the gap between network accuracy and prediction confidence, known as the confidence uncalibration problem. Thus, state-of-the-art SOD networks are prone to be overconfident. In other words, the predicted confidence of the networks does not reflect the real probability of correctness of salient object detection, which significantly hinder their real-world applicability. In this paper, we introduce an uncertaintyaware deep SOD network, and propose two strategies from different perspectives to prevent deep SOD networks from being overconfident. The first strategy, namely Boundary Distribution Smoothing (BDS), generates continuous labels by smoothing the original binary ground-truth with respect to pixel-wise uncertainty. The second strategy, namely Uncertainty-Aware Temperature Scaling (UATS), exploits a relaxed Sigmoid function during both training and testing with spatially-variant temperature scaling to produce softened output. Both strategies can be incorporated into existing deep SOD networks with minimal efforts. Moreover, we propose a new saliency evaluation metric, namely dense calibration measure C, to measure how the model is calibrated on a given dataset. Extensive experimental results on seven benchmark datasets demonstrate that our solutions can not only better calibrate SOD models, but also improve the network accuracy.

cs.CV↗

arXiv2020

Meta Learning-based MIMO Detectors: Design, Simulation, and Experimental Test

Deep neural networks (NNs) have exhibited considerable potential for efficiently balancing the performance and complexity of multiple-input and multiple-output (MIMO) detectors. We propose a receiver framework that enables efficient online training by leveraging the following simple observation: although NN parameters should adapt to channels, not all of them are channel-sensitive. In particular, we use a deep unfolded NN structure that represents iterative algorithms in signal detection and channel decoding modules as multi layer deep feed forward networks. An expectation propagation (EP) module, called EPNet, is established for signal detection by unfolding the EP algorithm and rendering the damping factors trainable. An unfolded turbo decoding module, called TurboNet, is used for channel decoding. This component decodes the turbo code, where trainable NN units are integrated into the traditional max-log-maximum a posteriori decoding procedure. We demonstrate that TurboNet is robust for channels and requires only one off-line training. Therefore, only a few damping factors in EPNet must be re-optimized online. An online training mechanism based on meta learning is then developed. Here, the optimizer, which is implemented by long short-term memory NNs, is trained to update damping factors efficiently by using a small training set such that they can quickly adapt to new environments. Simulation results indicate that the proposed receiver significantly outperforms traditional receivers and that the online learning mechanism can quickly adapt to new environments. Furthermore, an over-the-air platform is presented to demonstrate the significant robustness of the proposed receiver in practical deployment.

eess.SP↗

arXiv2020

Quasilinear Stochastic PDEs with two obstacles: Probabilistic approach

We prove an existence and uniqueness result for two-obstacle problem for quasilinear Stochastic PDEs (DOSPDEs for short). The method is based on the probabilistic interpretation of the solution by using the backward doubly stochastic differential equations (BDSDEs for short).

math.PR↗

arXiv2020

3D Guided Weakly Supervised Semantic Segmentation

Pixel-wise clean annotation is necessary for fully-supervised semantic segmentation, which is laborious and expensive to obtain. In this paper, we propose a weakly supervised 2D semantic segmentation model by incorporating sparse bounding box labels with available 3D information, which is much easier to obtain with advanced sensors. We manually labeled a subset of the 2D-3D Semantics(2D-3D-S) dataset with bounding boxes, and introduce our 2D-3D inference module to generate accurate pixel-wise segment proposal masks. Guided by 3D information, we first generate a point cloud of objects and calculate objectness probability score for each point. Then we project the point cloud with objectness probabilities back to 2D images followed by a refinement step to obtain segment proposals, which are treated as pseudo labels to train a semantic segmentation network. Our method works in a recursive manner to gradually refine the above-mentioned segment proposals. Extensive experimental results on the 2D-3D-S dataset show that the proposed method can generate accurate segment proposals when bounding box labels are available on only a small subset of training images. Performance comparison with recent state-of-the-art methods further illustrates the effectiveness of our method.

