arXiv subjects

Xin Chen

Publications and source records attributed to Xin Chen.

At least 577 records · Page 32Linked to original sources

arXiv2020

PAI-graphene: a new topological semimetallic two-dimensional carbon allotrope with highly tunable anisotropic Dirac cones

Using evolutionary algorithm for crystal structure prediction, we present a new stable two-dimensional (2D) carbon allotrope composed of polymerized as-indacenes (PAI) in a zigzag pattern, namely PAI-graphene whose energy is lower than most of the reported 2D allotropes of graphene. Crucially, the crystal structure realizes a nonsymmorphic layer group that enforces a nontrivial global topology of the band structure with two Dirac cones lying perfectly at the Fermi level. The absence of electron/hole pockets makes PAI-graphene a pristine crystalline topological semimetal having anisotropic Fermi velocities with a high value of $7.0 \times 10^{5}$ m/s. We show that while the semimetallic property of the allotrope is robust against the application of strain, the positions of the Dirac cone and the Fermi velocities can be modified significantly with strain. Moreover, by combining strain along both the x- and y-directions, two band inversions take place at $Γ$ leading to the annihilation of the Dirac nodes demonstrating the possibility of strain-controlled conversion of a topological semimetal into a semiconductor. Finally we formulate the bulk-boundary correspondence of the topological nodal phase in the form of a generalized Zak-phase argument finding a perfect agreement with the topological edge states computed for different edge-terminations.

cond-mat.mtrl-sci↗

arXiv2020

CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search

Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They also lack efficient mechanisms to reuse knowledge when confronting multiple tasks. These challenges preclude their applicability, and motivate our proposal of CATCH, a novel Context-bAsed meTa reinforcement learning (RL) algorithm for transferrable arChitecture searcH. The combination of meta-learning and RL allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces. CATCH utilizes a probabilistic encoder to encode task properties into latent context variables, which then guide CATCH's controller to quickly "catch" top-performing networks. The contexts also assist a network evaluator in filtering inferior candidates and speed up learning. Extensive experiments demonstrate CATCH's universality and search efficiency over many other widely-recognized algorithms. It is also capable of handling cross-domain architecture search as competitive networks on ImageNet, COCO, and Cityscapes are identified. This is the first work to our knowledge that proposes an efficient transferrable NAS solution while maintaining robustness across various settings.

cs.LG↗

arXiv2020

GOLD-NAS: Gradual, One-Level, Differentiable

There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper, we first relax these manually designed constraints and enlarge the search space to contain more than $10^{160}$ candidates. In the new space, most existing differentiable search methods can fail dramatically. We then propose a novel algorithm named Gradual One-Level Differentiable Neural Architecture Search (GOLD-NAS) which introduces a variable resource constraint to one-level optimization so that the weak operators are gradually pruned out from the super-network. In standard image classification benchmarks, GOLD-NAS can find a series of Pareto-optimal architectures within a single search procedure. Most of the discovered architectures were never studied before, yet they achieve a nice tradeoff between recognition accuracy and model complexity. We believe the new space and search algorithm can advance the search of differentiable NAS.

cs.CV↗

arXiv2020

Periodic homogenization of non-symmetric Lévy-type processes

In this paper, we study homogenization problem for strong Markov processes on $\R^d$ having infinitesimal generators $$ \sL f(x)=\int_{\R^d}\left(f(x+z)-f(x)-\langle \nabla f(x), z\rangle \I_{\{|z|\le 1\}} \right) k(x,z)\, Π(dz) +\langle b(x), \nabla f(x) \rangle, \quad f\in C^2_b (\R^d) $$ in periodic media, where $Π$ is a non-negative measure on $\R^d$ that does not charge the origin $0$, satisfies $\int_{\R^d} (1 \wedge |z|^2)\, Π(dz)<\infty$, and can be singular with respect to the Lebesgue measure on $\R^d$. Under a proper scaling, we show the scaled processes converge weakly to Lévy processes on $\R^d$. The results are a counterpart of the celebrated work \cite{BLP,Bh} in the jump-diffusion setting. In particular, we completely characterize the homogenized limiting processes when $b(x) $ is a bounded continuous multivariate 1-periodic $\R^d$-valued function, $k(x,z)$ is a non-negative bounded continuous function that is multivariate 1-periodic in both $x$ and $z$ variables, and, in spherical coordinate $z=(r, θ) \in \R_+\times \bS^{d-1}$, $$ \I_{\{|z|>1\}}\,Π(dz) = \I_{\{ r>1\}} \varrho_0(dθ) \, \frac{ dr }{r^{1+α}} $$ with $α\in (0,\infty)$ and $\varrho_0$ being any finite measure on the unit sphere $\bS^{d-1}$ in $\R^d$. Different phenomena occur depending on the values of $α$; there are five cases: $α\in (0, 1)$, $α=1$, $α\in (1, 2)$, $α=2$ and $α\in (2, \infty)$.

