Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is...Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is to learn the kernel from the data automatically. A general regularized risk functional （RRF） criterion for kernel matrix learning is proposed. Compared with the RRF criterion, general RRF criterion takes into account the geometric distributions of the embedding data points. It is proven that the distance between different geometric distdbutions can be estimated by their centroid distance in the reproducing kernel Hilbert space. Using this criterion for kernel matrix learning leads to a convex quadratically constrained quadratic programming （QCQP） problem. For several commonly used loss functions, their mathematical formulations are given. Experiment results on a collection of benchmark data sets demonstrate the effectiveness of the proposed method.展开更多
In this paper,we focus on inferring graph Laplacian matrix from the spatiotemporal signal which is defined as“time-vertex signal”.To realize this,we first represent the signals on a joint graph which is the Cartesia...In this paper,we focus on inferring graph Laplacian matrix from the spatiotemporal signal which is defined as“time-vertex signal”.To realize this,we first represent the signals on a joint graph which is the Cartesian product graph of the time-and vertex-graphs.By assuming the signals follow a Gaussian prior distribution on the joint graph,a meaningful representation that promotes the smoothness property of the joint graph signal is derived.Furthermore,by decoupling the joint graph,the graph learning framework is formulated as a joint optimization problem which includes signal denoising,timeand vertex-graphs learning together.Specifically,two algorithms are proposed to solve the optimization problem,where the discrete second-order difference operator with reversed sign(DSODO)in the time domain is used as the time-graph Laplacian operator to recover the signal and infer a vertex-graph in the first algorithm,and the time-graph,as well as the vertex-graph,is estimated by the other algorithm.Experiments on both synthetic and real-world datasets demonstrate that the proposed algorithms can effectively infer meaningful time-and vertex-graphs from noisy and incomplete data.展开更多
Sentiment analysis is a fine‐grained analysis task that aims to identify the sentiment polarity of a specified sentence.Existing methods in Chinese sentiment analysis tasks only consider sentiment features from a sin...Sentiment analysis is a fine‐grained analysis task that aims to identify the sentiment polarity of a specified sentence.Existing methods in Chinese sentiment analysis tasks only consider sentiment features from a single pole and scale and thus cannot fully exploit and utilise sentiment feature information,making their performance less than ideal.To resolve the problem,the authors propose a new method,GP‐FMLNet,that integrates both glyph and phonetic information and design a novel feature matrix learning process for phonetic features with which to model words that have the same pinyin information but different glyph information.Our method solves the problem of misspelling words influencing sentiment polarity prediction results.Specifically,the authors iteratively mine character,glyph,and pinyin features from the input comments sentences.Then,the authors use soft attention and matrix compound modules to model the phonetic features,which empowers their model to keep on zeroing in on the dynamic‐setting words in various positions and to dispense with the impacts of the deceptive‐setting ones.Ex-periments on six public datasets prove that the proposed model fully utilises the glyph and phonetic information and improves on the performance of existing Chinese senti-ment analysis algorithms.展开更多
Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recov...Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recovery accuracy and stronger theoretical guarantee. Specifically, the proposed method is based on a nonconvex optimization model, by solving the low-rank matrix which can be recovered from the noisy observation. To solve the model, an effective algorithm is derived by minimizing over the variables alternately. It is proved theoretically that this algorithm has stronger theoretical guarantee than the existing work. In natural image denoising experiments, the proposed method achieves lower recovery error than the two compared methods. The proposed low-rank matrix recovery method is also applied to solve two real-world problems, i.e., removing noise from verification code and removing watermark from images, in which the images recovered by the proposed method are less noisy than those of the two compared methods.展开更多
Redundant manipulators utilize their redundant solutions to achieve the position and orientation control of the end-effector in a given variety of complex tasks,which is an essential issue in the field of industrial r...Redundant manipulators utilize their redundant solutions to achieve the position and orientation control of the end-effector in a given variety of complex tasks,which is an essential issue in the field of industrial robots.Moreover,for manipulators with unknown models,traditional control methods generate large control errors during the execution of the task or even lead to the failure of the task.To address this problem,this paper proposes a Discrete Data-Driven Position and Orientation Control(D3POC)scheme.The scheme consists of a Discrete Jacobian Matrix Learning(DJML)algorithm,a Discrete Gradient Neural Dynamics(DGND)solver,and a Kalman filter.Then,theoretical analyses are provided to demonstrate the convergence of the D3POC scheme.Subsequently,simulations,comparisons,and experiments based on this scheme are carried out on redundant manipulators.The obtained results indicate the validity,superiority,and practicability of the proposed control scheme.展开更多
The rapid development of online services and information overload has inspired the fast development of recommender systems, among which collaborative filtering algorithms and model-based recommendation approaches are ...The rapid development of online services and information overload has inspired the fast development of recommender systems, among which collaborative filtering algorithms and model-based recommendation approaches are wildly exploited. For instance, matrix factorization （MF） demonstrated successful achievements and advantages in assisting internet users in finding interested information. These existing models focus on the prediction of the users＇ ratings on unknown items. The performance is usually evaluated by the metric root mean square error （RMSE）. However, achieving good performance in terms of RMSE does not always guarantee a good ranking performance. Therefore, in this paper, we advocate to treat the recommendation as a ranking problem. Normalized discounted cumulative gain （NDCG） is chosen as the optimization target when evaluating the ranking accuracy. Specifically, we present three ranking-oriented recommender algorithms, NSME AdaMF and AdaNSME NSMF builds a NDCG approximated loss function for Matrix Factorization. AdaMF is based on an algorithm by adaptively combining component MF recommenders with boosting method. To combine the advantages of both algorithms, we propose AdaNSME which is a hybird of NSMF and AdaME and show the superiority in both ranking accuracy and model generalization. In addition, we compare our proposed approaches with the state-of-the-art recommendation algorithms. The comparison studies confirm the advantage of our proposed approaches.展开更多
基金supported by the National Natural Science Fundation of China (60736021)the Joint Funds of NSFC-Guangdong Province(U0735003)
文摘Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is to learn the kernel from the data automatically. A general regularized risk functional （RRF） criterion for kernel matrix learning is proposed. Compared with the RRF criterion, general RRF criterion takes into account the geometric distributions of the embedding data points. It is proven that the distance between different geometric distdbutions can be estimated by their centroid distance in the reproducing kernel Hilbert space. Using this criterion for kernel matrix learning leads to a convex quadratically constrained quadratic programming （QCQP） problem. For several commonly used loss functions, their mathematical formulations are given. Experiment results on a collection of benchmark data sets demonstrate the effectiveness of the proposed method.
基金supported by the National Natural Science Foundation of China(Grant No.61966007)Key Laboratory of Cognitive Radio and Information Processing,Ministry of Education(No.CRKL180106,No.CRKL180201)+1 种基金Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing,Guilin University of Electronic Technology(No.GXKL06180107,No.GXKL06190117)Guangxi Colleges and Universities Key Laboratory of Satellite Navigation and Position Sensing.
文摘In this paper,we focus on inferring graph Laplacian matrix from the spatiotemporal signal which is defined as“time-vertex signal”.To realize this,we first represent the signals on a joint graph which is the Cartesian product graph of the time-and vertex-graphs.By assuming the signals follow a Gaussian prior distribution on the joint graph,a meaningful representation that promotes the smoothness property of the joint graph signal is derived.Furthermore,by decoupling the joint graph,the graph learning framework is formulated as a joint optimization problem which includes signal denoising,timeand vertex-graphs learning together.Specifically,two algorithms are proposed to solve the optimization problem,where the discrete second-order difference operator with reversed sign(DSODO)in the time domain is used as the time-graph Laplacian operator to recover the signal and infer a vertex-graph in the first algorithm,and the time-graph,as well as the vertex-graph,is estimated by the other algorithm.Experiments on both synthetic and real-world datasets demonstrate that the proposed algorithms can effectively infer meaningful time-and vertex-graphs from noisy and incomplete data.