cs.CV↗

arXiv2020

Inter-layer Transition in Neural Architecture Search

Differential Neural Architecture Search (NAS) methods represent the network architecture as a repetitive proxy directed acyclic graph (DAG) and optimize the network weights and architecture weights alternatively in a differential manner. However, existing methods model the architecture weights on each edge (i.e., a layer in the network) as statistically independent variables, ignoring the dependency between edges in DAG induced by their directed topological connections. In this paper, we make the first attempt to investigate such dependency by proposing a novel Inter-layer Transition NAS method. It casts the architecture optimization into a sequential decision process where the dependency between the architecture weights of connected edges is explicitly modeled. Specifically, edges are divided into inner and outer groups according to whether or not their predecessor edges are in the same cell. While the architecture weights of outer edges are optimized independently, those of inner edges are derived sequentially based on the architecture weights of their predecessor edges and the learnable transition matrices in an attentive probability transition manner. Experiments on five benchmarks confirm the value of modeling inter-layer dependency and demonstrate the proposed method outperforms state-of-the-art methods.

cs.CV↗

arXiv2020

Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things

In the Internet of Things (IoT) era, billions of sensors and devices collect and process data from the environment, transmit them to cloud centers, and receive feedback via the internet for connectivity and perception. However, transmitting massive amounts of heterogeneous data, perceiving complex environments from these data, and then making smart decisions in a timely manner are difficult. Artificial intelligence (AI), especially deep learning, is now a proven success in various areas including computer vision, speech recognition, and natural language processing. AI introduced into the IoT heralds the era of artificial intelligence of things (AIoT). This paper presents a comprehensive survey on AIoT to show how AI can empower the IoT to make it faster, smarter, greener, and safer. Specifically, we briefly present the AIoT architecture in the context of cloud computing, fog computing, and edge computing. Then, we present progress in AI research for IoT from four perspectives: perceiving, learning, reasoning, and behaving. Next, we summarize some promising applications of AIoT that are likely to profoundly reshape our world. Finally, we highlight the challenges facing AIoT and some potential research opportunities.

cs.AI↗

arXiv2020

Nighttime Dehazing with a Synthetic Benchmark

Increasing the visibility of nighttime hazy images is challenging because of uneven illumination from active artificial light sources and haze absorbing/scattering. The absence of large-scale benchmark datasets hampers progress in this area. To address this issue, we propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images, which first reconstructs the scene geometry, then simulates the light rays and object reflectance, and finally renders the haze effects. Based on it, we generate realistic nighttime hazy images by sampling real-world light colors from a prior empirical distribution. Experiments on the synthetic benchmark show that the degrading factors jointly reduce the image quality. To address this issue, we propose an optimal-scale maximum reflectance prior to disentangle the color correction from haze removal and address them sequentially. Besides, we also devise a simple but effective learning-based baseline which has an encoder-decoder structure based on the MobileNet-v2 backbone. Experiment results demonstrate their superiority over state-of-the-art methods in terms of both image quality and runtime. Both the dataset and source code will be available at https://github.com/chaimi2013/3R.

cs.CV↗

arXiv2020

Photoassociation spectroscopy of weakly bound $^{87}Rb_{2}$ molecules near $5P_{1/2} +5S_{1/2}$ threshold by optical Bragg scattering in Bose-Einstein condensates

We report the high resolution photoassociation (PA) spectroscopy of a $^{87}Rb$ Bose-Einstein condensate (BEC) to excited molecular states near the dissociation limit of $5P_{1/2} +5S_{1/2}$ by optical Bragg scattering. Since the detection of optical Bragg scattering in BEC has a high signal-noise ratio, we obtain the high resolution PA spectrum of excited molecular states in the range of $\pm1$ GHz near the dissociation limit of $5P_{1/2} +5S_{1/2}$. We compare the results with the conventional method of trap loss and show that the results agree each other very well. Many interesting phenomena of excited molecular states are observed, such as light-induced frequency shift and the anomalous strong bound molecular lines at the atomic transition from $|F=1\rangle$ to $|F^{\prime}=2\rangle$. The observed excited molecular states in the range of $\pm1$ GHz near the dissociation limit of $5P_{1/2} +5S_{1/2}$ are never reported before, which will help to further improve the long range bound state models near the dissociation limit.