math.PR↗

arXiv2020

Parametric amplifier for Bell measurement in continuous-variable quantum state teleportation

A parametric amplifier is in essence a linear four-port device, which couples and linearly mixes two inputs before amplifying and sending them to two output ports. Here, we show that for quadrature-phase amplitudes, a parametric amplifier can replace beam splitters to play the role of mixer. We apply this idea to a continuous-variable quantum state teleportation scheme in which a parametric amplifier replaces a beam splitter in Bell measurement. We show that this scheme is loss-tolerant in the Bell measurement process and thus demonstrate the advantage of PA over BS in the applications in quantum measurement.

quant-ph↗

arXiv2020

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

This paper presents a fully automatic framework for extracting editable 3D objects directly from a single photograph. Unlike previous methods which recover either depth maps, point clouds, or mesh surfaces, we aim to recover 3D objects with semantic parts and can be directly edited. We base our work on the assumption that most human-made objects are constituted by parts and these parts can be well represented by generalized primitives. Our work makes an attempt towards recovering two types of primitive-shaped objects, namely, generalized cuboids and generalized cylinders. To this end, we build a novel instance-aware segmentation network for accurate part separation. Our GeoNet outputs a set of smooth part-level masks labeled as profiles and bodies. Then in a key stage, we simultaneously identify profile-body relations and recover 3D parts by sweeping the recognized profile along their body contour and jointly optimize the geometry to align with the recovered masks. Qualitative and quantitative experiments show that our algorithm can recover high quality 3D models and outperforms existing methods in both instance segmentation and 3D reconstruction. The dataset and code of AutoSweep are available at https://chenxin.tech/AutoSweep.html.

cs.CV↗

arXiv2020

Performance Optimization of a Fuzzy Entropy based Feature Selection and Classification Framework

In this paper, based on a fuzzy entropy feature selection framework, different methods have been implemented and compared to improve the key components of the framework. Those methods include the combinations of three ideal vector calculations, three maximal similarity classifiers and three fuzzy entropy functions. Different feature removal orders based on the fuzzy entropy values were also compared. The proposed method was evaluated on three publicly available biomedical datasets. From the experiments, we concluded the optimized combination of the ideal vector, similarity classifier and fuzzy entropy function for feature selection. The optimized framework was also compared with other six classical filter-based feature selection methods. The proposed method was ranked as one of the top performers together with the Correlation and ReliefF methods. More importantly, the proposed method achieved the most stable performance for all three datasets when the features being gradually removed. This indicates a better feature ranking performance than the other compared methods.

cs.LG↗

arXiv2020

A Novel Weighted Combination Method for Feature Selection using Fuzzy Sets

In this paper, we propose a novel weighted combination feature selection method using bootstrap and fuzzy sets. The proposed method mainly consists of three processes, including fuzzy sets generation using bootstrap, weighted combination of fuzzy sets and feature ranking based on defuzzification. We implemented the proposed method by combining four state-of-the-art feature selection methods and evaluated the performance based on three publicly available biomedical datasets using five-fold cross validation. Based on the feature selection results, our proposed method produced comparable (if not better) classification accuracies to the best of the individual feature selection methods for all evaluated datasets. More importantly, we also applied standard deviation and Pearson's correlation to measure the stability of the methods. Remarkably, our combination method achieved significantly higher stability than the four individual methods when variations and size reductions were introduced to the datasets.

cs.LG↗

arXiv2020

A Novel Meta Learning Framework for Feature Selection using Data Synthesis and Fuzzy Similarity

This paper presents a novel meta learning framework for feature selection (FS) based on fuzzy similarity. The proposed method aims to recommend the best FS method from four candidate FS methods for any given dataset. This is achieved by firstly constructing a large training data repository using data synthesis. Six meta features that represent the characteristics of the training dataset are then extracted. The best FS method for each of the training datasets is used as the meta label. Both the meta features and the corresponding meta labels are subsequently used to train a classification model using a fuzzy similarity measure based framework. Finally the trained model is used to recommend the most suitable FS method for a given unseen dataset. This proposed method was evaluated based on eight public datasets of real-world applications. It successfully recommended the best method for five datasets and the second best method for one dataset, which outperformed any of the four individual FS methods. Besides, the proposed method is computationally efficient for algorithm selection, leading to negligible additional time for the feature selection process. Thus, the paper contributes a novel method for effectively recommending which feature selection method to use for any new given dataset.

