arXiv subjects

Yu Zhao

Publications and source records attributed to Yu Zhao.

At least 271 records · Page 15Linked to original sources

arXiv2020

Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing

With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results. However, the gap between machine translation systems and human translators needs to be manually closed by post-editing. In this paper, we propose an end-to-end deep learning framework of the quality estimation and automatic post-editing of the machine translation output. Our goal is to provide error correction suggestions and to further relieve the burden of human translators through an interpretable model. To imitate the behavior of human translators, we design three efficient delegation modules -- quality estimation, generative post-editing, and atomic operation post-editing and construct a hierarchical model based on them. We examine this approach with the English--German dataset from WMT 2017 APE shared task and our experimental results can achieve the state-of-the-art performance. We also verify that the certified translators can significantly expedite their post-editing processing with our model in human evaluation.

cs.CL↗

arXiv2020

Fixed-Time Cooperative Tracking Control for Double-Integrator Multi-Agent Systems: A Time-Based Generator Approach

In this paper, both the fixed-time distributed consensus tracking and the fixed-time distributed average tracking problems for double-integrator-type multi-agent systems with bounded input disturbances are studied, respectively. Firstly, a new practical robust fixed-time sliding mode control method based on the time-based generator is proposed. Secondly, a fixed-time distributed consensus tracking observer for double-integrator-type multi-agent systems is designed to estimate the state disagreements between the leader and the followers under undirected and directed communication, respectively. Thirdly, a fixed-time distributed average tracking observer for double-integrator-type multi-agent systems is designed to measure the average value of reference signals under undirected communication. Note that both the observers for the distributed consensus tracking and the distributed average tracking are devised based on time-based generators and can be extended to that of high-order multi-agent systems trivially. Furthermore, by combing the fixed-time sliding mode control with the fixed-time observers, the fixed-time controllers are designed to solve the distributed consensus tracking and the distributed average tracking problems. Finally, a few numerical simulations are shown to verify the results.

cs.MA↗

arXiv2020

Single-scan, dual-functional interferometer for fast spatiotemporal characterization of few-cycle pulses

Accurate and fast characterization of spatiotemporal information of high-intensity, ultrashort pulses is crucial in the field of strong-field laser science and technology. While conventional self-referenced interferometers were widely used to retrieve the spatial profile of the relative spectral phase of pulses, additional measurements of temporal and spectral information at a particular position of the laser beam were, however, necessary to remove the indeterminacy, which increases the system complexity. Here we report an advanced, dual-functional interferometer that is able to reconstruct the complete spatiotemporal information of ultrashort pulses with a single scan of the interferometer arm. The set-up integrates an interferometric frequency-resolved optical gating (FROG) with a radial shearing Michelson interferometer. Trough scanning one arm of the interferometer, both cross-correlated FROG trace at the central part of the laser beam and delay-dependent interferograms of the entire laser profile are simultaneously obtained, allowing a fast 3-dimensional reconstruction of few-cycle laser pulses.

physics.optics↗

arXiv2020

Connecting Embeddings for Knowledge Graph Entity Typing

Knowledge graph (KG) entity typing aims at inferring possible missing entity type instances in KG, which is a very significant but still under-explored subtask of knowledge graph completion. In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge from KGs. Specifically, we present two distinct knowledge-driven effective mechanisms of entity type inference. Accordingly, we build two novel embedding models to realize the mechanisms. Afterward, a joint model with them is used to infer missing entity type instances, which favors inferences that agree with both entity type instances and triple knowledge in KGs. Experimental results on two real-world datasets (Freebase and YAGO) demonstrate the effectiveness of our proposed mechanisms and models for improving KG entity typing. The source code and data of this paper can be obtained from: https://github.com/ Adam1679/ConnectE

cs.CL↗

arXiv2020

A unified structure preserving scheme for a multi-species model with a gradient flow structure and nonlocal interactions via singular kernels

In this paper, we consider a nonlinear and nonlocal parabolic model for multi-species ionic fluids and introduce a semi-implicit finite volume scheme, which is second order accurate in space, first order in time and satisfies the following properties: positivity preserving, mass conservation and energy dissipation. Besides, our scheme involves a fast algorithm on the convolution terms with singular but integrable kernels, which otherwise impedes the accuracy and efficiency of the whole scheme. Error estimates on the fast convolution algorithm are shown next. Numerous numerical tests are provided to demonstrate the properties, such as unconditional stability, order of convergence, energy dissipation and the complexity of the fast convolution algorithm. Furthermore, extensive numerical experiments are carried out to explore the modeling effects in specific examples, such as, the steric repulsion, the concentration of ions at the boundary and the blowup phenomenon of the Keller-Segel equations.