physics.atom-ph↗

arXiv2020

Magnetic mixed valent semimetal EuZnSb$_2$ with Dirac states in the band structure

We report discovery of new antiferromagnetic semimetal EuZnSb$_2$, obtained and studied in the form of single crystals. Electric resistivity, magnetic susceptibility and heat capacity indicate antiferromagnetic order of Eu with $T_N$ = 20 K. The effective moment of Eu$^{2+}$ inferred from the magnetization and specific heat measurement is 3.5 $μ_B$, smaller than the theoretical value of Eu$^{2+}$ due to presence of both Eu$^{3+}$ and Eu$^{2+}$. Magnetic field-dependent resistivity measurements suggest dominant quasi two dimensional Fermi surfaces whereas the first-principle calculations point to the presence of Dirac fermions. Therefore, EuZnSb$_2$ could represent the first platform to study the interplay of dynamical charge fluctuations, localized magnetic 4$f$ moments and Dirac states with Sb orbital character.

cond-mat.str-el↗

arXiv2020

CONNA: Addressing Name Disambiguation on The Fly

Name disambiguation is a key and also a very tough problem in many online systems such as social search and academic search. Despite considerable research, a critical issue that has not been systematically studied is disambiguation on the fly -- to complete the disambiguation in the real-time. This is very challenging, as the disambiguation algorithm must be accurate, efficient, and error tolerance. In this paper, we propose a novel framework -- CONNA -- to train a matching component and a decision component jointly via reinforcement learning. The matching component is responsible for finding the top matched candidate for the given paper, and the decision component is responsible for deciding on assigning the top matched person or creating a new person. The two components are intertwined and can be bootstrapped via jointly training. Empirically, we evaluate CONNA on two name disambiguation datasets. Experimental results show that the proposed framework can achieve a 1.21%-19.84% improvement on F1-score using joint training of the matching and the decision components. The proposed CONNA has been successfully deployed on AMiner -- a large online academic search system.

cs.SI↗

arXiv2020

Uncertainty Inspired RGB-D Saliency Detection

We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models treat this task as a point estimation problem by predicting a single saliency map following a deterministic learning pipeline. We argue that, however, the deterministic solution is relatively ill-posed. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection which utilizes a latent variable to model the labeling variations. Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution. The generator model is an encoder-decoder saliency network. To infer the latent variable, we introduce two different solutions: i) a Conditional Variational Auto-encoder with an extra encoder to approximate the posterior distribution of the latent variable; and ii) an Alternating Back-Propagation technique, which directly samples the latent variable from the true posterior distribution. Qualitative and quantitative results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps. The source code is publicly available via our project page: https://github.com/JingZhang617/UCNet.

cs.CV↗

arXiv2020

MLBF-Net: A Multi-Lead-Branch Fusion Network for Multi-Class Arrhythmia Classification Using 12-Lead ECG

Automatic arrhythmia detection using 12-lead electrocardiogram (ECG) signal plays a critical role in early prevention and diagnosis of cardiovascular diseases. In the previous studies on automatic arrhythmia detection, most methods concatenated 12 leads of ECG into a matrix, and then input the matrix to a variety of feature extractors or deep neural networks for extracting useful information. Under such frameworks, these methods had the ability to extract comprehensive features (known as integrity) of 12-lead ECG since the information of each lead interacts with each other during training. However, the diverse lead-specific features (known as diversity) among 12 leads were neglected, causing inadequate information learning for 12-lead ECG. To maximize the information learning of multi-lead ECG, the information fusion of comprehensive features with integrity and lead-specific features with diversity should be taken into account. In this paper, we propose a novel Multi-Lead-Branch Fusion Network (MLBF-Net) architecture for arrhythmia classification by integrating multi-loss optimization to jointly learning diversity and integrity of multi-lead ECG. MLBF-Net is composed of three components: 1) multiple lead-specific branches for learning the diversity of multi-lead ECG; 2) cross-lead features fusion by concatenating the output feature maps of all branches for learning the integrity of multi-lead ECG; 3) multi-loss co-optimization for all the individual branches and the concatenated network. We demonstrate our MLBF-Net on China Physiological Signal Challenge 2018 which is an open 12-lead ECG dataset. The experimental results show that MLBF-Net obtains an average $F_1$ score of 0.855, reaching the highest arrhythmia classification performance. The proposed method provides a promising solution for multi-lead ECG analysis from an information fusion perspective.

