检索结果-内蒙古大学图书馆

Exploring implicit influence for social recommendation based on GNN

Soft computing 2024年第19期28卷 11001-11014页

作者： Liu, Zhewei Yang, Peilin Hao, Qingbo Zheng, Wenguang Xiao, Yingyuan Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China

In recent years, the method of using graph neural networks (GNN) to learn users’ social influence has been widely applied to social recommendation and has shown effectiveness, but several important challenges have not been well addressed: (i) Most work fails to consider the user interests (historical user-item interactions) when first building user-user social relationships, which can make it difficult to capture accurate user embedding and thus prevent the model from better exploring the users’ social influence;(ii) Most of the current methods do not build social neighbors (with the same item-user interaction) that belong to the item and do not aggregate information from the perspective of social neighbors, which makes it possible for the item to lose a lot of details when expressing the user’s interest factors. Therefore, to address the above challenges, we propose Exploring Implicit Influence for Social Recommendation Based on GNN (EIIGNN). First, we construct the initial user embedding with user-item interaction information and use the implicit modeling module in user modeling to explore the implicit influence of interest factors on users. In addition, EIIGNN models the social graph structure of item (an item-item graph) so that item can aggregate information from the perspective of their social neighbors, which helps the model learn a more accurate representation of the item. Finally, extensive experimental results on two real-world datasets clearly demonstrate the effectiveness of EIIGNN. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A novel policy iteration algorithm for solving the optimal consensus control problem of a discrete-time multiagent system with unknown dynamics

引用

Science China(Information Sciences) 2023年第8期66卷 269-270页

作者： Wenkai XU Li WANG Shiwen SUN Chengyi XIA Zengqiang CHEN Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology The Engineering Research Center of Learning-Based Intelligent System Ministry of Education College of Artificial Intelligence Nankai University

At present, an increasing number of researchers have noticed the importance of optimal consensus control(OCC) of multiagent systems(MASs) because of their rich practical applications in various areas [1–4]. To accomp...

关键词：

来源：评论

学校读者我要写书评

暂无评论

DNS Covert Channel Attack Detection Based on Spatio-Temporal Feature Fusion 22

DNS Covert Channel Attack Detection Based on Spatio-Temporal...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： You, Wei Zhao, Chunlei Shan, Chao Dong, Guozhong Yu, Jie Guan, Yong Tianjin University of Technology Tianjin Key Laboratory of Intelligent Computing and Software New Technology Tianjin China Coordination Center of China Hubei Branch of National Computer Network Emergency Response Technical Team HuBei China Pengcheng Laboratory Department of New Networks Shenzhen China

ISBN: (纸本)9798331509712

An increasing number of Advanced Persistent Threat (APT) organizations are utilizing DNS (Domain Name System) covert channels to evade network intrusion detection systems and establish private authoritative servers for remote attacks. However, current detection models for DNS covert channels often have poor performance and limited generalization ability. To address these challenges, we propose a DNS covert channel attack detection method based on spatiotemporal feature fusion. This method combines the Interaction timing sequence features of DNS traffic with the spatial statistical features of domain names, and constructs a detection model called ConvSLSTM, which integrates a Convolutional Neural Network (CNN) with a stacked Long Short Term Memory (LSTM) network. CNN extracts local spatial features from traffic, while stacked LSTM captures Interaction timing sequence features, significantly improving detection accuracy. This article uses three typical public datasets for experiments, which contain a total of 440000 DNS covert channel attack data. Comparative experiments show that our method is significantly superior to existing methods and exhibits stronger generalization ability in detecting DNS covert channel attacks constructed by unknown tools. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

MRIN: Fine-grained Feature Interaction based on Multiple Feature Relationships for CTR Prediction 26

MRIN: Fine-grained Feature Interaction based on Multiple Fea...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Ju, Jianbang Xiao, Yingyuan Yang, Peilin Zheng, Wenguang Tianjin University of Technology Enginnering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China