math.NA↗

arXiv2020

Q-greedyUCB: a New Exploration Policy for Adaptive and Resource-efficient Scheduling

This paper proposes a learning algorithm to find a scheduling policy that achieves an optimal delay-power trade-off in communication systems. Reinforcement learning (RL) is used to minimize the expected latency for a given energy constraint where the environments such as traffic arrival rates or channel conditions can change over time. For this purpose, this problem is formulated as an infinite-horizon Markov Decision Process (MDP) with constraints. To handle the constrained optimization problem, we adopt the Lagrangian relaxation technique to solve it. Then, we propose a variant of Q-learning, Q-greedyUCB that combines Q-learning for \emph{average} reward algorithm and Upper Confidence Bound (UCB) policy to solve this decision-making problem. We prove that the Q-greedyUCB algorithm is convergent through mathematical analysis. Simulation results show that Q-greedyUCB finds an optimal scheduling strategy, and is more efficient than Q-learning with the $\varepsilon$-greedy and Average-payoff RL algorithm in terms of the cumulative reward (i.e., the weighted sum of delay and energy) and the convergence speed. We also show that our algorithm can reduce the regret by up to 12% compared to the Q-learning with the $\varepsilon$-greedy and Average-payoff RL algorithm.

eess.SY↗

arXiv2020

ADMM-IDNN: Iteratively Double-reweighted Nuclear Norm Algorithm for Group-prior based Nonconvex Compressed Sensing via ADMM

Group-prior based regularization method has led to great successes in various image processing tasks, which can usually be considered as a low-rank matrix minimization problem. As a widely used surrogate function of low-rank, the nuclear norm based convex surrogate usually lead to over-shrinking phenomena, since the nuclear norm shrinks the rank components (singular value) simultaneously. In this paper, we propose a novel Group-prior based nonconvex image compressive sensing (CS) reconstruction framework via a family of nonconvex nuclear norms functions which contain common concave and monotonically properties. To solve the resulting nonconvex nuclear norm minimization (NNM) problem, we develop a Group based iteratively double-reweighted nuclear norm algorithm (IDNN) via an alternating direction method of multipliers (ADMM) framework. Our proposed algorithm can convert the nonconvex nuclear norms optimization problem into a double-reweighted singular value thresholding (DSVT) problem. Extensive experiments demonstrate our proposed framework achieved favorable reconstruction performance compared with current state-of-the-art convex methods.

eess.IV↗

arXiv2020

Nonconvex Nonsmooth Low-Rank Minimization for Generalized Image Compressed Sensing via Group Sparse Representation

Group sparse representation (GSR) based method has led to great successes in various image recovery tasks, which can be converted into a low-rank matrix minimization problem. As a widely used surrogate function of low-rank, the nuclear norm based convex surrogate usually leads to over-shrinking problem, since the standard soft-thresholding operator shrinks all singular values equally. To improve traditional sparse representation based image compressive sensing (CS) performance, we propose a generalized CS framework based on GSR model, which leads to a nonconvex nonsmooth low-rank minimization problem. The popular L_2-norm and M-estimator are employed for standard image CS and robust CS problem to fit the data respectively. For the better approximation of the rank of group-matrix, a family of nuclear norms are employed to address the over-shrinking problem. Moreover, we also propose a flexible and effective iteratively-weighting strategy to control the weighting and contribution of each singular value. Then we develop an iteratively reweighted nuclear norm algorithm for our generalized framework via an alternating direction method of multipliers framework, namely, GSR-AIR. Experimental results demonstrate that our proposed CS framework can achieve favorable reconstruction performance compared with current state-of-the-art methods and the robust CS framework can suppress the outliers effectively.

eess.IV↗

arXiv2019

Graph-augmented Convolutional Networks on Drug-Drug Interactions Prediction

We propose an end-to-end model to predict drug-drug interactions (DDIs) by employing graph-augmented convolutional networks. And this is implemented by combining graph CNN with an attentive pooling network to extract structural relations between drug pairs and make DDI predictions. The experiment results suggest a desirable performance achieving ROC at 0.988, F1-score at 0.956, and AUPR at 0.986. Besides, the model can tell how the two DDI drugs interact structurally by varying colored atoms. And this may be helpful for drug design during drug discovery.

