arXiv subjects

Jian Chen

Publications and source records attributed to Jian Chen.

At least 271 records · Page 15Linked to original sources

arXiv2021

Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task

The black-box nature of machine learning models hinders the deployment of some high-accuracy models in medical diagnosis. It is risky to put one's life in the hands of models that medical researchers do not fully understand. However, through model interpretation, black-box models can promptly reveal significant biomarkers that medical practitioners may have overlooked due to the surge of infected patients in the COVID-19 pandemic. This research leverages a database of 92 patients with confirmed SARS-CoV-2 laboratory tests between 18th Jan. 2020 and 5th Mar. 2020, in Zhuhai, China, to identify biomarkers indicative of severity prediction. Through the interpretation of four machine learning models, decision tree, random forests, gradient boosted trees, and neural networks using permutation feature importance, Partial Dependence Plot (PDP), Individual Conditional Expectation (ICE), Accumulated Local Effects (ALE), Local Interpretable Model-agnostic Explanations (LIME), and Shapley Additive Explanation (SHAP), we identify an increase in N-Terminal pro-Brain Natriuretic Peptide (NTproBNP), C-Reaction Protein (CRP), and lactic dehydrogenase (LDH), a decrease in lymphocyte (LYM) is associated with severe infection and an increased risk of death, which is consistent with recent medical research on COVID-19 and other research using dedicated models. We further validate our methods on a large open dataset with 5644 confirmed patients from the Hospital Israelita Albert Einstein, at São Paulo, Brazil from Kaggle, and unveil leukocytes, eosinophils, and platelets as three indicative biomarkers for COVID-19.

cs.LG↗

arXiv2021

Adaptive Multi-layer Contrastive Graph Neural Networks

We present Adaptive Multi-layer Contrastive Graph Neural Networks (AMC-GNN), a self-supervised learning framework for Graph Neural Network, which learns feature representations of sample data without data labels. AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks. AMC-GNN could learn the importance weights of embeddings in different layers adaptively through the attention mechanism, and an auxiliary encoder is introduced to train graph contrastive encoders better. The accuracy is improved by maximizing the representation's consistency of positive pairs in the early layers and the final embedding space. Our experiments show that the results can be consistently improved by using the AMC-GNN framework, across four established graph benchmarks: Cora, Citeseer, Pubmed, DBLP citation network datasets, as well as four newly proposed datasets: Co-author-CS, Co-author-Physics, Amazon-Computers, Amazon-Photo.

cs.LG↗

arXiv2021

Indoor Localization Using Smartphone Magnetic with Multi-Scale TCN and LSTM

A novel multi-scale temporal convolutional network (TCN) and long short-term memory network (LSTM) based magnetic localization approach is proposed. To enhance the discernibility of geomagnetic signals, the time-series preprocessing approach is constructed at first. Next, the TCN is invoked to expand the feature dimensions on the basis of keeping the time-series characteristics of LSTM model. Then, a multi-scale time-series layer is constructed with multiple TCNs of different dilation factors to address the problem of inconsistent time-series speed between localization model and mobile users. A stacking framework of multi-scale TCN and LSTM is eventually proposed for indoor magnetic localization. Experiment results demonstrate the effectiveness of the proposed algorithm in indoor localization.

eess.SP↗

arXiv2021

Photonic toroidal vortex

Toroidal vortices are whirling disturbances rotating about a ring-shaped core while advancing in the direction normal to the ring orifice. Toroidal vortices are commonly found in nature and being studied in a wide range of disciplines. Here we report the experimental observation of photonic toroidal vortex as a new solution to Maxwell's equations with the use of conformal mapping. The helical phase twists around a closed loop leading to an azimuthal local orbital angular momentum density. The preparation of such intriguing light field may offer insights of extending toroidal vortex to other disciplines and find important applications in light-matter interaction, optical manipulation, photonic symmetry and topology, and quantum information.