基金Science and Technology Innovation 2030‐“New Generation Artificial Intelligence”major project,Grant/Award Number:2020AAA0108703。
文摘Sentiment analysis is a fine‐grained analysis task that aims to identify the sentiment polarity of a specified sentence.Existing methods in Chinese sentiment analysis tasks only consider sentiment features from a single pole and scale and thus cannot fully exploit and utilise sentiment feature information,making their performance less than ideal.To resolve the problem,the authors propose a new method,GP‐FMLNet,that integrates both glyph and phonetic information and design a novel feature matrix learning process for phonetic features with which to model words that have the same pinyin information but different glyph information.Our method solves the problem of misspelling words influencing sentiment polarity prediction results.Specifically,the authors iteratively mine character,glyph,and pinyin features from the input comments sentences.Then,the authors use soft attention and matrix compound modules to model the phonetic features,which empowers their model to keep on zeroing in on the dynamic‐setting words in various positions and to dispense with the impacts of the deceptive‐setting ones.Ex-periments on six public datasets prove that the proposed model fully utilises the glyph and phonetic information and improves on the performance of existing Chinese senti-ment analysis algorithms.
基金Projects(61173122,61262032) supported by the National Natural Science Foundation of ChinaProjects(11JJ3067,12JJ2038) supported by the Natural Science Foundation of Hunan Province,China
文摘Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recovery accuracy and stronger theoretical guarantee. Specifically, the proposed method is based on a nonconvex optimization model, by solving the low-rank matrix which can be recovered from the noisy observation. To solve the model, an effective algorithm is derived by minimizing over the variables alternately. It is proved theoretically that this algorithm has stronger theoretical guarantee than the existing work. In natural image denoising experiments, the proposed method achieves lower recovery error than the two compared methods. The proposed low-rank matrix recovery method is also applied to solve two real-world problems, i.e., removing noise from verification code and removing watermark from images, in which the images recovered by the proposed method are less noisy than those of the two compared methods.
基金supported by the Excellence in Science and Technology Innovation and Entrepreneurship for Young and Middle-aged Talents(Team)of Jilin Province(No.20240601030RC)the National Natural Science Foundation of China(Nos.62373065 and 61873304).
文摘Redundant manipulators utilize their redundant solutions to achieve the position and orientation control of the end-effector in a given variety of complex tasks,which is an essential issue in the field of industrial robots.Moreover,for manipulators with unknown models,traditional control methods generate large control errors during the execution of the task or even lead to the failure of the task.To address this problem,this paper proposes a Discrete Data-Driven Position and Orientation Control(D3POC)scheme.The scheme consists of a Discrete Jacobian Matrix Learning(DJML)algorithm,a Discrete Gradient Neural Dynamics(DGND)solver,and a Kalman filter.Then,theoretical analyses are provided to demonstrate the convergence of the D3POC scheme.Subsequently,simulations,comparisons,and experiments based on this scheme are carried out on redundant manipulators.The obtained results indicate the validity,superiority,and practicability of the proposed control scheme.
文摘The rapid development of online services and information overload has inspired the fast development of recommender systems, among which collaborative filtering algorithms and model-based recommendation approaches are wildly exploited. For instance, matrix factorization （MF） demonstrated successful achievements and advantages in assisting internet users in finding interested information. These existing models focus on the prediction of the users＇ ratings on unknown items. The performance is usually evaluated by the metric root mean square error （RMSE）. However, achieving good performance in terms of RMSE does not always guarantee a good ranking performance. Therefore, in this paper, we advocate to treat the recommendation as a ranking problem. Normalized discounted cumulative gain （NDCG） is chosen as the optimization target when evaluating the ranking accuracy. Specifically, we present three ranking-oriented recommender algorithms, NSME AdaMF and AdaNSME NSMF builds a NDCG approximated loss function for Matrix Factorization. AdaMF is based on an algorithm by adaptively combining component MF recommenders with boosting method. To combine the advantages of both algorithms, we propose AdaNSME which is a hybird of NSMF and AdaME and show the superiority in both ranking accuracy and model generalization. In addition, we compare our proposed approaches with the state-of-the-art recommendation algorithms. The comparison studies confirm the advantage of our proposed approaches.
