检索结果-内蒙古大学图书馆

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Hongrui Gao Yawen Li Meiyu Liang Zeli Guan Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing School of Economics and Management Beijing University of Posts and Telecommunications Beijing

ISBN: (纸本)9781665456579

Since most scientific literature data are unlabeled, this makes unsupervised graph-based semantic representation learning crucial. Therefore, an unsupervised semantic representation learning method of scientific literature based on graph attention mechanism and maximum mutual information (GAMMI) is proposed. By introducing a graph attention mechanism, the weighted summation of nearby node features makes the weights of adjacent node features entirely depend on the node features. Depending on the features of the nearby nodes, different weights can be applied to each node in the graph. In addition, an unsupervised graph contrastive learning strategy is proposed to solve the problem of being unlabeled and scalable on large-scale graphs. By comparing the mutual information between the positive and negative local node representations on the latent space and the global graph representation, the graph neural network can capture both local and global information. Experimental results demonstrate competitive performance on various node classification benchmarks, achieving good results and sometimes even surpassing the performance of supervised learning.

关键词： Representation learning Cloud computing Semantics Supervised learning computer architecture Benchmark testing Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities

arXiv

引用

arXiv 2022年

作者： Zhao, Zhe Li, Yudong Hou, Cheng Zhao, Jing Tian, Rong Liu, Weijie Chen, Yiren Sun, Ningyuan Liu, Haoyan Mao, Weiquan Guo, Han Guo, Weigang Wu, Taiqiang Zhu, Tao Shi, Wenhang Chen, Chen Huang, Shan Chen, Sihong Liu, Liqun Li, Feifei Chen, Xiaoshuai Sun, Xingwu Kang, Zhanhui Du, Xiaoyong Shen, Linlin Yan, Kimmo Tencent AI Lab China School of Computer Science and Software Engineering Shenzhen University China School of Information and DEKE MOE Renmin University of China China

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations. © 2022, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Research on Microservice Architecture: A Tertiary Study

SSRN

引用

SSRN 2022年

作者： Liu, Xiaodong Li, Shanshan Zhang, He Zhong, Chenxing Wang, Yanze Waseem, Muhammad Babar, Muhammad Ali State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Software Institute Nanjing University Nanjing China School of Computer Science Wuhan University Wuhan China Centre for Research on Engineering Software Technologies School of Computer Science University of Adelaide Adelaide Australia Cyber Security Cooperative Research Centre Australia

Context: Microservices architecture (MSA) has gained its popularity for designing software systems. Migrating to MSA is a challenging task and requires comprehensive understanding and careful decisions. Objective: This study aims to characterize secondary studies in the field of MSA from two main points of view, i.e., the topics addressed and their findings, as well as the potential opportunities for the future research. Method: We conducted a tertiary study following the guideline of Kitchenham and collected data from secondary studies of MSA published by the end of 2021. Results: We identified 37 secondary studies in the domain of MSA, including systematic literature reviews and systematic mapping studies that address research questions. The topics addressed, the findings, and the research directions are analyzed in detail in terms of different phases of MSA lifecycle, i.e., Architectural Understanding and Analysis, Architectural Transformation, Architectural Implementation, and Architectural Maintenance and Evolution. Conclusion: Emerging topics require more in-depth research by primary and secondary researchers. Researchers are suggested to have more collaboration with industry and pay more attention to some domains as well as emerging technologies. Tertiary researchers may consider some new types of secondary study with quality control, for example, gray literature review or multivocal literature review. © 2022, The Authors. All rights reserved.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

EATS: Efficient Adaptive Test Case Selection for Deep Neural Networks

EATS: Efficient Adaptive Test Case Selection for Deep Neural...

引用

IEEE International Conference on software Quality, Reliability and Security (QRS)

作者： Huanze Meng Zhiyi Zhang Yuchen Ding Shuxian Chen Yongming Yao Collage of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China School of Mathematical Science Yangzhou University Yangzhou China Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Nanjing China Army Engineering of PLA Nanjing China

ISBN: (数字)9798350365634

ISBN: (纸本)9798350365641

As deep neural network (DNN) has made significant advancements across various fields, systematically testing DNN has become increasingly crucial. To uncover potential faults within DNN, a vast number of test cases and their correct labels are required, but the process of labeling is time-consuming and labor-intensive. To alleviate the burden on developers, test case selection techniques for DNN models have been proposed, assisting in the selection of test cases from large datasets that are more likely to reveal model faults. In this study, we introduce an efficient adaptive test case selection method based on the principle of uniform distribution of test cases, named EATS. In addition, we propose a test case optimization method and an image similarity calculation method. The optimization method can save time during the test case selection process, while the image similarity calculation method computes the degree of difference between images based on model uncertainty. EATS leverages the model’s uncertainty to achieve a more uniform distribution of selected test cases, aiming to select test cases that can induce a diversity of model fault predictions, thereby optimizing model performance. We conducted comparative experiments of EATS and other test case selection strategies on four common datasets and their corresponding DNN models. The experimental results show that EATS outperforms other methods in terms of the uniformity of test case distribution, diversity of errors discovered, and model optimization. It also demonstrates excellent time efficiency.

