检索结果-内蒙古大学图书馆

A Flexible Two-Stage Constrained Multi-Objective Evolutionary Algorithm Based on Autonomic Regulation

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zou, Juan Luo, Jian Liu, Yuan Yang, Shengxiang Zheng, Jinhua Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Computer science College of Xiangtan University Hunan Province Xiangtan China Faculty of Informational Engineering University of Xiangtan Xiangtan411105 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

The core element in solving constrained multi-objective problems (CMOPs) with evolutionary algorithms is simultaneously balancing objective optimization and constraint satisfaction. The di ffi culty of maintaining this balance increases significantly for existing algorithms when dealing with complex CMOPs because various complex feasible regions often make CMOPs with very di ff erent characteristics. To address this issue, we propose a more flexible two-stage evolutionary algorithm based on autonomic regulation (ARCMO), which can e ff ectively control evolutionary trends to adapt to complex CMOPs. Specifically, the first stage performs a fast global search and passes the population information to the second stage. The second stage consists of two dynamically complementary sub-processes: named exploration subprocess and convergence subprocess. The ratio of these two sub-processes is dynamically adjusted according to the information from the first stage to adapt to CMOPs with di ff erent complexities. Experiments on several recently proposed benchmark suites and real-world application problems show that ARCMO is more adaptable than the contender algorithms when solving di ff erent complex CMOPs. © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

Label Distribution Learning with Correlation Information

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wu, Yilin Lin, Yaojin Guo, Wenzhong Ding, Weiping College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Zhangzhou363000 China School of Information Science and Technology Nantong University Nantong226019 China

Label distribution learning quantifies the label space for each instance and has widely applicability in different fields. However, most existing works primarily focus on label correlation, but they still have a limitation in capturing instance correlation. Meanwhile, traditional label distribution learning operates on individual labels sequentially, leading to limitation in applying common features. Therefore, in this paper, we propose a novel approach for label distribution learning with correlation information i.e. instance correlation and label correlation. Specifically, the instance correlation and label correlation are identified by an optimization function and Pearson correlation coefficient, respectively. Besides, we conduct $\ell_{2,1}-$norm regularization to exploit common features. Comprehensive experiments manifest the superiority of our proposed approach against other well-established label distribution learning algorithms. © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

Research and Exploration on Innovation and Entrepreneurship Practice Education System for Railway Transportation Specialists

学校读者我要写书评

暂无评论

Research and Exploration on Innovation and Entrepreneurship ...

作者： Jiu Yong Jianwu Dang Yangping Wang Jianguo Wei Yan Lu The National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University College of Intelligence and Computing Tianjin University The School of Electronic and Information Engineering Lanzhou Jiaotong University Key Laboratory of Four Electric BIM Engineering and Intelligent Application Railway Industry

With the background of concept of rail transit major engineering,guided by industry demand, and based on the cultivation of practical abilities for outstanding engineering and technology talents in rail transit characteristic majors,we are committed to creating a national strategic innovation and entrepreneurship practical education system for rail transit characteristic professionals, continuously improving the practical teaching mode. We will carry out the construction of a "matrix style" practical teaching system that integrates the four modernizations,the construction of a virtual simulation practical teaching platform that integrates expertise and innovation, and open sharing, as well as the reform and exploration of the entire chain of integrated practical education. The scheme focuses on improving students' ability to solve complex engineering problems and their ability to apply composite knowledge and innovate and start businesses, cultivating a large number of outstanding rail transit engineering talents with solid professional foundations, outstanding practical abilities, and innovative and entrepreneurial qualities.

关键词：

Extracting variable-depth logical document hierarchy from long documents: Method, evaluation, and application

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Rong-Yu Cao, Yi-Xuan Zhou, Gan-Bin Luo, Ping Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China WeChat Search Application Department Tencent Holdings Ltd. Beijing100080 China Peng Cheng Laboratory Shenzhen518066 China

In this paper, we study the problem of extracting variable-depth "logical document hierarchy" from long documents, namely organizing the recognized "physical document objects" into hierarchical structures. The discovery of logical document hierarchy is the vital step to support many downstream applications (e.g. passage-based retrieval and high-quality information extraction). However, long documents, containing hundreds or even thousands of pages and variable-depth hierarchy, challenge the existing methods. To address these challenges, we develop a framework, namely Hierarchy Extraction from Long Document (HELD), where we "sequentially" insert each physical object at the proper on of the current tree. Determining whether each possible position is proper or not can be formulated as a binary classification problem. To further improve its effectiveness and efficiency, we study the design variants in HELD, including traversal orders of the insertion positions, heading extraction explicitly or implicitly, tolerance to insertion errors in predecessor steps, and so on. As for evaluations, we find that previous studies ignore the error that the depth of a node is correct while its path to the root is wrong. Since such mistakes may worsen the downstream applications seriously, a new measure is developed for more careful evaluation. The empirical experiments based on thousands of long documents from Chinese, English financial market and English scientific publication show that the HELD model with the "root-to-leaf" traversal order and explicit heading extraction is the best choice to achieve the tradeoff between effectiveness and efficiency with the accuracy of 0.9726, 0.7291 and 0.9578 in Chinese financial, English financial and arXiv datasets, respectively. Finally, we show that logical document hierarchy can be employed to significantly improve the performance of the downstream passage retrieval task. In summary, we conduct a systematic study on this task in terms of meth

关键词： Finance

A New Method for Predefined-Time Synchronization Control of Memristive Cohen-Grossberg Neural Networks

学校读者我要写书评

暂无评论

A New Method for Predefined-Time Synchronization Control of ...

