检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zheng, Zhuonan Zhou, Sheng Xu, Hongjia Gu, Ming Xu, Yilun Li, Ao Li, Yuhong Gu, Jingjun Bu, Jiajun College of Computer Science Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Hangzhou310027 China School of Software Technology Zhejiang University Ningbo315048 China Bytedance Inc. Hangzhou311113 China Alibaba Group Hangzhou310052 China

Graph Neural Networks (GNNs) have achieved remarkable success in various graph mining tasks by aggregating information from neighborhoods for representation learning. The success relies on the homophily assumption that nearby nodes exhibit similar behaviors, while it may be violated in many real-world graphs. Recently, heterophilous graph neural networks (HeterGNNs) have attracted increasing attention by modifying the neural message passing schema for heterophilous neighborhoods. However, they suffer from insufficient neighborhood partition and heterophily modeling, both of which are critical but challenging to break through. To tackle these challenges, in this paper, we propose heterophilous distribution propagation (HDP) for graph neural networks. Instead of aggregating information from all neighborhoods, HDP adaptively separates the neighbors into homophilous and heterphilous parts based on the pseudo assignments during training. The heterophilous neighborhood distribution is learned with orthogonality-oriented constraint via a trusted prototype contrastive learning paradigm. Both the homophilous and heterophilous patterns are propagated with a novel semantic-aware message passing mechanism. We conduct extensive experiments on 9 benchmark datasets with different levels of homophily. Experimental results show that our method outperforms representative baselines on heterophilous datasets. © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Structure Enhanced Prototypical Alignment for Unsupervised Cross-Domain Node Classification

SSRN

引用

SSRN 2023年

作者： Liu, Meihan Zhang, Zhen Ma, Ning Gu, Ming Wang, Haishuai Zhou, Sheng Bu, Jiajun College of Computer Science Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Hangzhou310027 China School of Software Technology Zhejiang University Ningbo315048 China School of Computing National University of Singapore 117417 Singapore

Graph Neural Networks (GNNs) have demonstrated remarkable success in graph node classification task. However, their performance heavily relies on the availability of high-quality labeled data, which can be time-consuming and labor-intensive to acquire for graph-structured data. Therefore, the task of transferring knowledge from a label-rich graph (source domain) to a completely unlabeled graph (target domain) becomes crucial. In this paper, we propose a novel unsupervised graph domain adaptation framework called Structure Enhanced Prototypical Alignment (SEPA), which aims to learn domain-invariant representations on non-IID (non-independent and identically distributed) data. Specifically, SEPA captures class-wise semantics by constructing a prototype-based graph and introduces an explicit domain discrepancy metric to align the source and target domains. The proposed SPEA framework is optimized in an end-to-end manner, which could be incorporated into various GNN architectures. Experimental results on several real-world datasets demonstrate that our proposed framework outperforms recent state-of-the-art baselines with different gains. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Braille Layout Detection Model Based on Semantic Assistance

Hierarchical Braille Layout Detection Model Based on Semanti...

引用

Image Processing and Computer Applications (ICIPCA), IEEE International Conference on

作者： Guangwu Wang Yu Gu Wei Wang Zhi Yu Shuyi Song China Braille Library Beijing China School of Software Technology Zhejiang University Hangzhou China Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China DBAPPSecurity Ltd. College of Computer Science Zhejiang University Hangzhou China

This paper proposes a hierarchical Braille layout detection model based on semantic assistance, BLayoutNet. As research on Braille layout analysis is relatively scarce and there is a lack of relevant datasets, this paper proposes a Braille layout detection dataset to support research in this field. Finally, experimental results demonstrate that the proposed model achieves stable and accurate detection of Braille layout. It is hoped that this model can serve as a strong baseline for Braille layout analysis tasks and promote the development of this field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Braille Detection Model Based on Foreground Attention and Semantic Learning

Braille Detection Model Based on Foreground Attention and Se...

