检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhang, Qian Wu, Yonghong Wang, Peiguang Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding071002 China Department of Mathematics and Statistics Curtin University PerthWA6845 Australia

In this paper, we consider a mathematical model motivated by the studies of coral broadcastspawning\begin{align}\left\{\begin{aligned}\no\partial_{t} n+u\cdot\nabla n-\Delta n & =-\chi \nabla \cdot(n \nabla c)+n-\epsilon n^{q} \\\no\partial_{t} c+u\cdot\nabla c-\Delta c & =-c+n\end{aligned}\right. \quad \text { in } \mathbb{R}^{d} \times \mathbb{R}^{+},\end{align}where $d\geq1$, $\epsilon>0$, and $q\geq2$. We establish global-in-time well-posedness and boundedness of the solution to the Cauchy problem of this system by developing local-in-space estimates. The crux point of our proof depends intensely on localization in the space of solutions induced by ``local effect" of the $L^\infty(\R^d)$-norm. © 2024, The Authors. All rights reserved.

关键词： Biochemistry

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Network Embedding for Attribute Networks with Outliers Using High-Order Proximity

SSRN

引用

SSRN 2024年

作者： Wu, Zelong Wang, Yidan Hu, Kaixia Lin, Guoliang Xu, Xinwei Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Hebei Baoding071002 China College of Cyber Security Jinan University Guangdong Guangzhou510632 China

Real-world networks contain rich semantic information, making attribute network embedding a vital tool for their analysis and exploitation. Nevertheless, this embedding process encounters significant challenges, primarily integrating heterogeneous topological and semantic information and effectively managing outliers. To address these problems, we propose a model called Self-supervised Attribute Network Embedding with Outliers (SANEO). Firstly, an innovative heterogeneous topological and semantic information integration method is designed, which contains arbitrary high-order proximity and theoretically includes summation and multiplication forms. Secondly, SANEO adaptively reduces the impact of outliers during the embedding process. Moreover, by incorporating high-order proximity, SANEO increases the scores of outliers, resulting in better robustness. Finally, through a deep architecture with dual autoencoders, SANEO achieves joint embedding of network structure and node attributes while end-to-end reconstruction of structure and attributes extracts potential embedding information. Extensive experiments associated with statistical tests and sensitivity analysis demonstrate that SANEO outperforms state-of-the-art algorithms across various downstream tasks. Code available at https://***/wuzelong/SANEO. © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Membership-Based Resampling and Cleaning Algorithm for Multi-Class Imbalanced Overlapping Data

SSRN

引用

SSRN 2022年

作者： Ma, Tingting Lu, Shuxia Jiang, Chen Hebei Province Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding071002 China

Real-world datasets frequently have an imbalanced class distribution, which significantly degrades classification performance. However, some studies have suggested that the adverse effects of class imbalance occur only when datasets have other intrinsic characteristics (such as class overlap, noise, and data scarcity). Noise and class overlap have the greatest effect. To deal with other intrinsic characteristics that affect classification performance in a multi-class environment, such as class overlap, noise, and data scarcity, we propose a method that can directly handle multi-class overlapping data, called the membership-based multi-class resampling and cleaning (MC-MBRC) algorithm. The proposed method divides samples into safe, overlapping, and noisy areas based on their membership degrees, and then according to the influence of the samples in each area on classification performance, it performs various operations such as noise removal, interpolation oversampling, and energy-based cleaning of the overlapping region. An extensive comparison using various datasets shows that, compared with state-of-the-art methods, the proposed method makes significant statistical improvements in different classification performance metrics and is robust to data containing class overlap and label noise. Furthermore, for datasets that do not have complex intrinsic features, MC-MBRC will not significantly degrade classification performance. © 2022, The Authors. All rights reserved.

关键词： Cleaning

来源：评论

学校读者我要写书评

暂无评论

Update of approximations in ordered information systems under variations of attribute and object set

引用

Advances in computational Intelligence 2022年第1期2卷 1-13页

作者： Li, Yan Wu, Xiaoxue Hua, Qiang Key Laboratory of Machine Learning and Computational Intelligence of Hebei Province College of Mathematics and Information Science Hebei University Baoding China School of Applied Mathematics Beijing Normal University Zhuhai China

Many collected data from real world applications often evolve when new attributes or objects are inserted or old ones are removed. The set approximations of ordered information systems (OIS) need to be updated from time to time for further data reduction, analysis, or decision-making. Incremental approaches are feasible and efficient techniques for updating approaches when any variation occurs. In this paper, considering OIS for multi-criteria classification problems, we discuss the principles of incrementally updating approximations in dominance relation based method in four different types of dynamic environments which combine the changes of both attribute set and object set. In each dynamic environment, the corresponding updating principles and algorithm are given with detail proofs. The experimental results and analysis on UCI data sets show that the proposed incremental approach outperforms the non-incremental method and the integration of current incremental algorithms in the implementation efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on the Construction Method of Requirement Knowledge Atlas Based on Graph Neural Network 4

Study on the Construction Method of Requirement Knowledge At...

