Search arXiv⌕ Search

arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 793 records · Page 44Linked to original sources
arXiv2021

Biomedical named entity recognition using BERT in the machine reading comprehension framework

Recognition of biomedical entities from literature is a challenging research focus, which is the foundation for extracting a large amount of biomedical knowledge existing in unstructured texts into structured formats. Using the sequence labeling framework to implement biomedical named entity recognition (BioNER) is currently a conventional method. This method, however, often cannot take full advantage of the semantic information in the dataset, and the performance is not always satisfactory. In this work, instead of treating the BioNER task as a sequence labeling problem, we formulate it as a machine reading comprehension (MRC) problem. This formulation can introduce more prior knowledge utilizing well-designed queries, and no longer need decoding processes such as conditional random fields (CRF). We conduct experiments on six BioNER datasets, and the experimental results demonstrate the effectiveness of our method. Our method achieves state-of-the-art (SOTA) performance on the BC4CHEMD, BC5CDR-Chem, BC5CDR-Disease, NCBI-Disease, BC2GM and JNLPBA datasets, achieving F1-scores of 92.92%, 94.19%, 87.83%, 90.04%, 85.48% and 78.93%, respectively.

cs.CL↗
arXiv2021

Class-Incremental Learning for Wireless Device Identification in IoT

Deep Learning (DL) has been utilized pervasively in the Internet of Things (IoT). One typical application of DL in IoT is device identification from wireless signals, namely Non-cryptographic Device Identification (NDI). However, learning components in NDI systems have to evolve to adapt to operational variations, such a paradigm is termed as Incremental Learning (IL). Various IL algorithms have been proposed and many of them require dedicated space to store the increasing amount of historical data, and therefore, they are not suitable for IoT or mobile applications. However, conventional IL schemes can not provide satisfying performance when historical data are not available. In this paper, we address the IL problem in NDI from a new perspective, firstly, we provide a new metric to measure the degree of topological maturity of DNN models from the degree of conflict of class-specific fingerprints. We discover that an important cause for performance degradation in IL enabled NDI is owing to the conflict of devices' fingerprints. Second, we also show that the conventional IL schemes can lead to low topological maturity of DNN models in NDI systems. Thirdly, we propose a new Channel Separation Enabled Incremental Learning (CSIL) scheme without using historical data, in which our strategy can automatically separate devices' fingerprints in different learning stages and avoid potential conflict. Finally, We evaluated the effectiveness of the proposed framework using real data from ADS-B (Automatic Dependent Surveillance-Broadcast), an application of IoT in aviation. The proposed framework has the potential to be applied to accurate identification of IoT devices in a variety of IoT applications and services. Data and code available at IEEE Dataport (DOI: 10.21227/1bxc-ke87) and \url{https://github.com/pcwhy/CSIL}}

cs.LG↗
arXiv2021

A strange metal in a bosonic system

Fermi liquid theory forms the basis for our understanding of the majority of metals, which is manifested in the description of transport properties that the electrical resistivity goes as temperature squared in the limit of zero temperature. However, the observations of strange metal states in various quantum materials, notably high-temperature superconductors, bring this spectacularly successful theoretical framework into crisis. When electron scattering rate 1/τ hits its limit, kBT/{\hbar} where {\hbar} is the reduced Planck's constant, T represents absolute temperature and kB denotes Boltzmann's constant, Planckian dissipation occurs and lends strange metals a surprising link to black holes, gravity, and quantum information theory. Here, we show the characteristic signature of strange metallicity arising unprecedentedly in a bosonic system. Our nanopatterned YBa2Cu3O7-δ(YBCO) film arrays reveal T-linear resistance as well as B-linear magnetoresistance over an extended temperature and magnetic field range in a quantum critical region in the phase diagram. Moreover, the slope of the T-linear resistance α_cp appears bounded by α_cp {\approx} h/2e^2 [1/T]_c^onset where T_c^onset is the temperature at which Cooper pairs form, intimating a common scale-invariant transport mechanism corresponding to Planckian dissipation.In contrast to fermionic systems where the temperature and magnetic field dependent scattering rates combine in quadrature of {\hbar}/τ {\approx} {\sqrt} (((k_B T)^2+(μ_B B)^2)), both terms linearly combine in the present bosonic system, i.e. {\hbar}/τ {\approx} (k_B T+[γμ]_B B), where γ is a constant. By extending the reach of strange metal phenomenology to a bosonic system, our results suggest that there is a fundamental principle governing their transport which transcends particle statistics.