cs.LG↗

arXiv2019

SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement

Knowledge graph (KG) refinement mainly aims at KG completion and correction (i.e., error detection). However, most conventional KG embedding models only focus on KG completion with an unreasonable assumption that all facts in KG hold without noises, ignoring error detection which also should be significant and essential for KG refinement.In this paper, we propose a novel support-confidence-aware KG embedding framework (SCEF), which implements KG completion and correction simultaneously by learning knowledge representations with both triple support and triple confidence. Specifically, we build model energy function by incorporating conventional translation-based model with support and confidence. To make our triple support-confidence more sufficient and robust, we not only consider the internal structural information in KG, studying the approximate relation entailment as triple confidence constraints, but also the external textual evidence, proposing two kinds of triple supports with entity types and descriptions respectively.Through extensive experiments on real-world datasets, we demonstrate SCEF's effectiveness.

cs.AI↗

arXiv2019

SmartBullets: A Cloud-Assisted Bullet Screen Filter based on Deep Learning

Bullet-screen is a technique that enables the website users to send real-time comment `bullet' cross the screen. Compared with the traditional review of a video, bullet-screen provides new features of feeling expression to video watching and more iterations between video viewers. However, since all the comments from the viewers are shown on the screen publicly and simultaneously, some low-quality bullets will reduce the watching enjoyment of the users. Although the bullet-screen video websites have provided filter functions based on regular expression, bad bullets can still easily pass the filter through making a small modification. In this paper, we present SmartBullets, a user-centered bullet-screen filter based on deep learning techniques. A convolutional neural network is trained as the classifier to determine whether a bullet need to be removed according to its quality. Moreover, to increase the scalability of the filter, we employ a cloud-assisted framework by developing a backend cloud server and a front-end browser extension. The evaluation of 40 volunteers shows that SmartBullets can effectively remove the low-quality bullets and improve the overall watching experience of viewers.

cs.MM↗

arXiv2019

On the $K$-theoretic Hall algebra of a surface

In this paper, we define the $K$-theoretic Hall algebra for $0$-dimensional coherent sheaves on a smooth projective surface, prove that the algebra is associative and construct a homomorphism to a redefined shuffle algebra analogous to Negut.

math.AG↗

arXiv2018

Uniqueness to Inverse Acoustic and Electromagnetic Scattering From Locally Perturbed Rough Surfaces

In this paper, we consider inverse time-harmonic acoustic and electromagnetic scattering from locally perturbed rough surfaces in three dimensions. The scattering interface is supposed to be the graph of a Lipschitz continuous function with compact support. It is proved that an acoustically sound-soft or sound-hard surface can be uniquely determined by the far-field pattern of infinite number of incident plane waves with distinct directions. Moreover, a single point source or plane wave can be used to uniquely determine a scattering surface of polyhedral type. These uniqueness results apply to Maxwell equations with the perfectly conducting boundary condition. Our arguments rely on the mixed reciprocity relation in a half space and the reflection principle for Helmholtz and Maxwell equations.

math.AP↗

arXiv2018

Hierarchical multi-class segmentation of glioma images using networks with multi-level activation function

For many segmentation tasks, especially for the biomedical image, the topological prior is vital information which is useful to exploit. The containment/nesting is a typical inter-class geometric relationship. In the MICCAI Brain tumor segmentation challenge, with its three hierarchically nested classes 'whole tumor', 'tumor core', 'active tumor', the nested classes relationship is introduced into the 3D-residual-Unet architecture. The network comprises a context aggregation pathway and a localization pathway, which encodes increasingly abstract representation of the input as going deeper into the network, and then recombines these representations with shallower features to precisely localize the interest domain via a localization path. The nested-class-prior is combined by proposing the multi-class activation function and its corresponding loss function. The model is trained on the training dataset of Brats2018, and 20% of the dataset is regarded as the validation dataset to determine parameters. When the parameters are fixed, we retrain the model on the whole training dataset. The performance achieved on the validation leaderboard is 86%, 77% and 72% Dice scores for the whole tumor, enhancing tumor and tumor core classes without relying on ensembles or complicated post-processing steps. Based on the same start-of-the-art network architecture, the accuracy of nested-class (enhancing tumor) is reasonably improved from 69% to 72% compared with the traditional Softmax-based method which blind to topological prior.

