检索结果-内蒙古大学图书馆

Few-Shot Partial Multi-View Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 11824-11841页

作者： Zhou, Yuan Guo, Yanrong Hao, Shijie Hong, Richang Luo, Jiebo Ministry of Education Hefei University of Technology The Key Laboratory of Knowledge Engineering with Big Data Hefei230009 China Hefei University of Technology The School of Computer Science and Information Engineering Hefei230009 China University of Rochester The Department of Computer Science RochesterNY14627 United States

It is often the case that data are with multiple views in real-world applications. Fully exploring the information of each view is significant for making data more representative. However, due to various limitations and failures in data collection and pre-processing, it is inevitable for real data to suffer from view missing and data scarcity. The coexistence of these two issues makes it more challenging to achieve the pattern classification task. Currently, to our best knowledge, few appropriate methods can well-handle these two issues simultaneously. Aiming to draw more attention from the community to this challenge, we propose a new task in this paper, called few-shot partial multi-view learning, which focuses on overcoming the negative impact of the view-missing issue in the low-data regime. The challenges of this task are twofold: (i) it is difficult to overcome the impact of data scarcity under the interference of missing views;(ii) the limited number of data exacerbates information scarcity, thus making it harder to address the view-missing issue in turn. To address these challenges, we propose a new unified Gaussian dense-anchoring method. The unified dense anchors are learned for the limited partial multi-view data, thereby anchoring them into a unified dense representation space where the influence of data scarcity and view missing can be alleviated. We conduct extensive experiments to evaluate our method. The results on Cub-googlenet-doc2vec, Handwritten, Caltech102, Scene15, Animal, ORL, tieredImagenet, and Birds-200-2011 datasets validate its effectiveness. The codes will be released at https://***/zhouyuan888888/UGDA. © 1979-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Stochastic Variational Inference-Based Parallel and Online Supervised Topic Model for Large-Scale Text Processing

引用

Journal of Computer Science & Technology 2018年第5期33卷 1007-1022页

作者： Yang Li Wen-Zhuo Song Bo Yang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun 130012 China Aviation University of Air Force Changchun 130062 China

Topic modeling is a mainstream and effective technology to deal with text data, with wide applications in text analysis, natural language, personalized recommendation, computer vision, etc. Among all the known topic models, supervised Latent Dirichlet Allocation （sLDA） is acknowledged as a popular and competitive supervised topic model. How- ever, the gradual increase of the scale of datasets makes sLDA more and more inefficient and time-consuming, and limits its applications in a very narrow range. To solve it, a parallel online sLDA, named PO-sLDA （Parallel and Online sLDA）, is proposed in this study. It uses the stochastic variational inference as the learning method to make the training procedure more rapid and efficient, and a parallel computing mechanism implemented via the MapReduce framework is proposed to promote the capacity of cloud computing and big data processing. The online training capacity supported by PO-sLDA expands the application scope of this approach, making it instrumental for real-life applications with high real-time demand. The validation using two datasets with different sizes shows that the proposed approach has the comparative accuracy as the sLDA and can efficiently accelerate the training procedure. Moreover, its good convergence and online training capacity make it lucrative for the large-scale text data analyzing and processing.

关键词： topic modeling, large-scale text classification, stochastic variational inference, cloud computing online learning

来源：评论

学校读者我要写书评

暂无评论

Fast SimRank computation over disk-resident graphs

Fast SimRank computation over disk-resident graphs

引用

18th International Conference on database Systems for Advanced Applications, DASFAA 2013

作者： Zhang, Yinglong Li, Cuiping Chen, Hong Sheng, Likun Key Lab of Data Engineering and Knowledge Engineering of Ministry of Education And Department of Computer Science Renmin University of China China JiangXi Agricultural University China

ISBN: (纸本)9783642374494

There are many real-world applications based on similarity between objects, such as clustering, similarity query processing, information retrieval and recommendation systems. SimRank is a promising measure of similarity based on random surfers model. However, the computational complexity of SimRank is high and several optimization techniques have been proposed. In the paper optimization issue of Sim-Rank computation in disk-resident graphs is our primary focus. First we suggest a new approach to compute *** we propose optimization techniques that improve the time cost of the new approach from O (kN2 D2) to O (kNL), where k is the number of iteration, N is the number of nodes, L is the number of edges, and D is the average degree of nodes. Meanwhile, a threshold sieving method is presented to reduce storage and computational cost. On this basis, an external algorithm computing SimRank in disk-resident graphs is introduced. In the experiments, our algorithm outperforms its opponent whose computation complexity also is O (kNL). © Springer-Verlag 2013.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