关键词： Adaptation models Uncertainty Costs Computational modeling Optimization methods Artificial neural networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

Dynamic Behavior Pattern: Mining the Fraudsters in Telecom Network

Dynamic Behavior Pattern: Mining the Fraudsters in Telecom N...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Dengshi Li Lu Zeng Ruimin Hu Zijun Huang Xiaocong Liang Yilong Zang School of Artificial Intelligence Jianghan University Wuhan China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China

In telecom network fraud, the fraud method of the fraudsters varies significantly in different periods. However, the traditional method of telecom fraud is to train the telecom fraud mining model through the user's long-term telephone data. So they can not detect the new fraud method of fraudsters and can not identify those with only have short-term telephone data. To increase the identification precision of telecom fraudsters, the dynamic changes in social structure and behavior pattern features of fraudsters were studied in this paper. Specifically, from the perspective of social structure change, the social structure of fraudsters changes rapidly over time. In contrast, the social structure of normal users is stable over time. From the perspective of user behavior pattern features, we found that the behavior patterns of fraudsters and normal users were very different. The behavior pattern of fraudsters in the different periods also changes significantly. Therefore, a telecom network fraud detection framework based on the social relationship evo-lution model was proposed. We designed the feature extraction method of dynamic telephone social behavior patterns based on time slices. The method combines the features of social structure and behavior patterns of users. And the Telephone Network Fraud Detection(TNFD) model is built using LSTM. We set up a sliding time window to enable the model to identify users with only short-term telephone data. This time window dynamically takes the features of the user's telephone social behavior pattern as the input of the TNFD model. Experiments on real dataset show that the precision of TNFD is 7% higher than that of the latest method. Our research may reference public security organs in telecom fraud cases.

关键词： Social networking (online) Telephone sets Feature extraction Data models Fraud Behavioral sciences Telecommunications

来源：评论

学校读者我要写书评

暂无评论

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling

arXiv

引用

arXiv 2024年

作者： Zha, Yaohua Li, Naiqi Wang, Yanzi Dai, Tao Guo, Hang Chen, Bin Wang, Zhi Ouyang, Zhihao Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University China Institute of Visual Intelligence Pengcheng Laboratory China College of Computer Science and Software Engineering Shenzhen University China Harbin Institute of Technology Shenzhen China Bytedance Inc China

The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transformer, leading to quadratic complexity and limited decoder, hindering their practice application. To address this limitation, we first conduct a comprehensive analysis of existing Transformer-based MPM, emphasizing the idea that redundancy reduction is crucial for point cloud analysis. To this end, we propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. Considering the varying information density between masked and unmasked patches in the decoder inputs of MPM, we introduce a locally constrained Mamba-based decoder. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density. Extensive experimental results show that our compact model significantly surpasses existing Transformer-based models in both performance and efficiency, especially our LCM-based Point-MAE model, compared to the Transformer-based model, achieved an improvement of 1.84%, 0.67%, and 0.60% in average accuracy on the three variants of ScanObjectNN while reducing parameters by 88% and computation by 73%. Code is available at https://***/zyh16143998882/LCM. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Adaptive Student Inference Network for Efficient Single Image Super-Resolution

Adaptive Student Inference Network for Efficient Single Imag...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Kang Miao Zhao Zhang Jiahuan Ren Mingbo Zhao Haijun Zhang Richang Hong School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China School of Information Science and Technology Donghua University Shanghai China Department of Computer Science Harbin Institute of Technology (Shenzhen) Shenzhen China

