检索结果-内蒙古大学图书馆

Attention-based network embedding with higher-order weights and node attributes

CAAI Transactions on Intelligence technology 2024年第2期9卷 440-451页

作者： Xian Mo Binyuan Wan Rui Tang Junkai Ding Guangdi Liu School of Information Engineering Ningxia UniversityYinchuanChina School of Cyber Science and Engineering Sichuan UniversityChengduChina Computer Science and Information Technology University of MalayaKuala LumpurMalaysia Academy of Medical Sciences Zhengzhou UniversityZhengzhouChina

Network embedding aspires to learn a low-dimensional vector of each node in networks,which can apply to diverse data mining *** real-life,many networks include rich attributes and temporal ***,most existing embedding approaches ignore either temporal information or network attributes.A self-attention based architecture using higher-order weights and node attributes for both static and temporal attributed network embedding is presented in this article.A random walk sampling algorithm based on higher-order weights and node attributes to capture network topological features is *** static attributed networks,the algorithm incorporates first-order to k-order weights,and node attribute similarities into one weighted graph to preserve topological features of *** temporal attribute networks,the algorithm incorporates previous snapshots of networks containing first-order to k-order weights,and nodes attribute similarities into one weighted *** addition,the algorithm utilises a damping factor to ensure that the more recent snapshots allocate a greater *** features are then incorporated into topological ***,the authors adopt the most advanced architecture,Self-Attention Networks,to learn node *** results on node classification of static attributed networks and link prediction of temporal attributed networks reveal that our proposed approach is competitive against diverse state-of-the-art baseline approaches.

关键词： data mining deep neural networks social network

来源：评论

学校读者我要写书评

暂无评论

The governance technology for blockchain systems:a survey

引用

Frontiers of computer science 2024年第2期18卷 181-197页

作者： Guocheng ZHU Debiao HE Haoyang AN Min LUO Cong PENG School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China Shandong Provincial Key Laboratory of Computer Networks Qilu University of Technology(Shandong Academy of Sciences)Jinan 250014China

After the Ethereum DAO attack in 2016,which resulted in significant economic losses,blockchain governance has become a prominent research ***,there is a lack of comprehensive and systematic literature review on blockchain *** deeply understand the process of blockchain governance and provide guidance for the future design of the blockchain governance model,we provide an in-depth review of blockchain *** this paper,first we introduce the consensus algorithms currently used in blockchain and relate them to governance ***,we present the main content of off-chain governance and investigate two well-known off-chain governance ***,we investigate four common on-chain governance voting techniques,then summarize the seven attributes that the on-chain governance voting process should meet,and finally analyze four well-known on-chain governance blockchain projects based on the previous *** hope this survey will provide an in-depth insight into the potential development direction of blockchain governance and device future research agenda.

关键词： blockchain governance off-chain governance on-chain governance voting

来源：评论

学校读者我要写书评

暂无评论

Parameter Efficient Point Cloud Prompt Tuning for Unified Point Cloud Understanding

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-16页

作者： Fei, Ben Liu, Liwen Yang, Weidong Li, Zhijun Chen, Wen-Ming Ma, Lipeng School of Computer Science Fudan University Shanghai China School of Mechanical Engineering Tongji University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China

The prevailing paradigm in 3D vision involves fully fine-tuning all the backbone parameters of pre-trained models. However, this approach poses challenges due to the large number of parameters requiring tuning, resulting in unexpected storage demands. To address these issues and alleviate the computational cost and storage burden associated with full fine-tuning, we propose Point Cloud Prompt Tuning (PCPT) as an effective method for large Transformer models in point cloud processing. PCPT offers a powerful and efficient solution to mitigate the costs associated with full fine-tuning. Drawing inspiration from recent advancements in efficient tuning of large-scale language models and 2D vision models, PCPT leverages less than 0.05 % of trainable parameters, while keeping the pre-trained parameters of the Transformer backbone unchanged. To evaluate the effectiveness of PCPT, extensive experiments were conducted on four discriminative datasets (ModelNet40, few-shot ModelNet40, ScanObjectNN, ShapeNetPart) and four generation datasets (PCN, MVP, ShapeNet55, and ShapeNet34/Unseen21). The results demonstrate that the task-specific prompts utilized in PCPT enable the Transformer model to adapt effectively to the target domains, yielding results comparable to those obtained through other full fine-tuning methods. This highlights the versatility of PCPT across various domains and tasks. Our code is available at https://***/Fayeben/PCPT. IEEE

关键词： Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

OpenAnnotate2: Multi-Modal Auto-Annotating for Autonomous Driving

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Zhou, Yijie Cai, Likun Cheng, Xianhui Zhang, Qiming Xue, Xiangyang Ding, Wenchao Pu, Jian School of Computer Science Fudan University Shanghai China Independent Researcher Shanghai China SenseAuto Inc Shanghai China Computer Science Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Institute of Science and Technology for BrainInspired Intelligence Fudan University Shanghai China

The demand for high-quality annotated data has surged in recent years for applications driven by real-world artificial intelligence, such as autonomous driving and embodied intelligence. Consequently, the development of a tool that can assist humans in the highly automated and high-quality annotation of large-scale, multi-modal data is of significant importance and urgency for both academic research and practical applications. Most existing multi-modal data annotation tools require frame-by-frame, object-by-object annotation with keyboard and mouse, making it challenging to provide high-quality and real-time annotations for 2D images and 3D point clouds in highly open scenarios like autonomous driving. To address these challenges, we propose OpenAnnotate2, which understands human intentions based on natural language prompt, and formulates plans to decompose and execute complex multi-modal data annotation tasks. Additionally, the tool can continually enhance its cognitive and annotation capabilities with minimal human-computer interaction, through an ever-updating external knowledge base. This significantly simplifies the annotation workflow, paving the way for the creation of massive datasets suitable for large-scale visual models. The source code will be released at https://***/Fudan-ProjectTitan/OpenAnnotate. IEEE

关键词： Three dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Minimum Epsilon-Kernel Computation for Large-Scale Data Processing

引用

Journal of computer science & technology 2022年第6期37卷 1398-1411页

作者： Hong-Jie Guo Jian-Zhong Li Hong Gao School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518000China

Kernel is a kind of data summary which is elaborately extracted from a large *** a problem,the solution obtained from the kernel is an approximate version of the solution obtained from the whole dataset with a provable approximate *** is widely used in geometric optimization,clustering,and approximate query processing,etc.,for scaling them up to massive *** this paper,we focus on the minimumε-kernel(MK)computation that asks for a kernel of the smallest size for large-scale data *** the open problem presented by Wang et *** whether the minimumε-coreset(MC)problem and the MK problem can be reduced to each other,we first formalize the MK problem and analyze its *** to the NP-hardness of the MK problem in three or higher dimensions,an approximate algorithm,namely Set Cover-Based Minimumε-Kernel algorithm(SCMK),is developed to solve *** prove that the MC problem and the MK problem can be Turing-reduced to each ***,we discuss the update of MK under insertion and deletion operations,***,a randomized algorithm,called the Randomized Algorithm of Set Cover-Based Minimumε-Kernel algorithm(RA-SCMK),is utilized to further reduce the complexity of *** efficiency and effectiveness of SCMK and RA-SCMK are verified by experimental results on real-world and synthetic *** show that the kernel sizes of SCMK are 2x and 17.6x smaller than those of an ANN-based method on real-world and synthetic datasets,*** speedup ratio of SCMK over the ANN-based method is 5.67 on synthetic ***-SCMK runs up to three times faster than SCMK on synthetic datasets.

关键词： approximate query processing kernel large-scale dataset NP-hard

来源：评论

学校读者我要写书评

暂无评论

Opinion Mining-Based Predictive Model Based on Social Media Responses 1

引用

2nd International Conference on Human-Centric Smart Computing, ICHCSC 2023

作者： Bhattacharya, Priyanka Guha, Sutirtha Kumar Department of Computer Science & Engineering Academy of Technology West Bengal Hooghly India Department of Computer Science & Engineering Meghnad Saha Institute of Technology West Bengal Kolkata India

ISBN: (数字)9789819977116

ISBN: (纸本)9789819977109

In the present-day scenario, it is observed that the effect of any natural or man-made disaster creates a havoc mess on society. The change in human behavior plays a crucial part in achieving sustainability. The development of a mathematical model to measure and analyze the relationship between environmental stability and human behavior can be a valuable tool in this effort. The proposed predictive model is helpful to identify the specific behaviors and the factors that can affect the harmony of the surroundings, to promote more sustainable outcomes. This paper would be helpful for the development of strategies and interventions to change behavior and promote more sustainable practices, both at the individual and societal levels. It has been explained in this paper that the stability of society toward any kind of disaster is dependent on social media as nowadays social media is the basic platform for communication in society. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Progressive Growth for Point Cloud Completion by Surface-Projection Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 1-15页

作者： Fei, Ben Zhang, Rui Yang, Weidong Li, Zhijun Chen, Wen-Ming School of Computer Science Fudan University Shanghai China School of Mechanical Engineering Tongji University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China

Point cloud completion concentrates on completing geometric and topological shapes from incomplete 3D shapes. Nevertheless, the unordered nature of point clouds will hamper the generation of high-quality point clouds without predicting structured and topological information of the complete shapes and introducing noisy points. To effectively address the challenges posed by missing topology and noisy points, we introduce SPOFormer, a novel topology-aware model that utilizes surface-projection optimization in a progressive growth manner. SPOFormer consists of three distinct steps for completing the missing topology: (1) Missing Keypoints Prediction. A topology-aware transformer auto-encoder is integrated for missing keypoint prediction. (2) Skeleton Generation. The skeleton generation module produces a new type of representation named skeletons with the aid of keypoints predicted by topology-aware transformer auto-encoder and the partial input. (3) Progressively Growth. We design a progressive growth module to predict final output under Multi-scale Supervision and Surface-projection Optimization. Surface-projection Optimization is firstly devised for point cloud completion, aiming to enforce the generated points to align with the underlying object surface. Experimentally, SPOFormer model achieves an impressive Chamfer Distance-$\ell _{1}$ (CD) score of 8.11 on PCN dataset. Furthermore, it attains average CD-$\ell _{2}$ scores of 1.13, 1.14, and 1.70 on ShapeNet-55, ShapeNet-34, and ShapeNet-Unseen21 datasets, respectively. Additionally, the model achieves a Maximum Mean Discrepancy (MMD) of 0.523 on the real-world KITTI dataset. These outstanding qualitative and quantitative performances surpass previous approaches by a significant margin, firmly establishing new state-of-the-art performance across various benchmark datasets. Our code is available at https://***/kiddoray/SPOFormer IEEE

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Complex Social Networks: Dynamics, Domains, and Dimensions 1

引用

International Conference on Electrical and Electronics engineering, ICEEE 2023

作者： Gera, Suruchi Sinha, Adwitiya Department of Computer Science and Engineering JSS Academy of Technical Education Noida India Department of Computer Science and Engineering and Information Technology Jaypee Institute of Information Technology Noida India

ISBN: (数字)9789819986613

ISBN: (纸本)9789819986606

The online social platforms witnessed enormous growth in its networked structure as users continue to connect and interact through e-social dialogues. This eventually causes the transformational emergence of online social systems into complex networks. These large-scale networks inherently allow social entities to get engaged in diverse forms of interactions, thereby resulting in dynamic and complex user behavior. This raises many distinct challenges in social networks, which requires cross-dimensional analysis of the complex information for societal benefits. Understanding these complex systems has become crucial for analyzing the behavioral characteristics for drawing essential inferences. Analysis and evaluation of social complex networks in the context of several parameters are performed with prerequisites of graph theory, computational statistics, and probabilistic models. Our research provides a review of the evolving challenges in the social domain with case studies being conducted over multiple social systems. The study covers major aspects of social network theory that reveal communities and the impact of the central behavior of users. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model to Detect Fake News about COVID-19

引用

Recent Advances in computer science and Communications 2023年第9期16卷 58-66页

作者： Shanmugavel, Selva Birunda Rangaswamy, Kanniga Devi Muthukannan, Muthiah Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamil Nadu India School of Computer Science and Engineering Vellore Institute of Technology Chennai Tamil Nadu Chennai India Department of Civil Engineering KCG College of Technology Chennai India

Aims/Background: Twitter has rapidly become a go-to source for current events coverage. The more people rely on it, the more important it is to provide accurate data. Twitter makes it easy to spread misinformation, which can have a significant impact on how people feel, especially if false information spreads around COVID-19. Methodology: Unfortunately, twitter was also used to spread myths and misinformation about the illness and its preventative immunization. So, it is crucial to identify false information before its spread gets out of hand. In this research, we look into the efficacy of several different types of deep neural networks in automatically classifying and identifying fake news content posted on social media platforms in relation to the COVID-19 pandemic. These networks include long short-term memory (LSTM), bi-directional LSTM, convolutional-neural-networks (CNN), and a hybrid of CNN-LSTM networks. Results: The "COVID-19 Fake News" dataset includes 42,280, actual and fake news cases for the COVID-19 pandemic and associated vaccines and has been used to train and test these deep neural networks. Conclusion: The proposed models are executed and compared to other deep neural networks, the CNN model was found to have the highest accuracy at 95.6%. © 2023 Bentham science Publishers.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

BDSLL: Biomedical Document Recommendation Using Knowledge-Empowered Semantic Intercepted Large Language Models 4th

BDSLL: Biomedical Document Recommendation Using Knowledge-Em...

引用

4th International Conference on Emerging Trends and Technologies on Intelligent Systems, ETTIS 2024

作者： Aravind Krishnan, A. Deepak, Gerard Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering BMS Institute of Technology and Management Bangalore India

ISBN: (纸本)9789819757022

There is a requirement for document recommendation frameworks focusing on certain domains linked to medical sciences and biosciences like biomedical document recommendation in the era of the Web 3.0. This paper proposes a biomedical document recommendation strategy that realizes informative term generation using the encompassment of extraction of terms and categories and the TF-IDF. The framework also generates an ontology from the informative terms harvested from which features are selected to classify the dataset using a random forest classifier. The model also uses very strong knowledge bases that are highly specific to the domain like QIAGEN. It also uses WikiData which is generic but has a full cover of world knowledge to bridge the knowledge present in the datasets and the existing structure web. Metadata generation also increases the quantity of additional knowledge that is encompassed in the model. BioBERT is a strategic large language model that focuses on biosciences and biomedicine as its domain is used to classify the metadata to make it more permeable into the model. Semantic similarity is computed using NPMI, web overlap, SimRank, and Ricklefs and Lau index at different stages in the pipeline to facilitate quantitative reasoning through semantic relatedness computation. The salient semantic analysis also accelerates the overall semantic association into the proposed framework. This framework can demonstrate a precision of 96.56%, recall of 96.93%, and an FDR of 0.04. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ontology

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：