检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ju, Wei Yi, Siyu Wang, Yifan Xiao, Zhiping Mao, Zhengyang Li, Hourun Gu, Yiyang Qin, Yifang Yin, Nan Wang, Senzhang Liu, Xinwang Luo, Xiao Yu, Philip S. Zhang, Ming School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University-Anker Embodied AI Lab Peking University Beijing China School of Statistics and Data Science Nankai University Tianjin300071 China School of Information Technology & Management University of International Business and Economics Beijing100029 China Department of Computer Science University of California Los Angeles90095 United States Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates The School of Computer Science and Technology Central South University Changsha410017 China The College of Computer National University of Defense Technology Changsha410073 China The Department of Computer Science University of Illinois at Chicago Chicago United States

Graph-structured data exhibits universality and widespread applicability across diverse domains, such as social network analysis, biochemistry, financial fraud detection, and network security. Significant strides have been made in leveraging Graph Neural Networks (GNNs) to achieve remarkable success in these areas. However, in real-world scenarios, the training environment for models is often far from ideal, leading to substantial performance degradation of GNN models due to various unfavorable factors, including imbalance in data distribution, the presence of noise in erroneous data, privacy protection of sensitive information, and generalization capability for out-of-distribution (OOD) scenarios. To tackle these issues, substantial efforts have been devoted to improving the performance of GNN models in practical real-world scenarios, as well as enhancing their reliability and robustness. In this paper, we present a comprehensive survey that systematically reviews existing GNN models, focusing on solutions to the four mentioned real-world challenges including imbalance, noise, privacy, and OOD in practical scenarios that many existing reviews have not considered. Specifically, we first highlight the four key challenges faced by existing GNNs, paving the way for our exploration of real-world GNN models. Subsequently, we provide detailed discussions on these four aspects, dissecting how these solutions contribute to enhancing the reliability and robustness of GNN models. Last but not least, we outline promising directions and offer future perspectives in the field. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization

arXiv

引用

arXiv 2022年

作者： Qiu, Zexuan Su, Qinliang Yu, Jianxing Si, Shijing School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangzhou China School of Economics and Finance Shanghai International Studies University China

Efficient document retrieval heavily relies on the technique of semantic hashing, which learns a binary code for every document and employs Hamming distance to evaluate document distances. However, existing semantic hashing methods are mostly established on outdated TFIDF features, which obviously do not contain lots of important semantic information about documents. Furthermore, the Hamming distance can only be equal to one of several integer values, significantly limiting its representational ability for document distances. To address these issues, in this paper, we propose to leverage BERT embeddings to perform efficient retrieval based on the product quantization technique, which will assign for every document a real-valued codeword from the codebook, instead of a binary code as in semantic hashing. Specifically, we first transform the original BERT embeddings via a learnable mapping and feed the transformed embedding into a probabilistic product quantization module to output the assigned codeword. The refining and quantizing modules can be optimized in an end-to-end manner by minimizing the probabilistic contrastive loss. A mutual information maximization based method is further proposed to improve the representativeness of codewords, so that documents can be quantized more accurately. Extensive experiments conducted on three benchmarks demonstrate that our proposed method significantly outperforms current state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Semiparametric quantile-difference estimation for length-biased and right-censored data

引用

science China Mathematics 2019年第9期62卷 1823-1838页

作者： Yutao Liu Shucong Zhang Yong Zhou School of Statistics and Mathematics Central University of Finance and EconomicsBeijing100081China School of Statistics and Management Shanghai University of Finance and EconomicsShanghai200433China Key Laboratory of Advanced Theory and Application in Statistics and Data Science(MOE) Institute of Statistics and Interdisciplinary Sciences and School of StatisticsEast China Normal UniversityShanghai200241China

Prevalent cohort studies frequently involve length-biased and right-censored data, a fact that has drawn considerable attention in survival analysis. In this article, we consider survival data arising from lengthbiased sampling, and propose a new semiparametric-model-based approach to estimate quantile differences of failure time. We establish the asymptotic properties of our new estimators theoretically under mild technical conditions, and propose a resampling method for estimating their asymptotic variance. We then conduct simulations to evaluate the empirical performance and efficiency of the proposed estimators, and demonstrate their application by a real data analysis.