physics.optics↗

arXiv2021

Improve photon number discrimination for a superconducting series nanowire detector by applying a digital matched filter

Photon number resolving (PNR) is an important capacity for detectors working in quantum and classical applications. Although a conventional superconducting nanowire single-photon detector (SNSPD) is not a PNR detector, by arranging nanowires in a series array and multiplexing photons over space, such series PNR-SNSPD can gain quasi-PNR capacity. However, the accuracy and maximum resolved photon number are both limited by the signal-to-noise (SNR) ratio of the output pulses. Here, we introduce a matched filter, which is an optimal filter in terms of SNR for SNSPD pulses. Experimentally, compared to conventional readout using a room-temperature amplifier, the normalized spacing between pulse amplitudes from adjacent photon number detections increased by a maximum factor of 2.1 after the matched filter. Combining with a cryogenic amplifier to increase SNR further, such spacing increased by a maximum factor of 5.3. In contrast to a low pass filter, the matched filter gave better SNRs while maintaining good timing jitters. Minimum timing jitter of 55 ps was obtained experimentally. Our results suggest that the matched filter is a useful tool for improving the performance of the series PNR-SNSPD and the maximum resolved photon number can be expected to reach 65 or even large.

quant-ph↗

arXiv2021

$LnCu_3(OH)_6Cl_3 (Ln = Gd, Tb, Dy)$: Heavy Lanthanides on Spin-1/2 Kagome Magnets

The spin-1/2 kagome antiferromagnets are key prototype materials for studying frustrated magnetism. Three isostructural kagome antiferromagnets LnCu$_3$(OH)$_6$Cl$_3$ (Ln = Gd, Tb, Dy) have been successfully synthesized by the hydrothermal method. LnCu$_3$(OH)$_6$Cl$_3$ adopts space group $P\overline{3}m1$ and features the layered Cu-kagome lattice with lanthanide Ln$^{3+}$ cations sitting at the center of the hexagons. Although heavy lanthanides (Ln = Gd, Tb, Dy) in LnCu$_3$(OH)$_6$Cl$_3$ provide a large effective magnetic moment and ferromagnetic-like spin correlations compared to light-lanthanides (Nd, Sm, Eu) analogues, Cu-kagome holds an antiferromagnetically ordered state at around 17 K like YCu$_3$(OH)$_6$Cl$_3$.

cond-mat.str-el↗

arXiv2021

Dzyaloshinskii-Moriya anisotropy effect on field-induced magnon condensation in kagome antiferromagnet $α-Cu_3Mg(OH)_6Br_2$

We performed a comprehensive electron spin resonance, magnetization and heat capacity study on the field-induced magnetic phase transitions in the kagome antiferromagnet $α-Cu_3Mg(OH)_6Br_2$. With the successful preparation of single crystals, we mapped out the magnetic phase diagrams under the $c$-axis and $ab$-plane directional magnetic fields $B$. For $B\|c$, the three-dimensional (3D) magnon Bose-Einstein condensation (BEC) is evidenced by the power law scaling of the transition temperature, $T_c\propto (B_c-B)^{2/3}$. For $B\|ab$, the transition from the canted antiferromagetic (CAFM) state to the fully polarized (FP) state is a crossover rather than phase transition, and the characteristic temperature has a significant deviation from the 3D BEC scaling. The different behaviors of the field-induced magnetic transitions for $B\|c$ and $B\|ab$ could result from the Dzyaloshinkii-Moriya (DM) interaction with the DM vector along the $c$-axis, which preserves the $c$-axis directional spin rotation symmetry and breaks the spin rotation symmetry when $B\|ab$. The 3D magnon BEC scaling for $B\|c$ is immune to the off-stoichiometric disorder in our sample $α-Cu_{3.26}Mg_{0.74}(OH)_6Br_2$. Our findings have the potential to shed light on the investigations of the magnetic anisotropy and disorder effects on the field-induced magnon BEC in the quantum antiferromagnet.