A Spatial-Temporal Attention Model for Human Trajectory Prediction

引用

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 965-974页

作者： Xiaodong Zhao Yaran Chen Jin Guo Dongbin Zhao the School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083 the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China the Key Laboratory of Knowledge Automation for Industrial Processes Ministry of EducationBeijing 100083China

Human trajectory prediction is essential and promising in many related applications. This is challenging due to the uncertainty of human behaviors, which can be influenced not only by himself, but also by the surrounding environment. Recent works based on long-short term memory(LSTM) models have brought tremendous improvements on the task of trajectory prediction. However, most of them focus on the spatial influence of humans but ignore the temporal influence. In this paper, we propose a novel spatial-temporal attention(ST-Attention) model,which studies spatial and temporal affinities jointly. Specifically,we introduce an attention mechanism to extract temporal affinity,learning the importance for historical trajectory information at different time instants. To explore spatial affinity, a deep neural network is employed to measure different importance of the neighbors. Experimental results show that our method achieves competitive performance compared with state-of-the-art methods on publicly available datasets.

关键词： Attention mechanism long-short term memory(LSTM) spatial-temporal model trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

Color Image Super-Resolution and Enhancement with Inter-Channel Details at Trivial Cost

引用

Journal of Computer Science & Technology 2020年第4期35卷 889-899页

作者： Chuang-Ye Zhang Yan Niu Tie-Ru Wu Xi-Ming Li College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computer and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012China School of Mathematics Jilin UniversityChangchun 130012China

Image super-resolution is essential for a variety of applications such as medical imaging,surveillance imaging,and satellite imaging,among ***,the most popular color image super-resolution is performed in each color channel *** this paper,we show that the super-resolution quality can be further enhanced by exploiting the cross-channel *** by the High-Quality Linear Interpolation(HQLI)demosaicking algorithm by Malvar et al.,we design an image super-resolution scheme that integrates intra-channel interpolation with cross-channel details by isotropic linear *** its simplicity,our super-resolution method achieves the accuracy comparable with the existing fastest state-of-the-art super-resolution algorithm at 20 times faster *** is well applicable to applications that adopt traditional interpolations,for improved visual quality at trivial computation *** comparative study verifies the effectiveness and efficiency of the proposed super-resolution algorithm.

关键词： image super-resolution isotropic linear interpolation inter-channel detail enhancement low cost

来源：评论

学校读者我要写书评

暂无评论

Multicomponent Similarity Graphs for Cross-Network Node Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1411-1424页

作者： Zhang, Yuhong Shi, Congmei Li, Xinzheng Zhang, Zan Hu, Xuegang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei230009 China

Cross-network node classification aims to train a classifier for an unlabeled target network using a source network with rich labels. In applications, the degree of nodes mostly conforms to the long-tail distribution, i.e., most nodes in the network are tail nodes with sparse neighborhoods. The established methods focus on either the discrepancy cross network or the long tail in a single network. As for the cross-network node classification under long tail, the coexistence of sparsity of tail nodes and the discrepancy cross-network challenges existing methods for long tail or methods for the cross-network node classification. To this end, a multicomponent similarity graphs for cross-network node classification (MS-CNC) is proposed in this article. Specifically, in order to address the sparsity of the tail nodes, multiple component similarity graphs, including attribute and structure similarity graphs, are constructed for each network to enrich the neighborhoods of the tail nodes and alleviate the long-tail phenomenon. Then, multiple representations are learned from the multiple similarity graphs separately. Based on the multicomponent representations, a two-level adversarial model is designed to address the distribution difference across networks. One level is used to learn the invariant representations cross network in view of structure and attribute components separately, and the other level is used to learn the invariant representations in view of the fused structure and attribute graphs. Extensive experimental results show that the MS-CNC outperforms the state-of-the-art methods. Impact Statement-Node classification is an important task in graph mining. With the unavailability of labels, some researchers propose cross-network node classification, using one labeled network to assist the node classification of another unlabeled network. However, the long-tail of nodes leads to unsatisfactory performance and challenges the recent cross-network node classification m

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

knowledge-augmented Self-training of A Question Rewriter for Conversational knowledge Base Question Answering