cond-mat.supr-con↗
arXiv2021

On the sum of sizes of overlapping families

Let $\mathcal{A}_1,\ldots,\mathcal{A}_m$ be families of $k$-subsets of an $n$-set. Suppose that one cannot choose pairwise disjoint edges from $s+1$ distinct families. Subject to this condition we investigate the maximum of $|\mathcal{A}_1|+\ldots+|\mathcal{A}_m|$. Note that the subcase $m=s+1$, $\mathcal{A}_1=\ldots=\mathcal{A}_m$ is the Erdős Matching Conjecture, one of the most important open problems in extremal set theory. We provide some upper bounds, a general conjecture and its solution for the range $n\geq 4k^2s$.

math.CO↗
arXiv2021

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

Unsupervised domain adaptation (UDA) methods for person re-identification (re-ID) aim at transferring re-ID knowledge from labeled source data to unlabeled target data. Although achieving great success, most of them only use limited data from a single-source domain for model pre-training, making the rich labeled data insufficiently exploited. To make full use of the valuable labeled data, we introduce the multi-source concept into UDA person re-ID field, where multiple source datasets are used during training. However, because of domain gaps, simply combining different datasets only brings limited improvement. In this paper, we try to address this problem from two perspectives, \ie{} domain-specific view and domain-fusion view. Two constructive modules are proposed, and they are compatible with each other. First, a rectification domain-specific batch normalization (RDSBN) module is explored to simultaneously reduce domain-specific characteristics and increase the distinctiveness of person features. Second, a graph convolutional network (GCN) based multi-domain information fusion (MDIF) module is developed, which minimizes domain distances by fusing features of different domains. The proposed method outperforms state-of-the-art UDA person re-ID methods by a large margin, and even achieves comparable performance to the supervised approaches without any post-processing techniques.

cs.CV↗
arXiv2021

Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Images

Recently, the research on protecting the intellectual properties (IP) of deep neural networks (DNN) has attracted serious concerns. A number of DNN copyright protection methods have been proposed. However, most of the existing watermarking methods focus on verifying the copyright of the model, which do not support the authentication and management of users' fingerprints, thus can not satisfy the requirements of commercial copyright protection. In addition, the query modification attack which was proposed recently can invalidate most of the existing backdoor-based watermarking methods. To address these challenges, in this paper, we propose a method to protect the intellectual properties of DNN models by using an additional class and steganographic images. Specifically, we use a set of watermark key samples to embed an additional class into the DNN, so that the watermarked DNN will classify the watermark key sample as the predefined additional class in the copyright verification stage. We adopt the least significant bit (LSB) image steganography to embed users' fingerprints into watermark key images. Each user will be assigned with a unique fingerprint image so that the user's identity can be authenticated later. Experimental results demonstrate that, the proposed method can protect the copyright of DNN models effectively. On Fashion-MNIST and CIFAR-10 datasets, the proposed method can obtain 100% watermark accuracy and 100% fingerprint authentication success rate. In addition, the proposed method is demonstrated to be robust to the model fine-tuning attack, model pruning attack, and the query modification attack. Compared with three existing watermarking methods (the logo-based, noise-based, and adversarial frontier stitching watermarking methods), the proposed method has better performance on watermark accuracy and robustness against the query modification attack.

cs.AI↗
arXiv2021

Quenched Invariance Principle for a class of random conductance models with long-range jumps