cs.LG↗

arXiv2020

Online Residential Demand Response via Contextual Multi-Armed Bandits

Residential loads have great potential to enhance the efficiency and reliability of electricity systems via demand response (DR) programs. One major challenge in residential DR is to handle the unknown and uncertain customer behaviors. Previous works use learning techniques to predict customer DR behaviors, while the influence of time-varying environmental factors is generally neglected, which may lead to inaccurate prediction and inefficient load adjustment. In this paper, we consider the residential DR problem where the load service entity (LSE) aims to select an optimal subset of customers to maximize the expected load reduction with a financial budget. To learn the uncertain customer behaviors under the environmental influence, we formulate the residential DR as a contextual multi-armed bandit (MAB) problem, and the online learning and selection (OLS) algorithm based on Thompson sampling is proposed to solve it. This algorithm takes the contextual information into consideration and is applicable to complicated DR settings. Numerical simulations are performed to demonstrate the learning effectiveness of the proposed algorithm.

eess.SY↗

arXiv2020

Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters

DARTS is a popular algorithm for neural architecture search (NAS). Despite its great advantage in search efficiency, DARTS often suffers weak stability, which reflects in the large variation among individual trials as well as the sensitivity to the hyper-parameters of the search process. This paper owes such instability to an optimization gap between the super-network and its sub-networks, namely, improving the validation accuracy of the super-network does not necessarily lead to a higher expectation on the performance of the sampled sub-networks. Then, we point out that the gap is due to the inaccurate estimation of the architectural gradients, based on which we propose an amended estimation method. Mathematically, our method guarantees a bounded error from the true gradients while the original estimation does not. Our approach bridges the gap from two aspects, namely, amending the estimation on the architectural gradients, and unifying the hyper-parameter settings in the search and re-training stages. Experiments on CIFAR10 and ImageNet demonstrate that our approach largely improves search stability and, more importantly, enables DARTS-based approaches to explore much larger search spaces that have not been investigated before.

cs.LG↗

arXiv2020

Random Conductance Models with Stable-like Jumps: Quenched Invariance Principle

We study the quenched invariance principle for random conductance models with long range jumps on $\Z^d$, where the transition probability from $x$ to $y$ is, on average, comparable to $|x-y|^{-(d+α)}$ with $α\in (0,2)$ but is allowed to be degenerate. Under some moment conditions on the conductance, we prove that the scaling limit of the Markov process is a symmetric $α$-stable Lévy process on $\R^d$.The well-known corrector method in homogenization theory does not seem to work in this setting. Instead, we utilize probabilistic potential theory for the corresponding jump processes. Two essential ingredients of our proof are the tightness estimate and the Hölder regularity of caloric functions for non-elliptic $α$-stable-like processes on graphs. Our method is robust enough to apply not only for $\Z^d$ but also for more general graphs whose scaling limits are nice metric measure spaces.

math.PR↗

arXiv2020

DRU-net: An Efficient Deep Convolutional Neural Network for Medical Image Segmentation

Residual network (ResNet) and densely connected network (DenseNet) have significantly improved the training efficiency and performance of deep convolutional neural networks (DCNNs) mainly for object classification tasks. In this paper, we propose an efficient network architecture by considering advantages of both networks. The proposed method is integrated into an encoder-decoder DCNN model for medical image segmentation. Our method adds additional skip connections compared to ResNet but uses significantly fewer model parameters than DenseNet. We evaluate the proposed method on a public dataset (ISIC 2018 grand-challenge) for skin lesion segmentation and a local brain MRI dataset. In comparison with ResNet-based, DenseNet-based and attention network (AttnNet) based methods within the same encoder-decoder network structure, our method achieves significantly higher segmentation accuracy with fewer number of model parameters than DenseNet and AttnNet. The code is available on GitHub (GitHub link: https://github.com/MinaJf/DRU-net).

eess.IV↗

arXiv2020

FU-net: Multi-class Image Segmentation Using Feedback Weighted U-net

In this paper, we present a generic deep convolutional neural network (DCNN) for multi-class image segmentation. It is based on a well-established supervised end-to-end DCNN model, known as U-net. U-net is firstly modified by adding widely used batch normalization and residual block (named as BRU-net) to improve the efficiency of model training. Based on BRU-net, we further introduce a dynamically weighted cross-entropy loss function. The weighting scheme is calculated based on the pixel-wise prediction accuracy during the training process. Assigning higher weights to pixels with lower segmentation accuracies enables the network to learn more from poorly predicted image regions. Our method is named as feedback weighted U-net (FU-net). We have evaluated our method based on T1- weighted brain MRI for the segmentation of midbrain and substantia nigra, where the number of pixels in each class is extremely unbalanced to each other. Based on the dice coefficient measurement, our proposed FU-net has outperformed BRU-net and U-net with statistical significance, especially when only a small number of training examples are available. The code is publicly available in GitHub (GitHub link: https://github.com/MinaJf/FU-net).