Knowledge-augmented Self-training of A Question Rewriter for...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Ke, Xirui Zhang, Jing Lv, Xin Xu, Yiqi Cao, Shulin Li, Cuiping Chen, Hong Li, Juanzi School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China Department of Computer Science and Technology Tsinghua University Beijing China

The recent rise of conversational applications such as online customer service systems and intelligent personal assistants has promoted the development of conversational knowledge base question answering (ConvKBQA). Different from the traditional single-turn KBQA, ConvKBQA usually explores multi-turn questions around a topic, where ellipsis and coreference pose great challenges to the single-turn KBQA systems which require self-contained questions. In this paper, we propose a rewrite- and-reason framework to first produce a full-fledged rewritten question based on the conversation history and then reason the answer by existing single-turn KBQA models. To overcome the absence of the rewritten supervision signals, we introduce a knowledge-augmented self-training mechanism to transfer the question rewriter from another dataset to adapt to the current knowledge base. Our question rewriter is decoupled from the subsequent QA process, which makes it easy to be united with either retrieval-based or semantic parsing-based KBQA models. Experiment results demonstrate the effectiveness of our method and a new state-of-the-art result is achieved. The code and dataset are available online now. © 2022 Association for Computational Linguistics.

关键词： knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

DPListCF: A Differentially Private Approach for Listwise Collaborative Filtering

DPListCF: A Differentially Private Approach for Listwise Col...

引用

IEEE Symposium on Computers and Communications

作者： Yuncheng Wu Juru Zeng Hong Chen Yao Wu Wenjuan Liang Hui Peng Cuiping Li Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China

ISBN: (纸本)9781509006809

Recently, listwise ranking-oriented collaborative filtering (CF) algorithms have gained great success in recommender systems. However, the ranked preference list may compromise the privacy of individuals. A notable paradigm for offering strong privacy guarantee is differential privacy. In this paper, we propose DPListCF, a differentially private algorithm based on ListCF (a state-of-art listwise CF algorithm). The main idea of DPListCF is to make both of the similarity calculation phase and rank prediction phase of ListCF satisfy differential privacy, by using input perturbation method and output perturbation method in the two phases respectively. Extensive experiments using two real datasets evaluate the performance of DPListCF, and demonstrate that the proposed algorithm outperforms state-of-art approaches.

关键词： Open area test sites Privacy collaborative filtering Recommender systems Perturbation methods Arts CONTAINMENT FAILURE

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence in Remote Sensing Image Registration:A survey

引用

International Journal of Automation and computing 2021年第1期18卷 1-17页

作者： Yue Wu Jun-Wei Liu Chen-Zhuo Zhu Zhuang-Fei Bai Qi-Guang Miao Wen-Ping Ma Mao-Guo Gong Key Laboratory of Big Data and Intelligent Vision School of Computer Science and TechnologyXidian UniversityXi′an 710071China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial IntelligenceXidian UniversityXi′an 710071China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic EngineeringXidian UniversityXi′an 710071China

In recent years,computational intelligence has been widely used in many fields and achieved remarkable *** computing and deep learning are important branches of computational *** methods based on evolutionary computation and deep learning have achieved good performance in remote sensing image *** paper introduces the application of computational intelligence in remote sensing image registration from the two directions of evolutionary computing and deep *** the part of remote sensing image registration based on evolutionary calculation,the principles of evolutionary algorithms and swarm intelligence algorithms are elaborated and their application in remote sensing image registration is *** application of deep learning in remote sensing image registration is also *** the same time,the development status and future of remote sensing image registration are summarized and their prospects are examined.

关键词： Computational intelligence evolutionary computation neural network deep learning remote sensing image registration

来源：评论

学校读者我要写书评

暂无评论

An improved multi-objective evolutionary algorithm for computation offloading in the multi-cloudlet environment

引用

Frontiers of Computer Science 2021年第5期15卷 207-209页

作者： Li LIU Yuanyuan DU Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education University of Science and Technology BeijingBeijing 100083China

1 Introduction Mobile cloud computing(MCC)can break the limitations of mobile devices by migrating applications to the Cloud with richer computing and storage resources[1].Consequently,mobile users can obtain better service experience,improved processing power and reliability,expansion of storage capacity and so on[2].We focus on the computational offloading problem in the multi-cloudlet architecture(Fig.1).

关键词： loading service cloud

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：