检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Minority Matters: A Diversity-Promoting Collab.rative Metric Learning Algorithm

arXiv

引用

arXiv 2022年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China Peng Cheng Laboratory China

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a diversity control regularization term to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML. © 2022, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

iSplit LBI: Individualized partial ranking with ties via split LBI

arXiv

引用

arXiv 2019年

作者： Xu, Qianqian Sun, Xinwei Yang, Zhiyong Cao, Xiaochun Huang, Qingming Yao, Yuan Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Microsoft Research Asia State Key Laboratory of Information Security Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management CAS Peng Cheng Laboratory Department of Mathematics Hong Kong University of Science and Technology Hong Kong

Due to the inherent uncertainty of data, the problem of predicting partial ranking from pairwise comparison data with ties has attracted increasing interest in recent years. However, in real-world scenarios, different individuals often hold distinct preferences. It might be misleading to merely look at a global partial ranking while ignoring personal diversity. In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective. Particularly, we formulate a unified framework which not only can be used for individualized partial ranking prediction, but also be helpful for abnormal user selection. This is realized by a variable splitting-based algorithm called iSplitLBI. Specifically, our algorithm generates a sequence of estimations with a regularization path, where both the hyperparameters and model parameters are updated. At each step of the path, the parameters can be decomposed into three orthogonal parts, namely, abnormal signals, personalized signals and random noise. The abnormal signals can serve the purpose of abnormal user selection, while the abnormal signals and personalized signals together are mainly responsible for individual partial ranking prediction. Extensive experiments on simulated and real-world datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives. The code is now availiable at https://***/qianqianxu010/ NeurIPS2019-iSplitLBI. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

2D Structured Turbo Compressed Sensing for Channel Estimation in OTFS systems

2D Structured Turbo Compressed Sensing for Channel Estimatio...

引用

International Conference on Communication systems

作者： Mingchen Zhang Fanggang Wang Xiaojun Yuan Lei Chen Center for Intelligent Networking and Commun National Key Lab. of Sci. and Tech. on Commun University of Electronic Sci. and Tech. of China Chengdu China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China School of Information Science and Technology ShanghaiTech University Shanghai China

ISBN: (纸本)9781538678657;9781538678640

High-speed mobility is a challenging scenario in wireless communications since it involves fast-varying channels, in which orthogonal frequency-division multiplexing (OFDM) could degrade significantly without accurate Doppler compensation. Recently, a modulation called orthogonal time frequency space (OTFS) was proposed for the specific scenario. The advantages are two-fold, i.e., the orthogonality in the time-frequency domain and the clustered sparsity of channel information in the delay-Doppler domain. In this paper, we propose a two-dimensional structured Turbo compressed sensing (CS) algorithm based on our previous work on Turbo CS for fast time-varying channel estimation. Markov random field is applied to model the clustered sparse prior of the channel in the two-dimensional delay-Doppler domain. In contrast to the conventional Turbo CS, a two-dimensional structured minimum mean-square error (MMSE) estimator is designed by message passing over a Markov random field. The convergence and the MSE performance of the proposed algorithm is evaluated, and the simulation results validate that the proposed algorithm outperforms the existing algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Power system state estimation via feasible point pursuit: Algorithms and Cramér-Rao bound

arXiv

引用

arXiv 2017年

作者： Wang, Gang Zamzam, Ahmed S. Giannakis, Georgios B. Sidiropoulos, Nicholas D. Digital Tech. Center ECE Dept. U. of Minnesota MplsMN55455 United States State Key Lab. of Intelligent Control and Decision of Complex Systems Beijing Inst. of Tech. Beijing100081 China