Recent advances in single image super-resolution (SISR) have achieved remarkable performance through deep learning. However, the high computational cost hinders the deployment of SISR models on edge devices. Instead of proposing new SISR models, a new trend is emerging to improve network efficiency by reducing parameters, FLOPs, and inference time through slight modifications to the original models. However, recent methods usually focus on reducing only one of three metrics, i.e., FLOPs, parameters and inference time, which inevitably increases the other two metrics. In this paper, we propose a novel Adaptive Student Inference Network (ASIN) on popular SISR models, which aims at reducing FLOPs and inference time while maintaining the number of parameters and restoring clearer high-resolution images. Specifically, our ASIN divides a SISR model into three components (head, body and tail) and adopts various strategies for each part. For head and tail parts, to ensure the restored images contain more detailed information, a novel auxiliary Enhanced Teacher Network (ETNet) is designed, which is trained with the ground-truth images to obtain more prior knowledge to guide student network to extract more accurate textures using a new knowledge distillation method. For the body part, owing to the varying difficulties of the reconstructions in different regions, we propose an Adaptive Depth Predicted Module (ADPM) to dynamically shorten average depth of network to reduce the computational cost of overall network. Extensive experiments on two datasets demonstrate the effectiveness and state-of-the-art performance of our ASIN compared to its counterparts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From Coarse to Fine: Knowledge Distillation for Remote Sensing Scene Classification

From Coarse to Fine: Knowledge Distillation for Remote Sensi...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jinsheng Ji Xiaoming Xi Xiankai Lu Yiyou Guo Huan Xie School of Electrical and Electronic Engineering Nanyang Technological University Singaproe School of Computer Science and Technology Shandong Jianzhu University Jinan China School of Software Shandong University Jinan China College of Surveying and Geo-Informatics Tongji University Shanghai China

Scene classification is one of the most commonly studied areas of parsing the earth observation data. How to effectively interpreting the remote sensing images and extracting informative features are the great challenges for remote sensing image classification. Many important applications, such as land management and urban analysis, are based on the performance of remote sensing classification model. Recently, a lot of CNN based methods have been proposed and achieve promising results. Inspired by the success of knowledge distillation which transfers the learned information from a teacher model to a student model, a knowledge distillation based framework is proposed in this paper to handle the task of remote sensing scene classification from coarse to fine. Specifically, the learned knowledge from the teacher network is transformed into the coarse soft label and fine output mask to better guiding the student network to learn more informative features. Experiments are conducted on two widely used remote sensing scene datasets to evaluate the effectiveness of the proposed method and achieve comparable results compared with some state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning

arXiv

引用

arXiv 2023年

作者： Ge, Jidong Liu, Yuxiang Gui, Jie Fang, Lanting Lin, Ming Kwok, James Tin-Yau Huang, LiGuo Luo, Bin State Key Laboratory for Novel Software Technology Software Institute Nanjing University Nanjing210093 China The School of Cyber Science and Engineering Southeast University Purple Mountain Laboratories Nanjing210000 China *** L.L.C. United States Alibaba Group China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology 999077 Hong Kong The Department of Computer Science Southern Methodist University DallasTX75205 United States

Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing the consistency of two augmentations, the burden of manual annotations can be freed. Contrastive learning exploits instance-level information to learn robust features. However, the learned information is probably confined to different views of the same instance. In this paper, we attempt to leverage the similarity between two distinct images to boost representation in self-supervised learning. In contrast to instance-level information, the similarity between two distinct images may provide more useful information. Besides, we analyze the relation between similarity loss and feature-level cross-entropy loss. These two losses are essential for most deep learning methods. However, the relation between these two losses is not clear. Similarity loss helps obtain instance-level representation, while feature-level cross-entropy loss helps mine the similarity between two distinct images. We provide theoretical analyses and experiments to show that a suitable combination of these two losses can get state-of-the-art results. Code is available at https://***/guijiejie/ICCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

EFM: A Negative Network Public Opinion Early Warning Model Based on Evolutionary Feature Mining

EFM: A Negative Network Public Opinion Early Warning Model B...

引用

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Fanfeixue Meng Jingchen Wu Feifan Song Xu Wu Lan Hu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security BUPT Beijing University of Posts and Telecommunications Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT School of Economics and Finance Changchun Finance College

With the popularity of the Internet and the increase in the number of netizens, it is of great significance to effectively monitor and predict the negative network public opinion on social media platforms. Most mainstream negative network public opinion early warning models mainly focus on mining textual features, while neglecting the response and dissemination among netizens during the process of negative network public opinion fermentation. This is one of the important reasons for the accuracy bottleneck of them. This article proposes a negative network public opinion early warning model based on evolutionary feature mining. Firstly, by using entity linking techniques based on knowledge graphs, domain prior knowledge is supplemented for the text need to be analyzed for negative network public opinion. Then, the text sentiment features extracted based on long short-term memory networks and the evolutionary features extracted based on graph convolutional networks are fused through an enhanced-feature fusion method. Finally, the features are used for classification and early warning. Experimental results based on the Weibo public dataset show that the EFM model has higher early warning performance for negative network public opinion compared to other baseline models. The accuracy of this model is 0.959.

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：