引用

4th IEEE International Conference on Information Systems and Computer Aided Education, ICISCAE 2021

作者： Wang, Fei Wang, Shuo Tang, Qing Du, Yongjie Renmin University of China Beijing China Hebei University Key Laboratory of Machine Learning and Computational Intelligence Baoding071002 China Sense Time Beijing China Agricultural Bank of China Beijing China

ISBN: (纸本)9781665441247

As a structured semantic knowledge system, knowledge graph mainly uses symbols to present physical concepts in real life, which involves three aspects: Triples, entities and the network structure connected with related number structures. Although there is a wide range of research on knowledge graph at present, most of the research on knowledge graph in China is of general type. Therefore, on the basis of clarifying the construction method of required knowledge graph, this paper, aiming at the overall formal representation and construction framework of knowledge graph, makes clear the specific representation mode of pattern layer and data layer from the logical perspective, and then verifies and analyzes the proposed method. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Rotation transformation-based selective ensemble of one-class extreme learning machines

引用

Advances in computational Intelligence 2021年第1期2卷 1-10页

作者： Xing, Hong-Jie Bai, Yu-Wen Hebei Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding China

Extreme learning machine (ELM) possesses merits of rapid learning speed and good generalization ability. However, due to the random initialization of connection weights, the network outputs of ELM are usually unstable. Similar to ELM, one-class ELM (OCELM) also has the disadvantage of output instability. To enhance the stability and generalization performance of OCELM, a selective ensemble of OCELMs based on rotation transformation is proposed. First, principal component analysis (PCA)-based rotation transformation is utilized to construct different transformed training sets. Furthermore, several component OCELMs are trained independently on these training sets. Second, a dissimilarity measure based on angle cosine is used to evaluate the dissimilarity between each pair of OCELMs. The diversity of each component OCELM in the obtained ensemble can be further achieved. Thereafter, the component OCELMs with lower value of diversity are removed from the original ensemble. Finally, the voting strategy is utilized to determine that testing samples belong to the target class or the non-target class. Experimental results on 15 UCI benchmark data sets and one handwritten digit data set show that the proposed method is superior to its related approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi- View Teacher with Curriculum Data Fusion for Robust Unsupervised Domain Adaptation

Multi- View Teacher with Curriculum Data Fusion for Robust U...

引用

International Conference on Data Engineering

作者： Yuhao Tang Junyu Luo Ling Yang Xiao Luo Wentao Zhang Bin Cui School of CS & Key Laboratory of High Confidence Software Technologies (MOE) Peking University School of CS Peking University University of California Los Angeles Center for Machine Learning Research Peking University Institute of Computational Social Science Peking University (Qingdao) China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Graph Neural Networks (GNNs) have emerged as an effective tool for graph classification, yet their reliance on extensive labeled data poses a significant challenge, especially when such labels are scarce. To address this challenge, this paper presents a novel framework, denoted as Multi-View Teacher with Curriculum Data Fusion (MTDF). MTDF achieves robust unsupervised domain adaptation in both the model and data perspectives. On the one hand, MTDF utilizes a multi-teacher framework with diverse update strategies for robust adaptation. Moreover, it employs a complementary perspective consistency model from local implicit representation and global explicit graph structure. On the other hand, MTDF generates source-mimicry data at the target domain to serve as a bridge to overcome the challenge of domain shift. MTDF achieves stable unsupervised domain adaptation through bi-directional processes from the perspective of both the model and the data. We have conducted comprehensive experimental evaluations across multiple real-world datasets with a range of baseline methods to demonstrate the superior performance of our proposed method.