eess.IV↗

arXiv2020

A Spatially Constrained Deep Convolutional Neural Network for Nerve Fiber Segmentation in Corneal Confocal Microscopic Images using Inaccurate Annotations

Semantic image segmentation is one of the most important tasks in medical image analysis. Most state-of-the-art deep learning methods require a large number of accurately annotated examples for model training. However, accurate annotation is difficult to obtain especially in medical applications. In this paper, we propose a spatially constrained deep convolutional neural network (DCNN) to achieve smooth and robust image segmentation using inaccurately annotated labels for training. In our proposed method, image segmentation is formulated as a graph optimization problem that is solved by a DCNN model learning process. The cost function to be optimized consists of a unary term that is calculated by cross entropy measurement and a pairwise term that is based on enforcing a local label consistency. The proposed method has been evaluated based on corneal confocal microscopic (CCM) images for nerve fiber segmentation, where accurate annotations are extremely difficult to be obtained. Based on both the quantitative result of a synthetic dataset and qualitative assessment of a real dataset, the proposed method has achieved superior performance in producing high quality segmentation results even with inaccurate labels for training.

cs.CV↗

arXiv2020

Defect Engineering of Two-dimensional Molybdenum Disulfide

Two-dimensional (2D) molybdenum disulfide (MoS2) holds great promise in electronic and optoelectronic applications owing to its unique structure and intriguing properties. The intrinsic defects such as sulfur vacancies (SVs) of MoS2 nanosheets are found to be detrimental to the device efficiency. To mitigate this problem, functionalization of 2D MoS2 using thiols has emerged as one of the key strategies for engineering defects. Herein, we demonstrate an approach to controllably engineer the SVs of chemically exfoliated MoS2 nanosheets using a series of substituted thiophenols in solution. The degree of functionalization can be tuned by varying the electron withdrawing strength of substituents in thiophenols. We find that the intensity of 2LA(M) peak normalized to A1g peak strongly correlates to the degree of functionalization. Our results provide a spectroscopic indicator to monitor and quantify the defect engineering process. This method of MoS2 defect functionalization in solution also benefits the further exploration of defect free MoS2 for a wide range of applications.

physics.chem-ph↗

arXiv2020

A generic ensemble based deep convolutional neural network for semi-supervised medical image segmentation

Deep learning based image segmentation has achieved the state-of-the-art performance in many medical applications such as lesion quantification, organ detection, etc. However, most of the methods rely on supervised learning, which require a large set of high-quality labeled data. Data annotation is generally an extremely time-consuming process. To address this problem, we propose a generic semi-supervised learning framework for image segmentation based on a deep convolutional neural network (DCNN). An encoder-decoder based DCNN is initially trained using a few annotated training samples. This initially trained model is then copied into sub-models and improved iteratively using random subsets of unlabeled data with pseudo labels generated from models trained in the previous iteration. The number of sub-models is gradually decreased to one in the final iteration. We evaluate the proposed method on a public grand-challenge dataset for skin lesion segmentation. Our method is able to significantly improve beyond fully supervised model learning by incorporating unlabeled data.

cs.CV↗

arXiv2020

Distributed Automatic Load-Frequency Control with Optimality in Power Systems

With the increasing penetration of renewable energy resources, power systems face new challenges in balancing power supply and demand and maintaining the nominal frequency. This paper studies load control to handle these challenges. In particular, a fully distributed automatic load control (ALC) algorithm, which only needs local measurement and local communication, is proposed. We prove that the load control algorithm globally converges to an optimal operating point which minimizes the total disutility of users, restores the nominal frequency and the scheduled tie-line power flows, and respects the load capacity limits and the thermal constraints of transmission lines. It is further shown that the asymptotic convergence still holds even when inaccurate system parameters are used in the control algorithm. In addition, the global exponential convergence of the reduced ALC algorithm without considering the capacity limits is proved and leveraged to study the dynamical tracking performance and robustness of the algorithm. Lastly, the effectiveness, optimality, and robustness of the proposed algorithm are demonstrated via numerical simulations.

math.OC↗