eess.SP↗

arXiv2020

Condensing Two-stage Detection with Automatic Object Key Part Discovery

Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy. To address this problem, we propose that the model parameters of two-stage detection heads can be condensed and reduced by concentrating on object key parts. To this end, we first introduce an automatic object key part discovery task to make neural networks discover representative sub-parts in each foreground object. With these discovered key parts, we then decompose the object appearance modeling into a key part modeling process and a global modeling process for detection. Key part modeling encodes fine and detailed features from the discovered key parts, and global modeling encodes rough and holistic object characteristics. In practice, such decomposition allows us to significantly abridge model parameters without sacrificing much detection accuracy. Experiments on popular datasets illustrate that our proposed technique consistently maintains original performance while waiving around 50% of the model parameters of common two-stage detection heads, with the performance only deteriorating by 1.5% when waiving around 96% of the original model parameters. Codes are released on: https://github.com/zhechen/Condensing2stageDetection.

cs.CV↗

arXiv2020

Constraining the nuclear symmetry energy and properties of neutron star from GW170817 by Bayesian analysis

Based on the distribution of tidal deformabilities and component masses of binary neutron star merger GW170817, the parametric equation of states (EOS) are employed to probe the nuclear symmetry energy and the properties of neutron star. To obtain a proper distribution of the parameters of the EOS that is consistent with the observation, Bayesian analysis is used and the constraints of causality and maximum mass are considered. From this analysis, it is found that the symmetry energy at twice the saturation density of nuclear matter can be constrained within $E_{sym}(2{ρ_{0}})$ = $34.5^{+20.5}_{-2.3}$ MeV at 90\% credible level. Moreover, the constraints on the radii and dimensionless tidal deformabilities of canonical neutron stars are also demonstrated through this analysis, and the corresponding constraints are 10.80 km $< R_{1.4} <$ 13.20 km and $133 < Λ_{1.4} < 686$ at 90\% credible level, with the most probable value of $\bar{R}_{1.4}$ = 12.60 km and $\barΛ_{1.4}$ = 500, respectively. With respect to the prior, our result (posterior result) prefers a softer EOS, corresponding to a lower expected value of symmetry energy, a smaller radius and a smaller tidal deformability.

nucl-th↗

arXiv2020

High-order minibands and interband Landau level reconstruction in graphene moire superlattice

The propagation of Dirac fermions in graphene through a long-period periodic potential would result in a band folding together with the emergence of a series of cloned Dirac points (DPs). In highly aligned graphene/hexagonal boron nitride (G/hBN) heterostructures, the lattice mismatch between the two atomic crystals generates a unique kind of periodic structure known as a moiré superlattice. Of particular interests is the emergent phenomena related to the reconstructed band-structure of graphene, such as the Hofstadter butterfly, topological currents, gate dependent pseudospin mixing, and ballistic miniband conduction. However, most studies so far have been limited to the lower-order minibands, e.g. the 1st and 2nd minibands counted from charge neutrality, and consequently the fundamental nature of the reconstructed higher-order miniband spectra still remains largely unknown. Here we report on probing the higher-order minibands of precisely aligned graphene moiré superlattices by transport spectroscopy. Using dual electrostatic gating, the edges of these high-order minibands, i.e. the 3rd and 4th minibands, can be reached. Interestingly, we have observed interband Landau level (LL) crossinginducing gap closures in a multiband magneto-transport regime, which originates from band overlap between the 2nd and 3rd minibands. As observed high-order minibands and LL reconstruction qualitatively match our simulated results. Our findings highlight the synergistic effect of minibands in transport, thus presenting a new opportunity for graphene electronic devices.

cond-mat.mes-hall↗