关键词： quantile differences length-biased sampling right-censored proportional hazards model

来源：评论

学校读者我要写书评

暂无评论

The abstract of doctoral dissertation‘nonlinear wavelet density estimation and hazard rate estimation with data missing at random’

引用

Statistical Theory and Related Fields 2020年第1期4卷 117-119页

作者： Yuye Zou Guoliang Fan Riquan Zhang School of Economics and Management Shanghai Maritime UniversityShanghaiPeople’s Republic of China Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE School of StatisticsEast China Normal UniversityShanghaiPeople’s Republic of China

In this thesis,we establish non-linear wavelet density estimators and studying the asymptotic properties of the estimators with data missing at random when covariates are *** outstanding advantage of non-linear wavelet method is estimating the unsoothed functions,however,the classical kernel estimation cannot do this *** the same time,we study the larger sample properties of the ISE for hazard rate estimator.

关键词： Asymptotic normality integral square error mean integral square error missing at random non-linear wavelet

来源：评论

学校读者我要写书评

暂无评论

A Predictive Analytics Approach Based on Grey-Markov for Digital Economy

A Predictive Analytics Approach Based on Grey-Markov for Dig...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Guang Hu Yue Tang School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Statistics and Information Shanghai University of International Business and Economics Shanghai China

ISBN: (纸本)9781665458429

This paper presents a predictive analytics approach based on Grey-Markov for digital economy. It selects the cumulative value data of consumer goods retail sales in China from February to December 2020. Firstly, the GM(1, 1) model is established to forecast retail sales of consumer goods for each month of 2020. Markov model is used to divide three transition states according to the prediction error. Then the cumulative values of February and March 2021 are predicted by GM(1, 1), and the prediction results are corrected by Markov chain model. Through comparing the prediction results of GM(1, 1) model and GM(1, 1)-Markov model, it is found that the prediction accuracy of GM(1, 1)-Markov model is higher, which indicates that the GM(1, 1)-Markov model has certain practical significance for the short-term prediction of retail sales of consumer goods.

关键词： Analytical models Scientific computing Computational modeling Predictive models Markov processes data models Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Testing Independence and Conditional Independence in High Dimensions via Coordinatewise Gaussianization

arXiv

引用

arXiv 2025年

作者： Chang, Jinyuan Du, Yue He, Jing Yao, Qiwei Joint Laboratory of Data Science and Business Intelligence Southwestern University of Finance and Economics Chengdu China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Institute of Statistical Interdisciplinary Research Southwestern University of Finance and Economics Chengdu China Department of Statistics The London School of Economics and Political Science London United Kingdom

We propose new statistical tests, in high-dimensional settings, for testing the independence of two random vectors and their conditional independence given a third random vector. The key idea is simple, i.e., we first transform each component variable to standard normal via its marginal empirical distribution, and we then test for independence and conditional independence of the transformed random vectors using appropriate L∞-type test statistics. While we are testing some necessary conditions of the independence or the conditional independence, the new tests outperform the 13 frequently used testing methods in a large scale simulation comparison. The advantage of the new tests can be summarized as follows: (i) they do not require any moment conditions, (ii) they allow arbitrary dependence structures of the components among the random vectors, and (iii) they allow the dimensions of random vectors diverge at the exponential rates of the sample size. The critical values of the proposed tests are determined by a computationally efficient multiplier bootstrap procedure. Theoretical analysis shows that the sizes of the proposed tests can be well controlled by the nominal significance level, and the proposed tests are also consistent under certain local alternatives. The finite sample performance of the new tests is illustrated via extensive simulation studies and a real data application. Copyright © 2025, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

A Decision Support Method for Interdisciplinary Major in Colleges and Universities Based on Natural Language Processing and data Mining

A Decision Support Method for Interdisciplinary Major in Col...

引用

Big data, Artificial Intelligence and Risk Management (ICBAR), International Conference on

作者： Lida Zou School of Computer Science and Technology Shandong University of Finance and Economics Jinan China Key Laboratory of Machine Learning and Financial Data Mining in Universities of Shandong Jinan China

ISBN: (纸本)9781665495660

With the development of science and technology, many disciplines reveal the general trends of crossing and blending, and new interdisciplinary subjects emerge. For decision makers in colleges and universities, it is crucial and difficult to choose and construct a proper interdisciplinary major. In the paper we simulate the phenomenon of current conduction to improve natural language processing and data mining. An assistant decision-making method of setting up interdisciplinary majors for colleges and universities is designed, which could not only intelligently and automatically recommend the most suitable interdisciplinary majors, but also simplify and correct the work of decision-makers. Our experimental analysis demonstrates that similarity ratio of interdisciplinary majors recommended by the proposed assistant decision-making method runs at more than 70 percent compared with manual recommendation of specialists.

关键词： Technological innovation Education Decision making Manuals Big data Market research Natural language processing

来源：评论

学校读者我要写书评

暂无评论

LNAD: Towards Lightweight Network Anomaly Detection in Software-Defined Networking 22

LNAD: Towards Lightweight Network Anomaly Detection in Softw...

引用

22nd IEEE International Conference on High Performance Computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on data science and Systems, HPCC-SmartCity-DSS 2020

作者： Cui, Yunhe Qian, Qing Xing, Huanlai Li, Saifei Guizhou University State Key Laboratory of Public Big Data School of Computer Science and Technology Guiyang China Guizhou University of Finance and Economics School of Information Guiyang China Southwest Jiaotong University School of Information Science and Technology Chengdu China

ISBN: (纸本)9781728176499

As an emerging architecture, Software-Defined Networking (SDN) is suffering from a lot of security issues. Network anomaly detection technology plays a crucial role in addressing SDN security issues. In SDN, the network status can be denoted by the packets or flow entries. Hence, the existing network anomaly detection methods are commonly designed based on inspecting packets or flow entries. Subsequently, these anomaly detection methods have to collect packets or flow entries from the underlying switches. More seriously, some anomaly detection methods even need to add extra modules to the switches. Unlike these existing network anomaly detection methods, this work proposes a lightweight network anomaly detection method. The main design principle of the proposed method is mining the inherent OpenFlow messages in SDN to represent the network status and further detect the network anomaly. The proposed method does not need to collect any additional messages from the underlying switches or add any additional modules to the underlying switches. The evaluation results demonstrate that the proposed network anomaly detection method can afford high detection accuracy and reduce the overhead of SDN controller. © 2020 IEEE.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Modelling Matrix Time Series via a Tensor CP-Decomposition

arXiv

引用

arXiv 2021年

作者： Chang, Jinyuan He, Jing Yang, Lin Yao, Qiwei Joint Laboratory of Data Science and Business Intelligence Southwestern University of Finance and Economics Sichuan Chengdu611130 China Department of Statistics The London School of Economics and Political Science LondonWC2A 2AE United Kingdom

We consider to model matrix time series based on a tensor CP-decomposition. Instead of using an iterative algorithm which is the standard practice for estimating CP-decompositions, we propose a new and one-pass estimation procedure based on a generalized eigenanalysis constructed from the serial dependence structure of the underlying process. To overcome the intricacy of solving a rank-reduced generalized eigenequation, we propose a further refined approach which projects it into a lower-dimensional full-ranked eigenequation. This refined method improves significantly the finite-sample performance of the estimation. The asymptotic theory has been established under a general setting without the stationarity. It shows, for example, that all the component coefficient vectors in the CP-decomposition are estimated consistently with certain convergence rates. The proposed model and the estimation method are also illustrated with both simulated and real data;showing effective dimension-reduction in modelling and forecasting matrix time series. Copyright © 2021, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Producing Fully-Charmed Tetraquarks via Charm Quark Fragmentation in Colliders

arXiv

引用

arXiv 2024年

作者： Bai, Xiao-Wei Feng, Feng Gan, Chang-Man Huang, Yingsheng Sang, Wen-Long Zhang, Hong-Fei School of Physical Science and Technology Southwest University Chongqing400700 China Institute of High Energy Physics and Theoretical Physics Center for Science Facilities Chinese Academy of Sciences Beijing100049 China China University of Mining and Technology Beijing100083 China High Energy Physics Division Argonne National Laboratory ArgonneIL60439 United States Department of Physics & Astronomy Northwestern University EvanstonIL60208 United States College of Big Data Statistics Guizhou University of Finance and Economics Guiyang550025 China

Within the framework of nonrelativistic QCD (NRQCD), we calculate the fragmentation function for a charm quark into an S-wave fully-charmed tetraquark, denoted as T4c. The charm-to-T4c fragmentation function is expressed as a sum of products of the perturbatively calculable short-distance coefficients and the nonperturbative long-distance matrix elements (LDMEs). The short-distance coefficients are ascertained through the perturbative matching procedure at lowest order in αs expansion. The LDMEs are approximated using the T4c four-body wave functions at the origin, which have been evaluated by various phenomenological potential models in literature. Incorporating the celebrated QCD factorization and the charm-to-T4c fragmentation function, we predict the T4c production rate at high transverse momentum pT regime in colliders. Both the differential distribution over pT and the integrated cross sections are predicted at the LHC. The cross sections for T4c states production can reach several femtobarns to several hundreds femtobarns, suggesting a substantial potential for T4c event production at the LHC. Additionally, we estimate for the photoproduction of T4c in electron-proton (ep) collisions. It is observed that the cross sections for these processes are moderate at the HERA and EIC, and relatively small at the EicC. Given the luminosities of these colliders, the prospect of detecting these fully-charmed tetraquarks at ep colliders is somewhat challenging. Copyright © 2024, The Authors. All rights reserved.

关键词： Wave functions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：