We study random walks on $\mathbb Z^d$ (with $d\ge 2$) among stationary ergodic random conductances $\{C_{x,y}\colon x,y\in\mathbb Z^d\}$ that permit jumps of arbitrary length. Our focus is on the Quenched Invariance Principle (QIP) which we establish by a combination of corrector methods, functional inequalities and heat-kernel technology assuming that the $p$-th moment of $\sum_{x\in\mathbb Z^d}C_{0,x}|x|^2$ and $q$-th moment of $1/C_{0,x}$ for $x$ neighboring the origin are finite for some $p,q\ge1$ with $p^{-1}+q^{-1}<2/d$. In particular, a QIP thus holds for random walks on long-range percolation graphs with connectivity exponents larger than $2d$ in all $d\ge2$, provided all the nearest-neighbor edges are present. Although still limited by moment conditions, our method of proof is novel in that it avoids proving everywhere-sublinearity of the corrector. This is relevant because we show that, for long-range percolation with exponents between $d+2$ and $2d$, the corrector exists but fails to be sublinear everywhere. Similar examples are constructed also for nearest-neighbor, ergodic conductances in $d\ge3$ under the conditions complementary to those of the recent work of P. Bella and M. Schäffner. These examples elucidate the limitations of elliptic-regularity techniques that underlie much of the recent progress on these problems.

math.PR↗
arXiv2021

Zero-bias Deep Learning Enabled Quick and Reliable Abnormality Detection in IoT

Abnormality detection is essential to the performance of safety-critical and latency-constrained systems. However, as systems are becoming increasingly complicated with a large quantity of heterogeneous data, conventional statistical change point detection methods are becoming less effective and efficient. Although Deep Learning (DL) and Deep Neural Networks (DNNs) are increasingly employed to handle heterogeneous data, they still lack theoretic assurable performance and explainability. This paper integrates zero-bias DNN and Quickest Event Detection algorithms to provide a holistic framework for quick and reliable detection of both abnormalities and time-dependent abnormal events in the Internet of Things (IoT). We first use the zero-bias dense layer to increase the explainability of DNN. We provide a solution to convert zero-bias DNN classifiers into performance assured binary abnormality detectors. Using the converted abnormality detector, we then present a sequential quickest detection scheme that provides the theoretically assured lowest abnormal event detection delay under false alarm constraints. Finally, we demonstrate the effectiveness of the framework using both massive signal records from real-world aviation communication systems and simulated data. Code and data of our work is available at \url{https://github.com/pcwhy/AbnormalityDetectionInZbDNN}

cs.NI↗
arXiv2021

Drug Discovery Approaches using Quantum Machine Learning

Traditional drug discovery pipeline takes several years and cost billions of dollars. Deep generative and predictive models are widely adopted to assist in drug development. Classical machines cannot efficiently produce atypical patterns of quantum computers which might improve the training quality of learning tasks. We propose a suite of quantum machine learning techniques e.g., generative adversarial network (GAN), convolutional neural network (CNN) and variational auto-encoder (VAE) to generate small drug molecules, classify binding pockets in proteins, and generate large drug molecules, respectively.

cs.ET↗
arXiv2021

Robust Reinforcement Learning under model misspecification

Reinforcement learning has achieved remarkable performance in a wide range of tasks these days. Nevertheless, some unsolved problems limit its applications in real-world control. One of them is model misspecification, a situation where an agent is trained and deployed in environments with different transition dynamics. We propose an novel framework that utilize history trajectory and Partial Observable Markov Decision Process Modeling to deal with this dilemma. Additionally, we put forward an efficient adversarial attack method to assist robust training. Our experiments in four gym domains validate the effectiveness of our framework.

cs.LG↗
arXiv2021

Smart Scheduling based on Deep Reinforcement Learning for Cellular Networks

To improve the system performance towards the Shannon limit, advanced radio resource management mechanisms play a fundamental role. In particular, scheduling should receive much attention, because it allocates radio resources among different users in terms of their channel conditions and QoS requirements. The difficulties of scheduling algorithms are the tradeoffs need to be made among multiple objectives, such as throughput, fairness and packet drop rate. We propose a smart scheduling scheme based on deep reinforcement learning (DRL). We not only verify the performance gain achieved, but also provide implementation-friend designs, i.e., a scalable neural network design for the agent and a virtual environment training framework. With the scalable neural network design, the DRL agent can easily handle the cases when the number of active users is time-varying without the need to redesign and retrain the DRL agent. Training the DRL agent in a virtual environment offline first and using it as the initial version in the practical usage helps to prevent the system from suffering from performance and robustness degradation due to the time-consuming training. Through both simulations and field tests, we show that the DRL-based smart scheduling outperforms the conventional scheduling method and can be adopted in practical systems.