引用

IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS)

作者： Guangwu Wang Yu Gu Wei Wang Zhi Yu Shuyi Song China Braille Library Beijing China School of Software Technology Zhejiang University Hangzhou China Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China DBAPP Security Ltd College of Computer Science Zhejiang University Hangzhou China

This paper presents BrailleNet, an enhanced one-stage anchor-based object detection model for Braille character recognition, incorporating foreground attention and semantic learning. BrailleNet is validated using two new datasets: mobile phone live shot Braille and chart Braille. Experimental results show BrailleNet's superior performance on both public and introduced datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bayesian estimation-based sentiment word embedding model for sentiment analysis

引用

CAAI Transactions on Intelligence technology 2022年第2期7卷 144-155页

作者： Jingyao Tang Yun Xue Ziwen Wang Shaoyang Hu Tao Gong Yinong Chen Haoliang Zhao Luwei Xiao Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials School of Physics and Telecommunication EngineeringSouth China Normal UniversityGuangzhouChina College of Mathematics and Informatics&College of Software Engineering South China Agricultural UniversityGuangzhouChina School of Foreign Languages Zhejiang University of Finance&EconomicsHangzhouZhejiangChina Educational Testing Service PrincetonNew JerseyUSA School of Computing Informatics and Decision Systems EngineeringArizona State UniversityTempeUSA

Sentiment word embedding has been extensively studied and used in sentiment analysis ***,most existing models have failed to differentiate high-frequency and low-frequency ***,the sentiment information of low-frequency words is insufficiently captured,thus resulting in inaccurate sentiment word embedding and degradation of overall performance of sentiment analysis.A Bayesian estimation-based sentiment word embedding(BESWE)model,which aims to precisely extract the sentiment information of low-frequency words,has been *** the model,a Bayesian estimator is constructed based on the co-occurrence probabilities and sentiment proba-bilities of words,and a novel loss function is defined for sentiment word embedding *** experimental results based on the sentiment lexicons and Movie Review dataset show that BESWE outperforms many state-of-the-art methods,for example,C&W,CBOW,GloVe,SE-HyRank and DLJT1,in sentiment analysis tasks,which demonstrate that Bayesian estimation can effectively capture the sentiment information of low-frequency words and integrate the sentiment information into the word embedding through the loss *** addition,replacing the embedding of low-frequency words in the state-of-the-art methods with BESWE can significantly improve the performance of those methods in sentiment analysis tasks.

关键词： function embedding estimation

来源：评论

学校读者我要写书评

暂无评论

Distilling holistic knowledge with graph neural networks

arXiv

引用

arXiv 2021年

作者： Zhou, Sheng Wang, Yucheng Chen, Defang Chen, Jiawei Wang, Xin Wang, Can Bu, Jiajun Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University School of Software Technology Zhejiang University University of Science and Technology of China Tsinghua University

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network. Existing KD methods have mainly considered two types of knowledge, namely the individual knowledge and the relational knowledge. However, these two types of knowledge are usually modeled independently while the inherent correlations between them are largely ignored. It is critical for sufficient student network learning to integrate both individual knowledge and relational knowledge while reserving their inherent correlation. In this paper, we propose to distill the novel holistic knowledge based on an attributed graph constructed among instances. The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner. Extensive experiments and ablation studies are conducted on benchmark datasets, the results demonstrate the effectiveness of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Distilling Holistic Knowledge with Graph Neural Networks

Distilling Holistic Knowledge with Graph Neural Networks

引用

International Conference on Computer Vision (ICCV)

作者： Sheng Zhou Yucheng Wang Defang Chen Jiawei Chen Xin Wang Can Wang Jiajun Bu Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University School of Software Technology Zhejiang University University of Science and Technology of China Tsinghua University

ISBN: (纸本)9781665428132

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network. Existing KD methods have mainly considered two types of knowledge, namely the individual knowledge and the relational knowledge. However, these two types of knowledge are usually modeled independently while the inherent correlations between them are largely ignored. It is critical for sufficient student network learning to integrate both individual knowledge and relational knowledge while reserving their inherent correlation. In this paper, we propose to distill the novel holistic knowledge based on an attributed graph constructed among instances. The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner. Extensive experiments and ablation studies are conducted on benchmark datasets, the results demonstrate the effectiveness of the proposed method. The code has been published in https://***/wyc-ruiker/HKD