cond-mat.str-el↗

arXiv2021

Photonic orbital angular momentum with controllable orientation

Vortices are whirling disturbances commonly found in nature ranging from tremendously small scales in Bose-Einstein condensates to cosmologically colossal scales in spiral galaxies. An optical vortex, generally associated with a spiral phase, can carry orbital angular momentum (OAM). The optical OAM can either be in the longitudinal direction if the spiral phase twists in the spatial domain or in the transverse direction if the phase rotates in the spatiotemporal domain. In this article, we demonstrate the intersection of spatiotemporal vortices and spatial vortices in a wave packet. As a result of this intersection, the wave packet hosts a tilted OAM that provides an additional degree of freedom to the applications that harness the OAM of photons.

physics.optics↗

arXiv2021

Visualization Resources: A Starting Point

Visualization, as a vibrant field for researchers, practitioners, and higher educational institutions, is growing and evolving very rapidly. Tremendous progress has been made since 1987, the year often cited as the beginning of data visualization as a distinct field. As such, the number of visualization resources and the demand for those resources are increasing at a very fast pace. We present a collection of open visualization resources for all those with an interest in interactive data visualization and visual analytics. Because the number of resources is so large, we focus on collections of resources, of which there are already very many ranging from literature collections to collections of practitioner resources. We develop a novel classification of visualization resource collections based on the resource type, e.g. literature-based, web-based, etc. The result is a helpful overview and details-on-demand of many useful resources. The collection offers a valuable jump-start for those seeking out data visualization resources from all backgrounds spanning from beginners such as students to teachers, practitioners, and researchers wishing to create their own advanced or novel visual designs.

cs.HC↗

arXiv2021

Content-Aware Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. Specifically, the standard convolution traverses the input images/features using a sliding window scheme to extract features. However, not all the windows contribute equally to the prediction results of CNNs. In practice, the convolutional operation on some of the windows (e.g., smooth windows that contain very similar pixels) can be very redundant and may introduce noises into the computation. Such redundancy may not only deteriorate the performance but also incur the unnecessary computational cost. Thus, it is important to reduce the computational redundancy of convolution to improve the performance. To this end, we propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel. In this sense, we are able to effectively avoid the redundant computation on similar pixels. By replacing the standard convolution in CNNs with our CAC, the resultant models yield significantly better performance and lower computational cost than the baseline models with the standard convolution. More critically, we are able to dynamically allocate suitable computation resources according to the data smoothness of different images, making it possible for content-aware computation. Extensive experiments on various computer vision tasks demonstrate the superiority of our method over existing methods.

cs.CV↗

arXiv2021

Bivariate Separable-Dimension Glyphs can Improve Visual Analysis of Holistic Features

We introduce the cause of the inefficiency of bivariate glyphs by defining the corresponding error. To recommend efficient and perceptually accurate bivariate-glyph design, we present an empirical study of five bivariate glyphs based on three psychophysics principles: integral-separable dimensions, visual hierarchy, and pre-attentive pop out, to choose one integral pair ($length_y-length_x$), three separable pairs ($length-color$, $length-texture$, $length_y-length_y$), and one redundant pair ($length_y-color/length_x$). Twenty participants performed four tasks requiring: reading numerical values, estimating ratio, comparing two points, and looking for extreme values among a subset of points belonging to the same sub-group. The most surprising result was that $length-texture$ was among the most effective methods, suggesting that local spatial frequency features can lead to global pattern detection that facilitate visual search in complex 3D structure. Our results also reveal the following: $length-color$ bivariate glyphs led to the most accurate answers and the least task execution time, while $length_y-length_x$ (integral) dimensions were among the worst and is not recommended; it achieved high performance only when pop-up color was added.