Memristive computing and applications (ICMCA), IEEE International Conference on

作者： Aidi Liu Wenyue Yu Lili Huang Jian Guo Tengfei Lei Hui Zhao School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Computer and Information Engineering Qilu Institute of Technology Collaborative Innovation Center of Memristive Computing Application School of Computer and Information Engineering Qilu Institute of Technology Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and Engineering University of Jinan Jinan China

This article mainly conducts a series of research on the synchronization control of Cohen-Grossberg neural networks. Firstly, a memristive Cohen-Grossberg neural network model with time-varying delay was constructed, and an equivalent system was obtained by combining inverse function theory, differential inclusion, and set-valued mapping. Secondly, a new predefined-time stability theorem was proposed, and sufficient conditions were obtained to ensure that the drive-response system achieves predefined-time synchronization by designing appropriate control strategy. The simulation results show that the stability time of the error system can be adjusted by the user, verifying the correctness and of the theory.

关键词：

SDGFormer: An Efficient Convolution Network Structurally Similar to Transformer

学校读者我要写书评

暂无评论

SDGFormer: An Efficient Convolution Network Structurally Sim...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chaohao Wen Xun Gong School of Computing and Artificial Intelligence SWJTU Chengdu China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China National Engineering Laboratory of Integrated Transportation Big Data Application Technology SWJTU Chengdu China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province SWJTU Chengdu China

Deep Neural Networks (DNN) have achieved extraordinary success in many visual recognition tasks. Visual Transformer (ViT), which is derived from Natural Language Processing (NLP), has achieved state-of-the-art (SOTA) results on many tasks due to its capability of capturing long-range dependencies in visual data. However, Existing ViT models are challenging to deploy on devices due to their massive computational consumption, huge memory overhead, and reliance on large datasets. In this work, we address these issues by replacing some computationally expensive and memory-intensive modules in ViT with standard Convolutional Neural Network (CNN) modules. Firstly, we propose an efficient Self-Attention module called SDG-Attention (SDGA) with linear space and time complexity, and an economical FeedForward Network (FFN) composed of group convolution and shuffle channel (SFFN). Then, we develop a lightweight CNN model with SDGA and SFFN, SDGFormer, which embraces several priors of ViT and is LayerNorm-Free. We evaluate SDGFormer on ImageNet-1K and Mini-ImageNet, and the SDGFormer-S achieves a comparable top-1 accuracy of 77.6% on ImageNet-1K with 9.1M parameters and 1.6 GFlops regimes. Moreover, our SDGFormer-T achieves SOTA performance on Mini-ImageNet with 83.3% accuracy, demonstrating good generalization on small datasets without extra data.

关键词：

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

Dynamic graphs (DG) describe dynamic interactions between entities in many practical scenarios. Most existing DG representation learning models combine graph convolutional network and sequence neural network, which model spatial-temporal dependencies through two different types of neural networks. However, this hybrid design cannot well capture the spatial-temporal continuity of a DG. In this paper, we propose a tensor graph convolutional network to learn DG representations in one convolution framework based on the tensor product with the following two-fold ideas: a) representing the information of DG by tensor form;b) adopting tensor product to design a tensor graph convolutional network modeling spatial-temporal feature simultaneously. Experiments on real-world DG datasets demonstrate that our model obtains state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Tensors

Fast Latent Factor Analysis via a Fuzzy PID-Incorporated Stochastic Gradient Descent Algorithm

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Jinli Yuan, Ye School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

A high-dimensional and incomplete (HDI) matrix can describe the complex interactions among numerous nodes in various big data-related applications. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm learns a latent factor relying on the stochastic gradient of current instance error only without considering past update information. To address this critical issue, this paper innovatively proposes a Fuzzy PID-incorporated SGD (FPS) algorithm with two-fold ideas: 1) rebuilding the instance learning error by considering the past update information in an efficient way following the principle of PID, and 2) implementing hyper-parameters and gain parameters adaptation following the fuzzy rules. With it, an FPS-incorporated LFA model is further achieved for fast processing an HDI matrix. Empirical studies on six HDI datasets demonstrate that the proposed FPS-incorporated LFA model significantly outperforms the state-of-the-art LFA models in terms of computational efficiency for predicting the missing data of an HDI matrix with competitive accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Matrix algebra

A Node-collaboration-informed Graph Convolutional Network for Precise Representation to Undirected Weighted Graphs

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Ying Yuan, Ye Luo, Xin The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

An undirected weighted graph (UWG) is frequently adopted to describe the interactions among a solo set of nodes from real applications, such as the user contact frequency from a social network services system. A graph convolutional network (GCN) is widely adopted to perform representation learning to a UWG for subsequent pattern analysis tasks such as clustering or missing data estimation. However, existing GCNs mostly neglects the latent collaborative information hidden in its connected node pairs. To address this issue, this study proposes to model the node collaborations via a symmetric latent factor analysis model, and then regards it as a node-collaboration module for supplementing the collaboration loss in a GCN. Based on this idea, a Node-collaboration-informed Graph Convolutional Network (NGCN) is proposed with three-fold ideas: a) Learning latent collaborative information from the interaction of node pairs via a node-collaboration module;b) Building the residual connection and weighted representation propagation to obtain high representation capacity;and c) Implementing the model optimization in an end-to-end fashion to achieve precise representation to the target UWG. Empirical studies on UWGs emerging from real applications demonstrate that owing to its efficient incorporation of node-collaborations, the proposed NGCN significantly outperforms state-of-the-art GCNs in addressing the task of missing weight estimation. Meanwhile, its good scalability ensures its compatibility with more advanced GCN extensions, which will be further investigated in our future studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution