检索结果-内蒙古大学图书馆

Deepwalk-aware graph convolutional networks

science China(Information sciences) 2022年第5期65卷 81-95页

作者： Taisong JIN Huaqiang DAI Liujuan CAO Baochang ZHANG Feiyue HUANG Yue GAO Rongrong JI Media Analytics and Computing Lab Department of Computer Science and Technology School of InformaticsXiamen University Media Analytics and Computing Lab Department of Artificial Intelligence School of InformaticsXiamen University School of Automation Science and Electrical Engineering Beihang University Tencent Youtu Lab School of Software Tsinghua University

Graph convolutional networks(GCNs) provide a promising way to extract the useful information from graph-structured data. Most of the existing GCNs methods usually focus on local neighborhood information based on specific convolution operations, and ignore the global structure of the input data. To extract the latent representation for the graph-structured data more effectively, we introduce a deepwalk strategy into GCNs to efficiently explore the global graph information. This strategy can complement the local neighborhood information of a graph, resulting in the more robust representation for the graph *** fusion of the local neighboring and global structured information of a graph can further facilitate deep feature learning at the output layer of GCNs for node classification. Experimental results show that the proposed model has achieved state-of-the-art results on three benchmark datasets including Cora, Citeseer,and Pubmed citation networks.

关键词： graph convolutional networks global information fusion node classification

来源：评论

学校读者我要写书评

暂无评论

Training Artificial Neural Networks by Coordinate Search Algorithm

Training Artificial Neural Networks by Coordinate Search Alg...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Rokhsatyazdi, Ehsan Rahnamayan, Shahryar Miyandoab, Sevil Zanjani Bidgoli, Azam Asilian Tizhoosh, H.R. Lab Ontario Tech University Department of Electrical Computer and Software Engineering OshawaON Canada Brock University Department of Engineering St. CatharinesON Canada Wilfrid Laurier University Faculty of Science WaterlooON Canada Rhazes Lab Mayo Clinic Department of Artificial Intelligence and Informatics RochesterMN United States

ISBN: (纸本)9781665430654

Training Artificial Neural Networks (ANNs) poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do have several limitations. For instance, they require differentiable activation functions, and cannot optimize a model based on several independent non-differentiable loss functions simultaneously;for example, the F1-score, which is used during testing, can be used during training when a gradient-free optimization algorithm is utilized. Furthermore, the training (i.e., optimization of weights) in any DNN can be possible with a small size of the training dataset. To address these concerns, we propose an efficient version of the gradient-free Coordinate Search (CS) algorithm, an instance of General Pattern Search (GPS) methods, for training (i.e., optimizing) neural networks. The proposed algorithm can be used with non-differentiable activation functions and tailored to multi-objective/multi-loss problems. Finding the optimal values for weights of ANNs is a large-scale optimization problem. Therefore instead of finding the optimal value for each variable, which is the common technique in classical CS, we accelerate optimization and convergence by bundling the variables (i.e., weights). In fact, this strategy is a form of dimension reduction for optimization problems. Based on the experimental results, the proposed method is comparable with the SGD algorithm, and in some cases, it outperforms the gradient-based approach. Particularly, in situations with insufficient labeled training data, the proposed CS method performs better. The performance plots demonstrate a high convergence rate, highlighting the capability of our suggested method to find a reasonable solution with fewer function calls. As of now, the only practical and efficient way of training ANNs with hundreds of thousands of weights is gradient-based algorithms such

关键词： Artificial Neural Network (ANN) Coordinate Search Expensive Optimization Gradient-free Large-Scale Optimization Stochastic Gradient Descent (SGD)

来源：评论

学校读者我要写书评

暂无评论

FastMig: Leveraging FastFreeze to Establish Robust Service Liquidity in Cloud 2.0

arXiv

引用

arXiv 2024年

作者： Manatura, Sorawit Chanikaphon, Thanawat Chantrapornchai, Chantana Salehi, Mohsen Amini HPCNC Lab Department of Computer Engineering Kasetsart University Thailand HPCC Lab School of Computing and Informatics University of Louisiana LafayetteLA United States HPCC Lab Computer Science and Engineering Department University of North Texas TX United States

Service liquidity across edge-to-cloud or multi-cloud will serve as the cornerstone of the next generation of cloud computing systems (Cloud 2.0). Provided that cloud-based services are predominantly containerized, an efficient and robust live container migration solution is required to accomplish service liquidity. In a nod to this growing requirement, in this research, we leverage FastFreeze, a popular platform for process checkpoint/restore within a container, and promote it to be a robust solution for end-to-end live migration of containerized services. In particular, we develop a new platform, called FastMig that proactively controls the checkpoint/restore operations of FastFreeze, thereby, allowing for robust live migration of containerized services via standard HTTP interfaces. The proposed platform introduces post-checkpointing and pre-restoration operations to enhance migration robustness. Notably, the pre-restoration operation includes containerized service startup options, enabling warm restoration and reducing the migration downtime. In addition, we develop a method to make FastFreeze robust against failures that commonly happen during the migration and even during the normal operation of a containerized service. Experimental results under real-world settings show that the migration downtime of a containerized service can be reduced by 30X compared to the situation where the original FastFreeze was deployed for the migration. Moreover, we demonstrate that FastMig and warm restoration method together can significantly mitigate the container startup overhead. Importantly, these improvements are achieved without any significant performance reduction and only incurs a small resource usage overhead, compared to the bare (i.e., non-FastFreeze) containerized services. Copyright © 2024, The Authors. All rights reserved.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Multi-view Learning for the Identification of Risky Users in Dynamic Social Networks

arXiv

引用

arXiv 2025年

作者： Benedetti, Francesco Pellicani, Antonio Pio, Gianvito Ceci, Michelangelo Dept. of Computer Science University of Bari Bari Italy Dept. of Computer Science University of Pisa Pisa Italy Data Science Lab National Interuniversity Consortium for Informatics Rome Italy Dept. of Knowledge Technologies Jožef Stefan Institute Ljubljana Slovenia

Technological progress in the last few decades has granted an increasing number of people access to social media platforms such as Facebook, X (formerly Twitter), and Instagram. Consequently, the potential risks associated with these services have also risen due to users exploiting these services for malicious purposes. The platforms have tools capable of detecting and blocking dangerous users, but they primarily focus on the content posted by users and usually overlook additional factors, such as the relationships among users. Another key aspect to consider is that users’ beliefs and interests evolve over time. Therefore, a user who can be considered safe at one moment might later become malicious, and vice versa. This work describes a novel approach to node classification in temporal graphs, aimed at classifying users in social networks. The method was evaluated on a real-world scenario and was compared to a state-of-the-art system that treats the network as a static entity. Experiments showed that taking into account the temporal evolution of the network, in terms of node features and connections, is beneficial. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

UMS: Live Migration of Containerized Services across Autonomous Computing Systems

UMS: Live Migration of Containerized Services across Autonom...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Thanawat Chanikaphon Mohsen Amini Salehi HPCC Lab School of Computing and Informatics University of Louisiana at Lafayette LA USA Computer Science and Engineering Department HPCC Lab University of North Texas

Containerized services deployed within various computing systems, such as edge and cloud, desire live migration support to enable user mobility, elasticity, and load balancing. To enable such a ubiquitous and efficient service migration, a live migration solution needs to handle circumstances where users have various authority levels (full control, limited control, or no control) over the underlying computing systems. Supporting the live migration at these levels serves as the cornerstone of interoperability, and can unlock several use cases across various forms of distributed systems. As such, in this study, we develop a ubiquitous migration solution (called UMS) that, for a given containerized service, can automatically identify the feasible migration approach, and then seamlessly perform the migration across autonomous computing systems. UMS does not interfere with the way the orchestrator handles containers and can coordinate the migration without the orchestrator involvement. Moreover, UMS is orchestrator-agnostic, i.e., it can be plugged into any underlying orchestrator platform. UMS is equipped with novel methods that can coordinate and perform the live migration at the orchestrator, container, and service levels. Experimental results show that for single-process containers, the service-level approach, and for multi-process containers with small $(< 128 \mathbf{MiB})$ memory footprint, the container-level migration approach lead to the lowest migration overhead and service downtime. To demonstrate the potential of UMS in realizing interoperability and multi-cloud scenarios, we examined it to perform live service migration across heterogeneous orchestrators, and between Microsoft Azure and Google Cloud.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Struct2Hair: A hair shape descriptor for hairstyle modeling

Struct2Hair: A hair shape descriptor for hairstyle modeling

引用

作者： Zhang, Wenshu Nie, Yinyu Guo, Shihui Chang, Jian Zhang, Jianjun Tong, Ruofeng Faculty of Arts and Media Norwich University of the Arts Norfolk United Kingdom The Visual Computing & Artificial Intelligence Lab Technical University of Munich München Germany School of Informatics Xiamen University Fujian China National Centre for Computer Animation Bournemouth University Dorset United Kingdom College of Computer Science and Technology Zhejiang University Zhejiang China

In recent years, it becomes possible to extract hair information for hair reconstruction from multiple cameras or monocular camera. Using a single image as the input avoids the high cost setups and complex calibration compared to multiviewed reconstruction. Taking advantage of an extendible hairstyle database, this paper introduced Struct2Hair, a novel single-viewed hair modelling approach by extracting hair shape descriptor (HSD). The HSD is defined as the fundamental structure-aware feature, which is a combination of critical shapes in a hairstyle. A complete dataset of critical hair shapes is constructed from a known database of three-dimensional (3D) hair models. We first analyze the input two-dimensional (2D) image to extract the orientation information and 2D hair sketch automatically. The extracted information is then used to retrieve the corresponding critical shapes with optimization to build the robust HSD. Finally, the HSD constructs a weighted 3D hair orientation field to guide full-head hair model generation. Our method can preserve local geometric features of hair and retain the whole shape of the hairstyle globally owing to the HSD, which will benefit further hair editing and stylization. © 2022 John Wiley & Sons Ltd.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Relational Message Passing for Fully Inductive Knowledge Graph Completion 39

Relational Message Passing for Fully Inductive Knowledge Gra...

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Geng, Yuxia Chen, Jiaoyan Pan, Jeff Z. Chen, Mingyang Jiang, Song Zhang, Wen Chen, Huajun Zhejiang University College of Computer Science and Technology Hangzhou China Donghai Laboratory Zhoushan China The University of Manchester Department of Computer Science Manchester United Kingdom School of Informatics The University of Edinburgh Edinburgh United Kingdom Naie Pdu Huawei Technologies Co. Ltd. Xi'an China Zhejiang University Hangzhou China Zhejiang University Azft Joint Lab for Knowledge Engine Hangzhou China

ISBN: (纸本)9798350322279

In knowledge graph completion (KGC), predicting triples involving emerging entities and/or relations, which are unseen when the KG embeddings are learned, has become a critical challenge. Subgraph reasoning with message passing is a promising and popular solution. Some recent methods have achieved good performance, but they (i) usually can only predict triples involving unseen entities alone, failing to address more realistic fully inductive situations with both unseen entities and unseen relations, and (ii) often conduct message passing over the entities with the relation patterns not fully utilized. In this study, we propose a new method named RMPI which uses a novel Relational Message Passing network for fully Inductive KGC. It passes messages directly between relations to make full use of the relation patterns for subgraph reasoning with new techniques on graph transformation, graph pruning, relation-aware neighborhood attention, addressing empty subgraphs, etc., and can utilize the relation semantics defined in the KG's ontological schema. Extensive evaluation on multiple benchmarks has shown the effectiveness of RMPI's techniques and its better performance compared with the existing methods that support fully inductive KGC. RMPI is also comparable to the state-of-the-art partially inductive KGC methods with very promising results achieved. Our codes, data and some supplementary experiment results are available at https://***/zjukg/RMPI. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation

HGFormer: Hierarchical Grouping Transformer for Domain Gener...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jian Ding Nan Xue Gui-Song Xia Bernt Schiele Dengxin Dai NERCMS School of Computer Science Wuhan University China State Key Lab. LIESMARS Wuhan University China Max Planck Institute for Informatics Saarland Informatics Campus Germany

Current semantic segmentation models have achieved great success under the independent and identically distributed (i.i.d.) condition. However, in real-world applications, test data might come from a different domain than training data. Therefore, it is important to improve model robustness against domain differences. This work studies semantic segmentation under the domain generalization setting, where a model is trained only on the source domain and tested on the unseen target domain. Existing works show that Vision Transformers are more robust than CNNs and show that this is related to the visual grouping property of self-attention. In this work, we propose a novel hierarchical grouping transformer (HGFormer) to explicitly group pixels to form part-level masks and then whole-level masks. The masks at different scales aim to segment out both parts and a whole of classes. HGFormer combines mask classification results at both scales for class label prediction. We assemble multiple interesting cross-domain settings by using seven public semantic segmentation datasets. Experiments show that HGFormer yields more robust semantic segmentation results than per-pixel classification methods and flat-grouping transformers, and outperforms previous methods significantly. Code will be available at https://***/dingjianswl0l/HGFormer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding Using Convolutional Neural Network and Digital Signal Processing Techniques 12

Reversible Data Hiding Using Convolutional Neural Network an...

引用

12th International Conference on Information Technology in Medicine and Education, ITME 2022

作者： Qingmei, Peng Shaozi, Li Yaojin, Lin Xiehua, Yu University of Fujian Province Key Laboratory of Big Data and Artificial Intelligence MinNan Science and Technology University Quanzhou China Xiamen University School of Informatics Xiamen China Minnan Normal University School of Computer Science Lab of Data Science and Intelligence Application Zhangzhou China

ISBN: (纸本)9798350310153

Reversible data hiding is a data hiding process in which data is encrypted into an image as a means of authentication, and hidden data is used to hide the original image, and RDH is often used in areas where data authenticity and data preservation are important, such as legal/criminal investigations, medical images. In this study, this paper designed a novel reversible data hiding system that utilizes the Steghide algorithm to encrypt images and hide data, as well as an artificial neural network to recover embedded text and structure. Based on the analysis of the test results, it was concluded that the RDH scheme proposed in this article has the same or higher system accuracy and reliability as the existing RDH scheme. To further refine the system results in future studies, this paper proposes to increase the number of training iterations and the number of images in the training dataset to further improve the accuracy and reliability of the development. © 2022 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

FORKING PATHS IN NEURAL TEXT GENERATION

arXiv

引用

arXiv 2024年

作者： Bigelow, Eric Holtzman, Ari Tanaka, Hidenori Ullman, Tomer Harvard University Department of Psychology United States Harvard University Center for Brain Science United States NTT Research Physics & Informatics Lab University of Chicago Department of Computer Science United States

Estimating uncertainty in Large Language Models (LLMs) is important for properly evaluating LLMs, and ensuring safety for users. However, prior approaches to uncertainty estimation focus on the final answer in generated text, ignoring intermediate steps that might dramatically impact the outcome. We hypothesize that there exist key forking tokens, such that re-sampling the system at those specific tokens, but not others, leads to very different outcomes. To test this empirically, we develop a novel approach to representing uncertainty dynamics across individual tokens of text generation, and applying statistical models to test our hypothesis. Our approach is highly flexible: it can be applied to any dataset and any LLM, without fine tuning or accessing model weights. We use our method to analyze LLM responses on 7 different tasks across 4 domains, spanning a wide range of typical use cases. We find many examples of forking tokens, including surprising ones such as punctuation marks, suggesting that LLMs are often just a single token away from saying something very different. © 2024, CC BY.

关键词：

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：