关键词： learning systems Adaptation models Data integration Bidirectional control Data engineering Data models Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Maximizing bi-mutual information of features for self-supervised deep clustering

引用

Advances in computational Intelligence 2021年第1期2卷 1-11页

作者： Zhao, Jiacheng Chen, Junfen Meng, Xiangjie Zhai, Junhai Key Laboratory of Machine Learning and Computational Intelligence of Hebei Province College of Mathematics and Information Science Hebei University Baoding China

Self-supervised learning based on mutual information makes good use of classification models and label information produced by clustering tasks to train networks parameters, and then updates the downstream clustering assignment with respect to maximizing mutual information between label information. This kind of methods have attracted more and more attention and obtained better progress, but there is still a larger improvement space compared with the methods of supervised learning, especially on the challenge image datasets. To this end, a self-supervised deep clustering method by maximizing mutual information is proposed (bi-MIM-SSC), where deep convolutional network is employed as a feature encoder. The first term is to maximize mutual information between output-feature pairs for importing more semantic meaning to the output features. The second term is to maximize mutual information between an input image and its feature generated by the encoder for keeping the useful information of an original image in latent space as possible. Furthermore, pre-training is carried out to further enhance the representation ability of the encoder, and the auxiliary over-clustering is added in clustering network. The performance of the proposed method bi-MIM-SSC is compared with other clustering methods on the CIFAR10, CIFAR100 and STL10 datasets. Experimental results demonstrate that the proposed bi-MIM-SSC method has better feature representation ability and provide better clustering results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HGAMLP: Heterogeneous Graph Attention MLP with De-Redundancy Mechanism

HGAMLP: Heterogeneous Graph Attention MLP with De-Redundancy...

引用

International Conference on Data Engineering

作者： Yuxuan Liang Wentao Zhang Zeang Sheng Ling Yang Jiawei Jiang Yunhai Tong Bin Cui School of Intelligence Science and Technology Peking University Center for Machine Learning Research Peking University School of CS & Key Laboratory of High Confidence Software Technologies (MOE) Peking University School of Computer Science Wuhan University Institute of Computational Social Science Peking University (Qingdao)

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Heterogeneous graphs contain rich semantic information that can be exploited by heterogeneous graph neural networks (HGNNs). However, scaling HGNNs to large graphs is challenging due to the high computational cost. Existing non-parametric HGNNs use general subgraphs construction method and mean aggregator before training to reduce the complexity. Despite their success, they ignore two key characteristics of heterogeneous graphs, leading to low predictive performance. First, they adopt fixed local and global knowledge extractor for the feature aggregation and the semantic fusion. Besides, they bury the graph structure information of the higher-order meta-paths and fail to explore deeper graph structure information. In this paper, we address these two limitations and propose a new non-parametric HGNN framework called Heterogeneous Graph Attention Multi-Layer Perceptron (HGAMLP). Our framework employs the local multi-knowledge extractor to enhance the node representation, and leverages the de-redundancy mechanism to extract the pure graph structure information from higher-order meta-paths. Besides, it adopts a node-adaptive weight adjustment mechanism as an efficiency training model to fuse global knowledge and local knowledge. We evaluate our framework on ten commonly used heterogeneous graph datasets and show that it outperforms the state-of-the-art baselines in both accuracy and speed. Notably, our framework achieves the best performance on the large public heterogeneous graph dataset (i.e., Ogbn-mag) of Open Graph Benchmark 1 1 https://***/docs/leader_nodeprop.

关键词： Training Accuracy Fuses Semantics Feature extraction Data engineering Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Second-Order Convolutional Neural Network Based on Cholesky Compression Strategy 21st

Second-Order Convolutional Neural Network Based on Cholesky ...

引用

21st International Conference on Parallel and Distributed Computing, Applications, and Technologies, PDCAT 2020

作者： Li, Yan Zhang, Jing Hua, Qiang Key Laboratory of Machine Learning and Computational Intelligence of Hebei Province College of Mathematics and Information Science Hebei University Baoding071002 China Research Center for Applied Mathematics and Interdisciplinary Sciences Beijing Normal University at Zhuhai Beijing519087 China

ISBN: (纸本)9783030692438

In the past few years, Convolution Neural Network (CNN) has been successfully applied to many computer vision tasks. Most of these networks can only extract first-order information from input images. The second-order statistical information refers to the second-order correlation obtained by calculating the covariance matrix, the fisher information matrix, or the vector outer product operation on the local feature group according to the channels. It has been shown that using second-order information on facial expression datasets can better capture the distortion of facial area features, while at the same time generate more parameters which may cause much more computational cost. In this article we propose a new CNN structure including layers which can (i) incorporate first-order information into the covariance matrix;(ii) use eigenvalue vectors to measure the importance of feature channels;(iii) reduce the bilinear dimensionality of the parameter matrix;and (iv) perform Cholesky decomposition on the positive definite matrix to complete the compression of the second-order information matrix. Due to the incorporation of both first-order and second-order information and the Cholesky compression strategy, our proposed method reduces the number of parameters by half of the SPDNet model, and simultaneously achieves better results in facial expression classification tasks than the corresponding first-order model and the reference second-order model. © 2021, Springer Nature Switzerland AG.

关键词： Covariance matrix

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：