Accurately monitoring the system's operating point is central to the reliable and economic operation of an electric power grid. Power system state estimation (PSSE) aims to obtain complete voltage magnitude and angle information at each bus given a number of system variables at selected buses and lines. Power flow analysis is a special case of PSSE, and amounts to solving a set of noise-free power flow equations. Physical laws dictate quadratic relationships between availab.e quantities and unknown voltages, rendering general instances of power flow and PSSE nonconvex and NP-hard. Past approaches are largely based on gradient-type iterative procedures or semidefinite relaxation (SDR). Due to nonconvexity, the solution obtained via gradienttype schemes depends on initialization, while SDR methods do not perform as desired in challenging scenarios. This paper puts forth novel feasible point pursuit (FPP)-based solvers for power flow and PSSE, which iteratively seek feasible solutions for a nonconvex quadratically constrained quadratic programming (QCQP) reformulation of the weighted least-squares (WLS) problem. Relative to the prior art, the developed solvers offer superior performance at the cost of higher complexity. Furthermore, they converge to a stationary point of the WLS problem. As a baseline for comparing different estimators, the Cramér-Rao lower bound (CRLB) is derived for the fundamental PSSE problem in this paper. Judicious numerical tests on several IEEE benchmark systems showcase markedly improved performance of our FPPbased solvers for both power flow and PSSE tasks over popular WLS-based Gauss-Newton iterations and SDR approaches. Copyright © 2017, The Authors. All rights reserved.

关键词： state estimation

来源：评论

学校读者我要写书评

暂无评论

A Flight-Test Information Reasoning system Combining Textual CBR and RBR Approaches

A Flight-Test Information Reasoning System Combining Textual...

引用

7th International Conference on intelligent systems and Knowledge Engineering, ISKE 2012

作者： Yang, Bo Wang, Guodong Yao, Wentao State Key Laboratory of Intelligent Technology and Systems Tsinghua National Lab. for Information Science and Technology Dep. of Computer Science and Tech. Tsinghua University 100084 Beijing China Shenyang Aircraft Design and Research Institute 110031 Shenyang China

This paper presents a reasoning method based on the combination of Textual CBR and RBR to deal with the case described by the natural language with the intention of resolving the information retrieval in the flight-test procedure. Then experiments are made by using the reasoning system based on the method. The results show that not only could the method retrieve the cases from the system correctly, but also the Textual CBR procedure could complement the RBR procedure when the latter one cannot retrieve the case correctly. Thus the method could efficiently increase availab.lity of the reasoning system. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Case based reasoning

来源：评论

学校读者我要写书评

暂无评论

The 5th International Conference on Biomedical Engineering and Biotech.ology (ICBEB 2016) Abstracts

引用

BMC MEDICAL IMAGING 2016年第SUPPL 1期16卷 65-65页

作者： [Anonymous] Department of MRI Shandong Medical Imaging Research Institute Affiliated to Shandong University Jinan Shandong 250021 People’s Republic of China Department of Interventional Radiology Shandong Provincial Hospital Affiliated to Shandong University Jinan Shandong 250021 People’s Republic of China College of Information Science and Technology Engr. Research Center of Digitized Textile & Fashion Tech. for Ministry of Education Donghua University Shanghai 201620 China Intelligent multimedia information processing Lab College of Software Northeastern University Shenyang Liaoning Province 110004 China Institute of Biomedical and Health Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China School of Computer Science and Technology Nanjing Normal University Nanjing China Department of Electrical Engineering The City College of New York CUNY New York USA Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing Nanjing China School of Electronic Science and Engineering Nanjing University Nanjing Jiangsu 210046 China College of Engineering Nanyang Technological University Singapore 639798 Singapore School of Electronic Information Shanghai Dianji University Shanghai China School of Natural Sciences and Mathematics Shepherd University Shepherdstown WV 25443 USA Davis College of Agriculture Natural Resources and Design West Virginia University Morgantown WV 26505 USA State Key Laboratory of Millimeter Waves Southeast University Nanjing 210096 China Center of Medical Physics and Technology Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei China College of Agricultural and Life Sciences University of Florida Gainesville FL 32611 USA Courant Institute of Mathematical Sciences New York University New York NY 10012 USA Translational Imaging Division & MRI Unit Columbia University and New York State Psychiatric Institute New York NY 10032 USA Guangxi Key Laboratory of Manufacturing System & Adv

来源：评论

学校读者我要写书评

暂无评论

An encryption algorithm of JPEG2000 streams for supporting ciphertext-based transcoding

An encryption algorithm of JPEG2000 streams for supporting c...