cs.LG↗
arXiv2021

NaturalAE: Natural and Robust Physical Adversarial Examples for Object Detectors

In this paper, we propose a natural and robust physical adversarial example attack method targeting object detectors under real-world conditions. The generated adversarial examples are robust to various physical constraints and visually look similar to the original images, thus these adversarial examples are natural to humans and will not cause any suspicions. First, to ensure the robustness of the adversarial examples in real-world conditions, the proposed method exploits different image transformation functions, to simulate various physical changes during the iterative optimization of the adversarial examples generation. Second, to construct natural adversarial examples, the proposed method uses an adaptive mask to constrain the area and intensities of the added perturbations, and utilizes the real-world perturbation score (RPS) to make the perturbations be similar to those real noises in physical world. Compared with existing studies, our generated adversarial examples can achieve a high success rate with less conspicuous perturbations. Experimental results demonstrate that, the generated adversarial examples are robust under various indoor and outdoor physical conditions, including different distances, angles, illuminations, and photographing. Specifically, the attack success rate of generated adversarial examples indoors and outdoors is high up to 73.33% and 82.22%, respectively. Meanwhile, the proposed method ensures the naturalness of the generated adversarial example, and the size of added perturbations is much smaller than the perturbations in the existing works. Further, the proposed physical adversarial attack method can be transferred from the white-box models to other object detection models.

cs.CV↗
arXiv2021

Two tales of science technology linkage: Patent in-text versus front-page references

There is recurrent debate about how useful science is for technological development, but we know little about what kinds of science are more useful for technology. This paper fills this gap in the literature by exploring how the value of a patent (as measured by patent forward citations and the stock market response to the issuing of the patent) depends on the characteristics of the scientific papers that it builds on, specifically, basicness, interdisciplinarity, novelty, and scientific citations. Using a dataset of 33,337 USPTO biotech utility patents and their 860,879 in-text references to Web of Science journal articles, we find (1) a positive effect of the number of referenced scientific papers, (2) an inverted U-shaped effect of basicness, (3) an insignificant effect of interdisciplinarity, (4) a discontinuous and nonlinear effect of novelty, and (5) a positive effect of scientific citations for patent market value but an insignificant effect on patent citations. In addition, in-text referenced papers have a higher chance of being listed on the front-page of the same patent when they are moderately basic, less interdisciplinary, less novel, and more highly cited. Accordingly, using front-page reference yields substantially different results than using in-text references.

cs.DL↗
arXiv2021

Bismuth-doping Alters Structural Phase Transitions in Methylammonium Lead Tribromide Single Crystals

We study the effects of bismuth doping on the crystal structure and phase transitions in single crystals of the perovskite semiconductor methylammonium lead tribromide, MAPbBr3. By measuring temperature-dependent specific heat capacity (Cp) we find that, as Bi doping increases, the phase transition assigned to the cubic to tetragonal phase boundary decreases in temperature. Furthermore, after doping we observe one phase transition between 135 and 155 K, in contrast to two transitions observed in the undoped single crystal. These results appear strikingly similar to previously reported effects of mechanical pressure on perovskite crystal structure. Using X-ray diffraction, we show that the lattice constant decreases as Bi is incorporated into the crystal, as predicted by density functional theory (DFT). We propose that bismuth substitutional doping on the lead site is dominant, resulting in BiPb+ centers which induce compressive chemical strain that alters the crystalline phase transitions.

