检索结果-内蒙古大学图书馆

Research on patent recommendation method based on graph neural network

学校读者我要写书评

暂无评论

Research on patent recommendation method based on graph neur...

International Conference on Computer Supported Cooperative Work in Design

作者： Enchao Zhang Weidong Liu Shi Liu Yan Cao College of Computer Science Inner Mongolia University China Institute of Scientific and Technical Information of China China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problems such as low patent transformation efficiency and poor transaction quality. This paper proposes a method of recommending patents to consumers by experts to improve the environment of patent transactions. Through the analysis of the past transaction information of the patent, the effective path information of the target is extracted. The graph neural network is used to describe the characteristics and semantics among experts, patents and consumers, and then capture the potential weight among them through the common attention mechanism, and then dynamically integrate them to predict the occurrence of recommendation behavior. The paper makes reasonable use of social information and expert information in the transaction, which significantly improves the rationality and accuracy of expert recommendation.

关键词：

GESH-NET: GRAPH-ENHANCED SPHERICAL HARMONIC CONVOLUTIONAL NETWORKS FOR CORTICAL SURFACE REGISTRATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Ruoyu Wang, Lihui Tang, Kun Xu, Jingwen Wei, Hongjiang Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China

Cortical surface registration plays a crucial role in coordinating individual cortical functions and anatomical features, serving as a fundamental step in cortical surface analysis. Its aim is to align the anatomical or functional regions of different individuals, which is of great importance for neuroimaging studies across different populations. Currently, cortical surface registration techniques based on classical methods have been well developed. However, a key issue with classical registration methods is that for each pair of images to be registered, it is necessary to search for the optimal transformation in the deformation space according to a specific optimization algorithm until the similarity measure function converges, which cannot meet the requirements of real-time and high-precision in medical image registration. With the spectacular success of deep learning in the field of computer vision, researching cortical surface image registration techniques based on deep learning models has become a new direction. But so far, there are still only a few studies on cortical surface image registration based on deep learning. Moreover, although deep learning methods theoretically have stronger representation capabilities, surpassing the most advanced classical methods in registration accuracy and distortion control remains a challenge. Therefore, to address this challenge, this paper constructs a deep learning model to study the technology of cortical surface image registration. The specific work is as follows: (1) An unsupervised cortical surface registration network based on a multi-scale cascaded structure is designed, and a convolution method based on spherical harmonic transformation is introduced to register cortical surface data. This solves the problem of scale-inflexibility of spherical feature transformation and optimizes the multi-scale registration process. The results show that the proposed network outperforms the other deep learning-based registration m

关键词： Spheres

Hyperbolic Geometric Latent Diffusion Model for Graph Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

Pheromone Matrix Eigenvalue-based Convergence Assessment Indicator for Ant Colony Optimization

学校读者我要写书评

暂无评论

Pheromone Matrix Eigenvalue-based Convergence Assessment Ind...

Machine Intelligence Theory and Applications (MiTA), International Conference on

作者： Xu Li Lin Shi Jian-Yu Li Jing Xu Zhi-Hui Zhan School of Computer Science and Engineering South China University of Technology Guangzhou P. R. China Research Center of Intelligent Computing & Big Data Technology Guangdong University of Finance and Economics Guangzhou Guangdong P. R. China College of Artificial Intelligence Nankai University Tianjin P. R. China

ISBN: (数字)9798350385670

ISBN: (纸本)9798350385687

As a crucial member of the evolutionary computation (EC), ant colony optimization (ACO) converges to the optimal result through a continuous process of iterative optimization. However, determining the convergence status of an ant colony remains a challenging task without well-established methods. To this end, this paper proposes a global evaluation indicator—average absolute eigenvalue of pheromone matrix (AAEPM) by constructing a pheromone matrix and analyzing its eigenvalue variations. This indicator aims to assess the convergence status of the ant colony during the evolutionary process. Experimental results show that the AAEPM is correlated with the convergence status of ACO and is not significantly influenced by algorithm parameters and problem scale.

关键词： Measurement Ant colony optimization Heuristic algorithms Evolutionary computation Eigenvalues and eigenfunctions Robustness Iterative methods Optimization Machine intelligence Convergence

computing optimal partition problems via Lagrange multiplier approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cheng, Qing Guo, Jing Wang, Dong Department of Mathematics Tongji University Shanghai200092 China Key Laboratory of Intelligent Computing and Applications Tongji University Ministry of Education China School of Science and Engineering The Chinese University of Hong Kong Guangdong Shenzhen518172 China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data Guangdong518172 China

In this paper, we consider numerical approximations for the optimal partition problem using Lagrange multipliers. By rewriting it into constrained gradient flows, three and four steps numerical schemes based on the Lagrange multiplier approach [16, 17] are proposed to solve the constrained gradient system. Numerical schemes proposed for the constrained gradient flows satisfy the nice properties of orthogonality-preserving, norm-preserving, positivity-preserving and energy dissipating. The proposed schemes are very efficient in which only linear Poisson equations are solved at each time step. Extensive numerical results in 2D and 3D for optimal partition problem are presented to validate the effectiveness and accuracy of the proposed numerical schemes. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

