arXiv subjects

Xue Jiang

Publications and source records attributed to Xue Jiang.

At least 109 records · Page 6Linked to original sources

arXiv2022

HELoC: Hierarchical Contrastive Learning of Source Code Representation

Abstract syntax trees (ASTs) play a crucial role in source code representation. However, due to the large number of nodes in an AST and the typically deep AST hierarchy, it is challenging to learn the hierarchical structure of an AST effectively. In this paper, we propose HELoC, a hierarchical contrastive learning model for source code representation. To effectively learn the AST hierarchy, we use contrastive learning to allow the network to predict the AST node level and learn the hierarchical relationships between nodes in a self-supervised manner, which makes the representation vectors of nodes with greater differences in AST levels farther apart in the embedding space. By using such vectors, the structural similarities between code snippets can be measured more precisely. In the learning process, a novel GNN (called Residual Self-attention Graph Neural Network, RSGNN) is designed, which enables HELoC to focus on embedding the local structure of an AST while capturing its overall structure. HELoC is self-supervised and can be applied to many source code related downstream tasks such as code classification, code clone detection, and code clustering after pre-training. Our extensive experiments demonstrate that HELoC outperforms the state-of-the-art source code representation models.

cs.SE↗

arXiv2022

An Adaptive Finite Element DtN Method for Maxwell's Equations

This paper is concerned with a numerical solution to the scattering of a time-harmonic electromagnetic wave by a bounded and impenetrable obstacle in three dimensions. The electromagnetic wave propagation is modeled by a boundary value problem of Maxwell's equations in the exterior domain of the obstacle. Based on the Dirichlet-to-Neumann (DtN) operator, which is defined by an infinite series, an exact transparent boundary condition is introduced and the scattering problem is reduced equivalently into a bounded domain. An a posteriori error estimate based adaptive finite element DtN method is developed to solve the discrete variational problem, where the DtN operator is truncated into a sum of finitely many terms. The a posteriori error estimate takes into account both the finite element approximation error and the truncation error of the DtN operator. The latter is shown to decay exponentially with respect to the truncation parameter. Numerical experiments are presented to illustrate the effectiveness of the proposed method.

math.NA↗

arXiv2022

End-to-End Neural Speech Coding for Real-Time Communications

Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low latency for RTC. It takes an encoder-temporal filtering-decoder paradigm that has seldom been investigated in audio coding. An interleaved structure is proposed for temporal filtering to capture both short-term and long-term temporal dependencies. Furthermore, with end-to-end optimization, the TFNet is jointly optimized with speech enhancement and packet loss concealment, yielding a one-for-all network for three tasks. Both subjective and objective results demonstrate the efficiency of the proposed TFNet.

cs.SD↗

arXiv2021

Self-supervised Contrastive Learning for EEG-based Sleep Staging

EEG signals are usually simple to obtain but expensive to label. Although supervised learning has been widely used in the field of EEG signal analysis, its generalization performance is limited by the amount of annotated data. Self-supervised learning (SSL), as a popular learning paradigm in computer vision (CV) and natural language processing (NLP), can employ unlabeled data to make up for the data shortage of supervised learning. In this paper, we propose a self-supervised contrastive learning method of EEG signals for sleep stage classification. During the training process, we set up a pretext task for the network in order to match the right transformation pairs generated from EEG signals. In this way, the network improves the representation ability by learning the general features of EEG signals. The robustness of the network also gets improved in dealing with diverse data, that is, extracting constant features from changing data. In detail, the network's performance depends on the choice of transformations and the amount of unlabeled data used in the training process of self-supervised learning. Empirical evaluations on the Sleep-edf dataset demonstrate the competitive performance of our method on sleep staging (88.16% accuracy and 81.96% F1 score) and verify the effectiveness of SSL strategy for EEG signal analysis in limited labeled data regimes. All codes are provided publicly online.

cs.LG↗

arXiv2021

TreeBERT: A Tree-Based Pre-Trained Model for Programming Language

Source code can be parsed into the abstract syntax tree (AST) based on defined syntax rules. However, in pre-training, little work has considered the incorporation of tree structure into the learning process. In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks. To utilize tree structure, TreeBERT represents the AST corresponding to the code as a set of composition paths and introduces node position embedding. The model is trained by tree masked language modeling (TMLM) and node order prediction (NOP) with a hybrid objective. TMLM uses a novel masking strategy designed according to the tree's characteristics to help the model understand the AST and infer the missing semantics of the AST. With NOP, TreeBERT extracts the syntactical structure by learning the order constraints of nodes in AST. We pre-trained TreeBERT on datasets covering multiple programming languages. On code summarization and code documentation tasks, TreeBERT outperforms other pre-trained models and state-of-the-art models designed for these tasks. Furthermore, TreeBERT performs well when transferred to the pre-trained unseen programming language.

cs.LG↗

arXiv2021

Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline

Transfer learning (TL) has been widely used in motor imagery (MI) based brain-computer interfaces (BCIs) to reduce the calibration effort for a new subject, and demonstrated promising performance. While a closed-loop MI-based BCI system, after electroencephalogram (EEG) signal acquisition and temporal filtering, includes spatial filtering, feature engineering, and classification blocks before sending out the control signal to an external device, previous approaches only considered TL in one or two such components. This paper proposes that TL could be considered in all three components (spatial filtering, feature engineering, and classification) of MI-based BCIs. Furthermore, it is also very important to specifically add a data alignment component before spatial filtering to make the data from different subjects more consistent, and hence to facilitate subsequential TL. Offline calibration experiments on two MI datasets verified our proposal. Especially, integrating data alignment and sophisticated TL approaches can significantly improve the classification performance, and hence greatly reduces the calibration effort.

eess.SP↗

arXiv2021

MRNet: a Multi-scale Residual Network for EEG-based Sleep Staging

Sleep staging based on electroencephalogram (EEG) plays an important role in the clinical diagnosis and treatment of sleep disorders. In order to emancipate human experts from heavy labeling work, deep neural networks have been employed to formulate automated sleep staging systems recently. However, EEG signals lose considerable detailed information in network propagation, which affects the representation of deep features. To address this problem, we propose a new framework, called MRNet, for data-driven sleep staging by integrating a multi-scale feature fusion model and a Markov-based sequential correction algorithm. The backbone of MRNet is a residual block-based network, which performs as a feature extractor.Then the fusion model constructs a feature pyramid by concatenating the outputs from the different depths of the backbone, which can help the network better comprehend the signals in different scales. The Markov-based sequential correction algorithm is designed to reduce the output jitters generated by the classifier. The algorithm depends on a prior stage distribution associated with the sleep stage transition rule and the Markov chain. Experiment results demonstrate the competitive performance of our proposed approach on both accuracy and F1 score (e.g., 85.14% Acc and 78.91% F1 score on Sleep-EDFx, and 87.59% Acc and 79.62% F1 score on Sleep-EDF).

cs.LG↗

arXiv2021

EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks

Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is implementable in practice and has never been considered before. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs and calling for urgent attention to address it.

cs.CR↗

arXiv2020

Enhanced Ferromagnetism of CrI3 Bilayer by Self-Intercalation

Two-dimensional (2D) ferromagnets with high Curie temperature have long been the pursuit for electronic and spintronic applications. CrI3 is a rising star of intrinsic 2D ferromagnets, however, it suffers from weak exchange coupling. Here we propose a general strategy of self-intercalation to achieve enhanced ferromagnetism in bilayer CrI3. We showed that filling either Cr or I atoms into the van der Waals gap of stacked and twisted CrI3 bilayers can induce the double exchange effect and significantly strengthen the interlayer ferromagnetic coupling. According to our first-principles calculations, the intercalated native atoms act as covalent bridge between two CrI3 layers and lead to discrepant oxidation states for the Cr atoms. These theoretical results offer a facile route to achieve high-Curie-temperature 2D magnets for device implementation.

cond-mat.mtrl-sci↗

arXiv2020

A fast algorithm for the electromagnetic scattering from a large rectangular cavity in three dimensions

The paper is concerned with the three-dimensional electromagnetic scattering from a large open rectangular cavity that is embedded in a perfectly electrically conducting infinite ground plane. By introducing a transparent boundary condition, the scattering problem is formulated into a boundary value problem in the bounded cavity. Based on the Fourier expansions of the electric field, the Maxwell equation is reduced to one-dimensional ordinary differential equations for the Fourier coefficients. A fast algorithm, employing the fast Fourier transform and the Gaussian elimination, is developed to solve the resulting linear system for the cavity which is filled with either a homogeneous or a layered medium. In addition, a novel scheme is designed to evaluate rapidly and accurately the Fourier transform of singular integrals. Numerical experiments are presented for large cavities to demonstrate the superior performance of the proposed method.

math.NA↗

arXiv2020

An adaptive finite element DtN method for the elastic wave scattering by biperiodic structures

Consider the scattering of a time-harmonic elastic plane wave by a bi-periodic rigid surface. The displacement of elastic wave motion is modeled by the three-dimensional Navier equation in an open domain above the surface. Based on the Dirichlet-to-Neumann (DtN) operator, which is given as an infinite series, an exact transparent boundary condition is introduced and the scattering problem is formulated equivalently into a boundary value problem in a bounded domain. An a posteriori error estimate based adaptive finite element DtN method is proposed to solve the discrete variational problem where the DtN operator is truncated into a finite number of terms. The a posteriori error estimate takes account of the finite element approximation error and the truncation error of the DtN operator which is shown to decay exponentially with respect to the truncation parameter. Numerical experiments are presented to illustrate the effectiveness of the proposed method.

math.NA↗

arXiv2020

Pool-Based Unsupervised Active Learning for Regression Using Iterative Representativeness-Diversity Maximization (iRDM)

Active learning (AL) selects the most beneficial unlabeled samples to label, and hence a better machine learning model can be trained from the same number of labeled samples. Most existing active learning for regression (ALR) approaches are supervised, which means the sampling process must use some label information, or an existing regression model. This paper considers completely unsupervised ALR, i.e., how to select the samples to label without knowing any true label information. We propose a novel unsupervised ALR approach, iterative representativeness-diversity maximization (iRDM), to optimally balance the representativeness and the diversity of the selected samples. Experiments on 12 datasets from various domains demonstrated its effectiveness. Our iRDM can be applied to both linear regression and kernel regression, and it even significantly outperforms supervised ALR when the number of labeled samples is small.

cs.LG↗

arXiv2019

Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately designed small perturbations are added to the benign input samples to fool the deep learning model and degrade its performance. This paper considers transferability-based black-box attacks, where the attacker trains a substitute model to approximate the target model, and then generates adversarial examples from the substitute model to attack the target model. Learning a good substitute model is critical to the success of these attacks, but it requires a large number of queries to the target model. We propose a novel framework which uses query synthesis based active learning to improve the query efficiency in training the substitute model. Experiments on three convolutional neural network (CNN) classifiers and three EEG datasets demonstrated that our method can improve the attack success rate with the same number of queries, or, in other words, our method requires fewer queries to achieve a desired attack performance. To our knowledge, this is the first work that integrates active learning and adversarial attacks for EEG-based BCIs.

cs.LG↗

arXiv2018

An Adaptive Finite Element DtN Method for Maxwell's Equations in Biperiodic Structures

Consider the diffraction of an electromagnetic plane wave by a biperiodic structure where the wave propagation is governed by the three-dimensional Maxwell equations. Based on transparent boundary condition, the grating problem is formulated into a boundary value problem in a bounded domain. Using a duality argument technique, we derive an a posteriori error estimate for the finite element method with the truncation of the nonlocal Dirichlet-to-Neumann (DtN) boundary operator. The a posteriori error consists of both the finite element approximation error and the truncation error of boundary operator which decays exponentially with respect to the truncation parameter. An adaptive finite element algorithm is developed with error controlled by the a posterior error estimate, which determines the truncation parameter through the truncation error and adjusts the mesh through the finite element approximation error. Numerical experiments are presented to demonstrate the competitive behavior of the proposed adaptive method.

math.NA↗

arXiv2018

The materials data ecosystem: materials data science and its role in data-driven materials discovery

Since its launch in 2011, Materials Genome Initiative (MGI) has drawn the attention of researchers from across academia, government, and industry worldwide.As one of the three tools of MGI, the materials data, for the first time, emerged as an extremely significant approach in materials discovery. Data science has been applied in different disciplines as an interdisciplinary field to extract knowledge from the data. The concept of materials data science was utilized to demonstrate the data application in materials science. To explore its potential as an active research branch in the big data age, a three-tier system was put forward to define the infrastructure of data classification, curation and knowledge extraction of materials data.

cs.CY↗

arXiv2017

Twisted Acoustics

We use metasurfaces to enable acoustic orbital angular momentum (a-OAM) based multiplexing in real-time, postprocess-free and sensor-scanning-free fashions to improve the bandwidth of acoustic communication, with intrinsic compatibility and expandability to cooperate with other multiplexing technologies. The mechanism relied on encoding information onto twisted beams is numerically and experimentally demonstrated by realizing the real-time picture transfer, which differs from existing static data transfer by encoding data onto OAM states. Our study can boost the capacity of acoustic communication links and offer potential to revolutionize relevant fields.

physics.app-ph↗

arXiv2017

An adaptive finite element PML method for the acoustic-elastic interaction in three dimensions

Consider the scattering of a time-harmonic acoustic incident wave by a bounded, penetrable, and isotropic elastic solid, which is immersed in a homogeneous compressible air or fluid. The paper concerns the numerical solution for such an acoustic-elastic interaction problem in three dimensions. An exact transparent boundary condition (TBC) is developed to reduce the problem equivalently into a boundary value problem in a bounded domain. The perfectly matched layer (PML) technique is adopted to truncate the unbounded physical domain into a bounded computational domain. The well-posedness and exponential convergence of the solution are established for the truncated PML problem by using a PML equivalent TBC. An a posteriori error estimate based adaptive finite element method is developed to solve the scattering problem. Numerical experiments are included to demonstrate the competitive behavior of the proposed method.

math.NA↗

arXiv2017

Robust Phase Retrieval via ADMM with Outliers

An outlier-resistance phase retrieval algorithm based on alternating direction method of multipliers (ADMM) is devised in this letter. Instead of the widely used least squares criterion that is only optimal for Gaussian noise environment, we adopt the least absolute deviation criterion to enhance the robustness against outliers. Considering both intensity- and amplitude-based observation models, the framework of ADMM is developed to solve the resulting non-differentiable optimization problems. It is demonstrated that the core subproblem of ADMM is the proximity operator of the L1-norm, which can be computed efficiently by soft-thresholding in each iteration. Simulation results are provided to validate the accuracy and efficiency of the proposed approach compared to the existing schemes.

cs.IT↗