cs.CV↗

arXiv2018

Efficient Trajectory Optimization for Robot Motion Planning

Motion planning for multi-jointed robots is challenging. Due to the inherent complexity of the problem, most existing works decompose motion planning as easier subproblems. However, because of the inconsistent performance metrics, only sub-optimal solution can be found by decomposition based approaches. This paper presents an optimal control based approach to address the path planning and trajectory planning subproblems simultaneously. Unlike similar works which either ignore robot dynamics or require long computation time, an efficient numerical method for trajectory optimization is presented in this paper for motion planning involving complicated robot dynamics. The efficiency and effectiveness of the proposed approach is shown by numerical results. Experimental results are used to show the feasibility of the presented planning algorithm.

cs.RO↗

arXiv2018

A novel active learning framework for classification: using weighted rank aggregation to achieve multiple query criteria

Multiple query criteria active learning (MQCAL) methods have a higher potential performance than conventional active learning methods in which only one criterion is deployed for sample selection. A central issue related to MQCAL methods concerns the development of an integration criteria strategy (ICS) that makes full use of all criteria. The conventional ICS adopted in relevant research all facilitate the desired effects, but several limitations still must be addressed. For instance, some of the strategies are not sufficiently scalable during the design process, and the number and type of criteria involved are dictated. Thus, it is challenging for the user to integrate other criteria into the original process unless modifications are made to the algorithm. Other strategies are too dependent on empirical parameters, which can only be acquired by experience or cross-validation and thus lack generality; additionally, these strategies are counter to the intention of active learning, as samples need to be labeled in the validation set before the active learning process can begin. To address these limitations, we propose a novel MQCAL method for classification tasks that employs a third strategy via weighted rank aggregation. The proposed method serves as a heuristic means to select high-value samples of high scalability and generality and is implemented through a three-step process: (1) the transformation of the sample selection to sample ranking and scoring, (2) the computation of the self-adaptive weights of each criterion, and (3) the weighted aggregation of each sample rank list. Ultimately, the sample at the top of the aggregated ranking list is the most comprehensively valuable and must be labeled. Several experiments generating 257 wins, 194 ties and 49 losses against other state-of-the-art MQCALs are conducted to verify that the proposed method can achieve superior results.

cs.LG↗

arXiv2018

Modeling 4D fMRI Data via Spatio-Temporal Convolutional Neural Networks (ST-CNN)

Simultaneous modeling of the spatio-temporal variation patterns of brain functional network from 4D fMRI data has been an important yet challenging problem for the field of cognitive neuroscience and medical image analysis. Inspired by the recent success in applying deep learning for functional brain decoding and encoding, in this work we propose a spatio-temporal convolutional neural network (ST-CNN)to jointly learn the spatial and temporal patterns of targeted network from the training data and perform automatic, pin-pointing functional network identification. The proposed ST-CNN is evaluated by the task of identifying the Default Mode Network (DMN) from fMRI data. Results show that while the framework is only trained on one fMRI dataset,it has the sufficient generalizability to identify the DMN from different populations of data as well as different cognitive tasks. Further investigation into the results show that the superior performance of ST-CNN is driven by the jointly-learning scheme, which capture the intrinsic relationship between the spatial and temporal characteristic of DMN and ensures the accurate identification.

cs.CV↗

arXiv2018

Geometric approach of degree of polarization in 3D polarimetry

The geometric approach presented in this paper concerns the degree of polarization (DoP) of a random 3D statistical electromagnetic field. We use that a 3*3 coherency matrix can always be decomposed into an incoherent superposition of three specific coherency matrices, to construct the first orthant of a spherical shell(0<x,y,z<1,sqrt(3)/3<r<1) . For a random 3D statistical electromagnetic field, the polarimetric result of the can be expressed in terms of a point located in the first orthant of this spherical shell physically. Furthermore, based on the intrinsic relationship between the defined parameters (DoP3D_P,DoP3D_PP) and DoP, a spatially quadric surface is obtained to quantify the values of DoP the for all physically reachable points contained in the first orthant of this spherical shell. Within this geometric approach, two examples are cited to demonstrate the applicability of 3D polarimetry to intuitively display the polarimetric result of a random 3D statistical electromagnetic field.

physics.optics↗