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

Martingale Stopping Rule Application in Bayesian A/B Testing With Batch data

学校读者我要写书评

暂无评论

IEEE Access 2025年 13卷 100462-100478页

作者： Yali Wang Haiyan Yu Ching-Chi Yang Ronggui Zhang School of Management Huazhong University of Science and Technology Wuhan Hubei China School of Economics and Management Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China Chongqing Big Data Research Institute Peking University Chongqing China Department of Mathematical Sciences The University of Memphis Memphis TN USA Chongqing Key Laboratory of Emergency Medicine Chongqing Emergency Medical Center Chongqing University Central Hospital School of Medicine Chongqing University Chongqing China NHC Key Laboratory of Birth Defects and Reproductive Health Chongqing Population and Family Planning Science and Technology Research Institute Chongqing China

Continuous monitoring in A/B testing is widely used for selecting options, variants, or treatments in healthcare analytics. However, the appropriate stopping strategy for A/B testing in continuous monitoring remains unclear. This study proposes a Bayesian A/B testing method for continuous monitoring, incorporating a martingale stopping strategy. A uniform Beta distribution is used as the prior in the Bayesian A/B testing method. The posterior expected loss is employed as the criterion for choosing an option. When the posterior expected loss falls below a preset threshold, the result of the continuous monitoring is accepted for the A/B testing. With the proposed method, continuous monitoring of the null hypothesis (that the conversion rate of A is less than that of B) is managed using the posterior expected loss. The results obtained using the martingale stopping strategy enhance the interpretability of the A/B testing process. Finally, the effectiveness of the Bayesian A/B testing method is validated through numerical experiments on both simulated data and real-world applications.

关键词： Testing Bayes methods Monitoring Convergence Standards Decision making Posterior probability Stochastic processes Statistical analysis Maximum likelihood estimation

Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecasting

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiong, Qi Tang, Kai Ma, Minbo Zhang, Ji Xu, Jie Li, Tianrui School of Computing and Artificial Intelligence Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education National Engineering Laboratory of Integrated Transportation Big Data Application Technology Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China School of Computing The University of Leeds LeedsLS2 9JT United Kingdom

Long-term time series forecasting (LTSF) is a critical task across diverse domains. Despite significant advancements in LTSF research, we identify a performance bottleneck in existing LTSF methods caused by the inadequate modeling of Temporal Dependencies within the Target (TDT). To address this issue, we propose a novel and generic temporal modeling framework, Temporal Dependency Alignment (TDAlign), that equips existing LTSF methods with TDT learning capabilities. TDAlign introduces two key innovations: 1) a loss function that aligns the change values between adjacent time steps in the predictions with those in the target, ensuring consistency with variation patterns, and 2) an adaptive loss balancing strategy that seamlessly integrates the new loss function with existing LTSF methods without introducing additional learnable parameters. As a plug-and-play framework, TDAlign enhances existing methods with minimal computational overhead, featuring only linear time complexity and constant space complexity relative to the prediction length. Extensive experiments on six strong LTSF baselines across seven real-world datasets demonstrate the effectiveness and flexibility of TDAlign. On average, TDAlign reduces baseline prediction errors by 1.47% to 9.19% and change value errors by 4.57% to 15.78%, highlighting its substantial performance improvements. Copyright © 2024, The Authors. All rights reserved.

关键词： Time series analysis

Blockchain-Based Homomorphic Transaction Framework for Enhanced Consumer Security and Business Scalability

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Guo, Tao Shang, Fengjun Dai, Xiangguang Liu, Qilie Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing400065 China Chongqing Three Gorges University Key Lab. of Intelligent Info. Proc. and Contr. of Chongqing Munic. Institutions of Higher Education Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology School of Three Gorges Artificial Intelligence Chongqing400044 China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China

Energy trading in distributed microgrids represents an effective means of enhancing the utilization of renewable energy. However, the aggregation of large-scale consumption data may encounter business scalability issues and potential privacy exposure concerns, necessitating the development of novel secure and scalable frameworks for integrating consumption demands between prosumer and microgrid entities. we research focuses on providing a user-friendly transaction model for consumers and microgrid operators. Firstly, a privacy aggregation scheme for user resource requests is designed to ensure the security and decentralization of user data. In addition, the model employs a bidirectional heterogeneous resource allocation mechanism to support the optimal allocation of multiple resources, such as renewable energy, power assets, energy storage devices, and carbon credits, among different microgrids. Finally, a microgrid transaction prototype has been constructed on the Truffle development framework. In this context, smart contracts has been designed to ensure that the transactions are carried out automatically. Experimental results indicate that the scheme provides enhanced security for multi-resource trading in a cluster context relative to existing methodologies. The number of transactions increases linearly with the resource overhead, resulting in more efficient utilization of energy trading. Furthermore, the framework's scalability has been demonstrated through both temporal and spatial considerations. © 1975-2011 IEEE.

关键词： Decentralized finance