cs.GR↗

arXiv2021

Document Domain Randomization for Deep Learning Document Layout Extraction

We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages to real-world document segmentation. DDR renders pseudo-document pages by modeling randomized textual and non-textual contents of interest, with user-defined layout and font styles to support joint learning of fine-grained classes. We demonstrate competitive results using our DDR approach to extract nine document classes from the benchmark CS-150 and papers published in two domains, namely annual meetings of Association for Computational Linguistics (ACL) and IEEE Visualization (VIS). We compare DDR to conditions of style mismatch, fewer or more noisy samples that are more easily obtained in the real world. We show that high-fidelity semantic information is not necessary to label semantic classes but style mismatch between train and test can lower model accuracy. Using smaller training samples had a slightly detrimental effect. Finally, network models still achieved high test accuracy when correct labels are diluted towards confusing labels; this behavior hold across several classes.

cs.CV↗

arXiv2021

StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking

Deep learning has brought great progress for the sequential recommendation (SR) tasks. With advanced network architectures, sequential recommender models can be stacked with many hidden layers, e.g., up to 100 layers on real-world recommendation datasets. Training such a deep network is difficult because it can be computationally very expensive and takes much longer time, especially in situations where there are tens of billions of user-item interactions. To deal with such a challenge, we present StackRec, a simple, yet very effective and efficient training framework for deep SR models by iterative layer stacking. Specifically, we first offer an important insight that hidden layers/blocks in a well-trained deep SR model have very similar distributions. Enlightened by this, we propose the stacking operation on the pre-trained layers/blocks to transfer knowledge from a shallower model to a deep model, then we perform iterative stacking so as to yield a much deeper but easier-to-train SR model. We validate the performance of StackRec by instantiating it with four state-of-the-art SR models in three practical scenarios with real-world datasets. Extensive experiments show that StackRec achieves not only comparable performance, but also substantial acceleration in training time, compared to SR models that are trained from scratch. Codes are available at https://github.com/wangjiachun0426/StackRec.

cs.IR↗

arXiv2021

De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks

Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of malicious samples into the training dataset. Existing defense techniques against poisoning attacks are largely attack-specific: they are designed for one specific type of attacks but do not work for other types, mainly due to the distinct principles they follow. Yet few general defense strategies have been developed. In this paper, we propose De-Pois, an attack-agnostic defense against poisoning attacks. The key idea of De-Pois is to train a mimic model the purpose of which is to imitate the behavior of the target model trained by clean samples. We take advantage of Generative Adversarial Networks (GANs) to facilitate informative training data augmentation as well as the mimic model construction. By comparing the prediction differences between the mimic model and the target model, De-Pois is thus able to distinguish the poisoned samples from clean ones, without explicit knowledge of any ML algorithms or types of poisoning attacks. We implement four types of poisoning attacks and evaluate De-Pois with five typical defense methods on different realistic datasets. The results demonstrate that De-Pois is effective and efficient for detecting poisoned data against all the four types of poisoning attacks, with both the accuracy and F1-score over 0.9 on average.

cs.CR↗

arXiv2021

Securing NOMA Networks by Exploiting Intelligent Reflecting Surface

This paper investigates the security enhancement of an intelligent reflecting surface (IRS) assisted non-orthogonal multiple access (NOMA) network, where a distributed IRS enabled NOMA transmission framework is proposed to serve users securely in the presence of a passive eavesdropper. Considering that eavesdropper's instantaneous channel state information (CSI) is challenging to acquire in practice, we utilize secrecy outage probability (SOP) as the security metric. A problem of maximizing the minimum secrecy rate among users, subject to the successive interference cancellation (SIC) decoding constraints and SOP constraints, by jointly optimizing transmit beamforming at the BS and phase shifts of IRSs, is formulated. For special case with a single-antenna BS, we derive the exact closed-form SOP expressions and propose a novel ring-penalty based successive convex approximation (SCA) algorithm to design power allocation and phase shifts jointly. While for the more general and challenging case with a multi-antenna BS, we adopt the Bernstein-type inequality to approximate the SOP constraints by a deterministic convex form. To proceed, an efficient alternating optimization (AO) algorithm is developed to solve the considered problem. Numerical results validate the advantages of the proposed algorithms over the baseline schemes. Particularly, two interesting phenomena on distributed IRS deployment are revealed: 1) the secrecy rate peak is achieved only when distributed IRSs share the reflecting elements equally; and 2) the distributed IRS deployment does not always outperform the centralized IRS deployment, due to the tradeoff between the number of IRSs and the reflecting elements equipped at each IRS.

cs.IT↗

arXiv2021

An optics-free computational spectrometer using a broadband and tunable dynamic detector

Optical spectrometers are the central instruments for exploring the interaction between light and matter. The current pursuit of the field is to design a spectrometer without the need for wavelength multiplexing optics to effectively reduce the complexity and physical size of the hardware. Based on computational spectroscopic results and combining a broadband-responsive dynamic detector, we successfully demonstrate an optics-free single-detector spectrometer that maps the tunable quantum efficiency of a superconducting nanowire into an ill-conditioned matrix to build a solvable inverse mathematical equation. Such a spectrometer can realize a broadband spectral responsivity ranging from 660 to 1900 nm. The spectral resolution at the telecom is 6 nm, exceeding the energy resolving capacity of existing infrared single-photon detectors. Meanwhile, benefiting from the optics-free setup, precise time-of-flight measurements can be simultaneously achieved. We have demonstrated a spectral LiDAR with 8 spectral channels. This work provides a concise method for building multifunctional spectrometers and paves the way for applying superconducting nanowire detectors in spectroscopy.

physics.optics↗

arXiv2021

Spin-orbit coupling within tightly focused circularly polarized spatiotemporal vortex wavepacket

Spin-orbital coupling and interaction as intrinsic light fields characteristics have been extensively studied. Previous studies involve the spin angular momentum (SAM) carried by circular polarization and orbital angular momentum (OAM) associated with a spiral phase wavefront within the beam cross section, where both the SAM and OAM are in parallel with the propagation direction. In this work, we study a new type of spin-orbital coupling between the longitudinal SAM and the transverse OAM carried by a spatiotemporal optical vortex (STOV) wavepacket under tight focusing condition. Intricate spatiotemporal phase singularity structures are formed when a circularly polarized STOV wavepacket is tightly focused by a high numerical aperture objective lens. For the transversely polarized components, phase singularity orientation can be significantly tilted away from the transverse direction towards the optical axis due to the coupling between longitudinal SAM and transverse OAM. The connection between the amount of rotation and the temporal width of the wavepacket is revealed. More interestingly, spatiotemporal phase singularity structure with a continuous evolution from longitudinal to transverse orientation through the wavepacket is observed for the longitudinally polarized component. These exotic spin-orbit coupling phenomena are expected to render new effects and functions when they are exploited in light matter interactions.

physics.optics↗

arXiv2021

Learning Defense Transformers for Counterattacking Adversarial Examples

Deep neural networks (DNNs) are vulnerable to adversarial examples with small perturbations. Adversarial defense thus has been an important means which improves the robustness of DNNs by defending against adversarial examples. Existing defense methods focus on some specific types of adversarial examples and may fail to defend well in real-world applications. In practice, we may face many types of attacks where the exact type of adversarial examples in real-world applications can be even unknown. In this paper, motivated by that adversarial examples are more likely to appear near the classification boundary, we study adversarial examples from a new perspective that whether we can defend against adversarial examples by pulling them back to the original clean distribution. We theoretically and empirically verify the existence of defense affine transformations that restore adversarial examples. Relying on this, we learn a defense transformer to counterattack the adversarial examples by parameterizing the affine transformations and exploiting the boundary information of DNNs. Extensive experiments on both toy and real-world datasets demonstrate the effectiveness and generalization of our defense transformer.

cs.LG↗