关键词： Knowledge engineering Computer vision Correlation Codes Knowledge based systems Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient Medical Image Segmentation Based on Knowledge Distillation

arXiv

引用

arXiv 2021年

作者： Qin, Dian Bu, Jia-Jun Liu, Zhe Shen, Xin Zhou, Sheng Gu, Jing-Jun Wang, Zhi-Hua Wu, Lei Dai, Hui-Fen Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Ningbo Research Institute School of Software Technology Zhejiang University The Fourth Affiliated Hospital Zhejiang University School of Medicine

Recent advances have been made in applying convolutional neural networks to achieve more precise prediction results for medical image segmentation problems. However, the success of existing methods has highly relied on huge computational complexity and massive storage, which is impractical in the real-world scenario. To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network. This architecture empowers the lightweight network to get a significant improvement on segmentation capability while retaining its runtime efficiency. We further devise a novel distillation module tailored for medical image segmentation to transfer semantic region information from teacher to student network. It forces the student network to mimic the extent of difference of representations calculated from different tissue regions. This module avoids the ambiguous boundary problem encountered when dealing with medical imaging but instead encodes the internal information of each semantic region for transferring. Benefited from our module, the lightweight network could receive an improvement of up to 32.6% in our experiment while maintaining its portability in the inference phase. The entire structure has been verified on two widely accepted public CT datasets LiTS17 and KiTS19. We demonstrate that a lightweight network distilled by our method has non-negligible value in the scenario which requires relatively high operating speed and low storage usage. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Awareness and Settlement of IT Field key Challenges for Next Generation Development in World 2019

Awareness and Settlement of IT Field Key Challenges for Next...

引用

Proceedings of the 2019 7th International Conference on Information technology: IoT and Smart City

作者： Muhammad Bilal Zhi Yu Abid Bashir Muhammad Ali Hussain Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China Information Technology Services Manager MIS / Deputy Director of IT Department of Computer Science National Textile University Faisalabad Pakistan Management Science and Engineering School of Management and Economics University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781450376631

Information technology (IT) is playing a vital role in all aspects of our lives nowadays. IT is usually used for fast communication links and transferring useful information from one place to another. Nevertheless, around the world, unfortunately, IT is not properly handled. Without IT and Information and Communication technology (ICT) world will become a dark place. Most of the research in the IT field is inadequate. A subjective IT field development framework designed with the assistance of better Internet features utilized properly in all developing countries around the world. The proposed IT development framework can be used innovatively by adopting a wireless-based network in developing country growth around the world. We analyzed wired and wireless systems based on six common key Internet feature parameters for IT field improvement in developing countries around the world. In this empirical research, a total of 72 IT professional specialists included based on the statistical technique judgment sampling. The questionnaire survey results signify that speed, security, and reliability Internet features in the wired network are better than the wireless network. Moreover, mobility, coverage area, and cost relevant Internet features in the wireless network are much better than a wired network. According to expert decision-makers' strategy, the wireless-based network transmission medium is better to develop improvement in the world. Therefore, it finally concluded that developing countries could also play a significant role in the IT field as well as other fields around the world if Internet features are provided in the form of a wireless-based network properly. In the future, security and speed relevant problems will be resolved in the wireless-based system through improving routing algorithms.

关键词： Information technology Internet Decision-makers Developing countries Transmission medium

来源：评论

学校读者我要写书评

暂无评论

Awareness and settlement of IT field key challenges for next generation development in world 7

Awareness and settlement of IT field key challenges for next...

引用

7th International Conference on Information technology: IoT and Smart City, ICIT 2019

作者： Bilal, Muhammad Yu, Zhi Bashir, Abid Hussain, Muhammad Ali Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou310027 China Information Technology Services Department of Computer Science National Textile University Faisalabad38000 Pakistan Management Science and Engineering School of Management and Economics University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9781450376631

关键词： Developing countries

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：