引用

International Conference on Multisensor Fusion and Integration for intelligent systems (MFI)

作者： Yong Fu Xiaowei Yi Hengtai Ma Sci. and Tech. on Integrated Information System Lab. Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781479967339

With the increasing demands on image transcoding in heterogeneous networks, a ciphertext-based transcoding hierarchical encryption algorithm (CT-HEA) is proposed for JPEG2000 streams. By utilizing the rate-distortion optimized truncation, CT-HEA rearranges the compressed bitstream according to the quality layer and the resolution of the image, and then applies a hierarchical encryption scheme to the reorganized codestream via using cryptographic functions. This supports transparent transcoding operations directly on the compressed and encrypted bitstream. Simulation results demonstrate that the proposed CT-HEA has high transcoding flexibility with a low transcoding costs.

关键词： Encryption Streaming media Transcoding Image coding Transform coding

来源：评论

学校读者我要写书评

暂无评论

A capacity self-adaption information hiding algorithm based on RS code

A capacity self-adaption information hiding algorithm based ...

引用

International Conference on Multisensor Fusion and Integration for intelligent systems (MFI)

作者： Hengtai Ma Xiaowei Yi Xiaohui Wu Dingfeng Gu Hui Pan Changwen Zheng Sci. and Tech. on Integrated Information System Lab. Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Info. Engineering Chinese Academy of Sciences Beijing CN State Key Laboratory of Information Security Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781479967339

Information hiding based on error correcting code is one of the difficulties in information hiding research. Current information hiding algorithms cannot confirm the upper bound of covert channel capacity when channels are interfered. In this paper, a capacity self-adaption information hiding algorithm based on RS code is proposed to solve this problem. Firstly, Channel covert communication model is designed to describe the realization of information hiding algorithms based on the m-sequence. Secondly, the upper bound of embedding capacity of secret information based on block code and RS code is separately analyzed in theory. Thirdly, simulation verification is implemented under the supposed channel environment. Experimental results demonstrated that experimental values are consistent with the theoretical values, and in terms of the embedding rate, the performance of the RS code is better than the performance of recurrent code and block code.

关键词： Error correction codes Bit error rate Block codes Noise Decoding Upper bound

来源：评论

学校读者我要写书评

暂无评论

PowerTracer: Tracing requests in multi-tier services to diagnose energy inefficiency 12

PowerTracer: Tracing requests in multi-tier services to diag...

引用

9th ACM International Conference on Autonomic Computing, ICAC'12

作者： Lu, Gang Zhan, Jianfeng Wang, Haining Yuan, Lin Weng, Chuliang State Key Lab. of Computer Sys. and Arch. Institute of Computing Tech. Chinese Academy of Sciences China College of William and Mary Williamsburg VA 23187 United States Institute of Computing Tech. Chinese Academy of Sciences China Advanced System Lab Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781450315203

As energy has become one of the key operating costs in running a data center and power waste commonly exists, it is essential to reduce energy inefficiency inside data centers. In this paper, we develop an innovative framework called PowerTracer, for diagnosing energy-inefficiency. Inside the framework, we first present a resource tracing method based on request tracing in multi-tier services of black boxes. Then, we propose a generalized methodology of applying a request tracing approach for energy-inefficiency diagnosis in multitier service systems. With insights into service performance and resource consumption of individual requests, we develop a bottleneck diagnosis tool that pinpoints the root causes of energy inefficiency. We implement the prototype and conduct experiments to validate its effectiveness. Copyright 2012 ACM.

关键词： Operating costs

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：