ISBN: (纸本)9798350331684

CTR prediction is an important task in personalized recommendation and online advertising. In recent years, many models have been applied in CTR prediction systems to imporve the predcition accuracy. Although the current work has achieved results, the diversity of relationships between the different features was ignored: 1) most existing models usually use the vector-product to realize the interaction of each feature pairs, which ignore the potential contexts between the different feature interactions and lack the different interactive behaviors between the same pair of features;2) most existing models usually only consider the importance of features of the same order, which ignore the weight relationships between the different feature *** this paper, we propose a novel deep learning model called Multi-Relational Interaction Network (MRIN), which learns fine-grained feature interactions and captures latent relationships between features. On the one hand, we design two interactive modules that take different interactive methods to learn the feature interactions in the potential contexts. On the other hand, we flexibly apply attention network to further automatically learn the weight relationships between different feature representations. Extensive experiments conducted on two public datasets prove the effectiveness of our proposed model, which has better performance than the state-of-the-art models. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

keywords extraction method based on two-way feature fusion 2

Keywords extraction method based on two-way feature fusion

引用

2nd International Conference on Machine Learning and intelligent Systems Engineering, MLISE 2022

作者： Li, Yongrui Ning, Hongyun Tianjin University Of Technology Tianjin Key Laboratory Of Intelligence Computing & New Software Technology Tianjin China

ISBN: (数字)9781665492461

ISBN: (纸本)9781665492461

In order to improve the accuracy of keyword extraction, an improved method was proposed to solve the problem of missing keywords in traditional TF-IDF keyword extraction algorithm. In this method, two routes are used to extract the features of the text, one is responsible for storing the dependency syntactic relations in the preprocessing of the text, and the other is responsible for calculating the tF-IDF value, part of speech and position of the words, and constructing the comprehensive scoring weighting formula of the candidate keywords. Finally, the feature information of these two paths is fused in the stage of combinatorial optimization and sorted to form formal extracted keywords. Experimental results show that compared with the traditional TF-IDF algorithm and Textrank algorithm, the F value of the proposed method in Sina news data set is improved by 14.4% and 16.3% respectively, which effectively verifies that the proposed method can significantly improve the keyword extraction performance. © 2022 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Text keyword Extraction Method Combined with Dependent Syntax Analysis 22

Text Keyword Extraction Method Combined with Dependent Synta...

引用

2nd International Conference on Control and intelligent Robotics, ICCIR 2022

作者： Li, Yongrui Ning, Hongyun Tianjin Key Laboratory of Intelligence Computing & New Software Technology Tianjin University of Technology Tianjin China

ISBN: (纸本)9781450397179

In order to improve the accuracy of key word extraction, an improved TF-IDF method was proposed to solve the problems that traditional TF-IDF keyword extraction algorithm could not recognize new words and polysemous words. This method first TF - IDF values, part of speech of words and position characteristics is calculated respectively, build candidate keywords weighted formula comprehensive score, then stored pretreatment before interdependence syntactic relations from the text, using the established syntactic relations to score higher candidate keywords for combinatorial optimization or reducing weight, the last order form formal extracting keywords. Experimental results show that compared with the traditional TF-IDF method, the multi-feature method based on dependency parsing improves the F value of the dataset containing new words by 10.4%, reaching 60.6%, and the F value of the dataset containing polysemous words by 17.9%, reaching 66.5%, which effectively verifies that the proposed method can improve the accuracy of keyword extraction. © 2022 ACM.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Node Coupling for Inferring Networks from Short Time Series 5th

Node Coupling for Inferring Networks from Short Time Series

引用

5th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2021

作者： Li, Hang Wang, Li Xia, Chengyi Tianjin University of Technology Tianjin300382 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Beijing China

ISBN: (纸本)9789811939976

Commonly abstracted as a set of units, the complex systems in the real world are interconnected with each other using the specific dynamical methods. However, in practice, there is nothing else but the performances of the system known, nor are the network structure and the dynamical rules observed. In order to solve this problem, a research has been conducted on network reconstruction, so as to recover the potential network structure and network dynamics from the observed time series. In this paper, a new method is proposed, namely, slope difference similarity (SDS), which is a way of thinking in reverse. Based on the trend of change in nodes, the coupling degree between nodes is judged and the network is reconstructed. By comparing the SDS and Kendall rank correlation method with experiments, the experimental results are obtained in this paper to demonstrate the effectiveness of SDS network reconstruction. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Deep User and Item Inter-matching Network for CTR Prediction 28th

Deep User and Item Inter-matching Network for CTR Predicti...