cond-mat.mtrl-sci↗
arXiv2021

Transport Induced Dimer State from Topological Corner States

Recently, a new type of second-order topological insulator has been theoretically proposed by introducing an in-plane Zeeman field into the Kane-Mele model in the two-dimensional honeycomb lattice. A pair of topological corner states arise at the corners with obtuse angles of an isolated diamond-shaped flake. To probe the corner states, we study their transport properties by attaching two leads to the system. Dressed by incoming electrons, the dynamic corner state is very different from its static counterpart. Resonant tunneling through the dressed corner state can occur by tuning the in-plane Zeeman field. At the resonance, the pair of spatially well separated and highly localized corner states can form a dimer state, whose wavefunction extends almost the entire bulk of the diamond-shaped flake. By varying the Zeeman field strength, multiple resonant tunneling events are mediated by the same dimer state. This re-entrance effect can be understood by a simple model. These findings extend our understanding of dynamic aspects of the second-order topological corner states.

cond-mat.mes-hall↗
arXiv2021

Heat kernels for reflected diffusions with jumps on inner uniform domains

In this paper, we study sharp two-sided heat kernel estimates for a large class of symmetric reflected diffusions with jumps on the closure of an inner uniform domain $D$ in a length metric space. The length metric is the intrinsic metric of a strongly local Dirichlet form. When $D$ is an inner uniform domain in the Euclidean space, a prototype for a special case of the processes under consideration are symmetric reflected diffusions with jumps on $D$, whose infinitesimal generators are non-local (pseudo-differential) operators $L$ on $D$ of the form $$ L u(x) =\frac12 \sum_{i, j=1}^d \frac{\partial}{\partial x_i} \left(a_{ij}(x) \frac{\partial u(x)}{\partial x_j}\right) + \lim_{\eps \downarrow 0} \int_{\{y\in D: \, ρ_D(y, x)>\eps\}} (u(y)-u(x)) J(x, y)\, dy $$ satisfying "Neumann boundary condition". Here, $ρ_D(x,y)$ is the length metric on $D$, $A(x)=(a_{ij}(x))_{1\leq i,j\leq d}$ is a measurable $d\times d$ matrix-valued function on $D$ that is uniformly elliptic and bounded, and $$ J(x,y):= \frac{1}{Φ(ρ_D(x,y))} \int_{[α_1, α_2]} \frac{c(α, x,y)} {ρ_D(x,y)^{d+α}} \,ν(dα) , $$ where $ν$ is a finite measure on $[α_1, α_2] \subset (0, 2)$, $Φ$ is an increasing function on $[ 0, \infty )$ with $c_1e^{c_2r^β} \le Φ(r) \le c_3 e^{c_4r^β}$ for some $β\in [0,\infty]$, and $c(α, x, y)$ is a jointly measurable function that is bounded between two positive constants and is symmetric in $(x, y)$.

math.PR↗
arXiv2021

ActiveGuard: An Active DNN IP Protection Technique via Adversarial Examples

The training of Deep Neural Networks (DNN) is costly, thus DNN can be considered as the intellectual properties (IP) of model owners. To date, most of the existing protection works focus on verifying the ownership after the DNN model is stolen, which cannot resist piracy in advance. To this end, we propose an active DNN IP protection method based on adversarial examples against DNN piracy, named ActiveGuard. ActiveGuard aims to achieve authorization control and users' fingerprints management through adversarial examples, and can provide ownership verification. Specifically, ActiveGuard exploits the elaborate adversarial examples as users' fingerprints to distinguish authorized users from unauthorized users. Legitimate users can enter fingerprints into DNN for identity authentication and authorized usage, while unauthorized users will obtain poor model performance due to an additional control layer. In addition, ActiveGuard enables the model owner to embed a watermark into the weights of DNN. When the DNN is illegally pirated, the model owner can extract the embedded watermark and perform ownership verification. Experimental results show that, for authorized users, the test accuracy of LeNet-5 and Wide Residual Network (WRN) models are 99.15% and 91.46%, respectively, while for unauthorized users, the test accuracy of the two DNNs are only 8.92% (LeNet-5) and 10% (WRN), respectively. Besides, each authorized user can pass the fingerprint authentication with a high success rate (up to 100%). For ownership verification, the embedded watermark can be successfully extracted, while the normal performance of the DNN model will not be affected. Further, ActiveGuard is demonstrated to be robust against fingerprint forgery attack, model fine-tuning attack and pruning attack.

cs.CR↗