引用

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Yuan, Zhiyang Xiao, Yingyuan Yang, Peilin Hao, Qingbo Wang, Hongya Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China College of Computer Science and Engineering Donghua University Shanghai China

ISBN: (纸本)9783031306716

CTR prediction plays an important role in increasing company revenue and user experience, and many efforts start with historical behavior to uncover user interest. There are two main problems with previous works: (1) When most previous works mined interests from users’ historical behaviors, they only focus on implicit or explicit interests. (2) When most previous works mined user interests through the relationship between target users and similar users, the representation of target users was not rich and accurate enough, resulting in less accurate item recommendations. Therefore the Deep User and Item Inter-Matching Network (DUIIN) is proposed in this paper to solve the above problems. First, we design Item-to-Item Network (IIN), using two different sub-networks Evolving Interest Network (EIN) and Feature Interaction Network (FIN) to mine the hidden interests and explicit interests shown by users’ historical behaviors, respectively. Then the User-to-User Network (UUN) is designed to mine user interests through the relationship between target users and similar users after representing the target users more accurately and richly. The experimental results show that the DUIIN model proposed in this paper performs better than other state-of-the-art models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Security and privacy with opacity-based state observation for finite state machine

Security and privacy with opacity-based state observation fo...

引用

作者： Zhang, Zhipeng Xia, Chengyi Chen, Shengyong Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin University of Technology Tianjin China

Topics on security and privacy are very fundamental and important in the Internet of Things (IoT). In this paper, we explore the impact of state observation on the opacity of IoT, which is modeled by Moore-type finite state machine. Firstly, to characterize the intrusion estimator under the event-state observation, a multi-linear algebraic expression is proposed through the Boolean semi-tensor product (STP), and on the basis of the novel representation, the validation criterion is given by some matrix manipulations. Subsequently, considering that the input information may not be measured due to the physical shielding of the system against external intruders, we continue to discuss the opacity with state observation by a permutation structure matrix. Meanwhile, the verification of opacity with event-state observation is generalized to the one with only state observation. Finally, we offer an example to illustrate the effectiveness of the newly proposed method. Taken together, the current results are helpful to provide a novel theoretical approach for investigating the privacy-preserving problem in the area of IoT and complex cyber-physical networks. © 2021 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

CESFusion: Cross-Frequency Enhanced Spatial—Spectral Fusion Network for Hyperspectral and Multispectral Image Fusion

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Haozheng Yang, Yanhong Li, Chaoyang Lu, Yanjie Zhang, Guodao Chen, Shengyong Tianjin University of Technology School of Computer Science and Engineering Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China School of Computer Science and Engineering Tianjin300384 China Hangzhou Dianzi University Institute of Intelligent Media Computing Hangzhou310018 China

The fusion of hyperspectral and multispectral images (MSIs) involves integrating a high spectral resolution hyperspectral image (HSI) and a high spatial resolution MSI to generate an HSI with high-resolution HSI (HR-HSI). Existing HSI-MSI fusion methods primarily focus on information fusion within the spatial domain;however, few solutions have explored the employment of frequency analysis to enhance spatial resolution, limiting their capability for global perception. In this article, we propose an efficient and novel paradigm for HSI-MSI fusion through the cross-frequency enhanced spatial-spectral fusion network, named CESFusion, exploring the complementary fusion of information between the spatial and frequency domains. Specifically, we first present the cross-frequency fusion module (CFFM) to perform global analysis through the Fourier transform (FT) and effectively integrate and enhance the frequency domain information from both HSI and MSI. Subsequently, we propose the spectral modeling module (SpeMM) based on a state space model (SMM) to capture long-range spectral dependencies with linear complexity, and integrate it with the spatial residual block-based module (SRM) for joint spatial-spectral feature extraction. Finally, to enable sufficient interaction between the spatial and frequency domains, we adopt the cross-domain interaction module (CDIM), capturing and integrating complementary information from both domains. Moreover, a frequency-based loss function is purposely designed to further improve the restoration of global information. Extensive experiments conducted on both synthetic and real datasets demonstrate the superiority of our CESFusion, as evidenced by both quantitative and qualitative evaluation results. © 1980-2012 IEEE.

关键词： Image fusion

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：