检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Yi, Fengge Wei, Xiumei Liu, Xiaojing Jiang, Xuesong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

ISBN: (纸本)9798350330717

We present GauKGT5, a sequence-to-sequence model proposed for knowledge graph completion (KGC). Our research extends the KGT5 model, a recent sequence-to-sequence link prediction (LP) model. GauKGT5 takes advantage of textual characteristics inherent in the knowledge graph, exhibiting a small model size. However, KGT5's proficiency in link prediction necessitates the ensemble with a knowledge graph embedding model, which itself poses challenges due to its substantial size and expense. By integrating the Gated Attention Unit into the KGT5 model and directly applying it to the encoder-decoder structure, we achieve improved contextual dependency capturing within the sequence, resulting in enhanced prediction accuracy, accelerated training speed, and enhanced computational efficiency. At the same time, we introduce parallel computing as a means to enhance the efficiency of model training and inference within the XPU distributed computing environment. © 2023 IEEE.

关键词： gated attention unit knowledge graph completion sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Research on patent recommendation method based on graph neural network 26

Research on patent recommendation method based on graph neur...

引用

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

作者： Zhang, Enchao Liu, Weidong Liu, Shi Cao, Yan Institute of Scientific and Technical Information of China China College of Computer Science Inner Mongolia University China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

ISBN: (纸本)9798350331684

Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problems such as low patent transformation efficiency and poor transaction quality. This paper proposes a method of recommending patents to consumers by experts to improve the environment of patent transactions. Through the analysis of the past transaction information of the patent, the effective path information of the target is extracted. The graph neural network is used to describe the characteristics and semantics among experts, patents and consumers, and then capture the potential weight among them through the common attention mechanism, and then dynamically integrate them to predict the occurrence of recommendation behavior. The paper makes reasonable use of social information and expert information in the transaction, which significantly improves the rationality and accuracy of expert recommendation. © 2023 IEEE.

关键词： Patents and inventions

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient and Diverse Generative Model for Unconditional Human Motion Synthesis 24

Towards Efficient and Diverse Generative Model for Unconditi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yu, Hua Liu, Weiming Bai, Jiapeng Gui, Xu Hou, Yaqing Ong, Yewsoon Zhang, Qiang Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education School of Computer Science and Technology Dalian University of Technology Dalian China College of Computer Science Zhejiang University Hangzhou China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian China College of Computing and Data Science Nanyang Technological University Singapore Singapore Yonsei University Seoul Korea Republic of

ISBN: (纸本)9798400706868

Recent generative methods have revolutionized the way of human motion synthesis, such as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Denoising Diffusion Probabilistic Models (DMs). These methods have gained significant attention in human motion fields. However, there are still challenges in unconditionally generating highly diverse human motions from a given distribution. To enhance the diversity of synthesized human motions, previous methods usually employ deep neural networks (DNNs) to train a transport map that transforms Gaussian noise distribution into real human motion distribution. According to Figalli's regularity theory, the optimal transport map computed by DNNs frequently exhibits discontinuities. This is due to the inherent limitation of DNNs in representing only continuous maps. Consequently, the generated human motions tend to heavily concentrate on densely populated regions of the data distribution, resulting in mode collapse or mode mixture. To address the issues, we propose an efficient method called MOOT for unconditional human motion synthesis. First, we utilize a reconstruction network based on GRU and transformer to map human motions to latent space. Next, we employ convex optimization to match the noise distribution with the latent space distribution of human motions through the Optimal Transport (OT) map. Then, we combine the extended OT map with the generator of reconstruction network to generate new human motions. Thereby overcoming the issues of mode collapse and mode mixture. MOOT generates a latent code distribution that is well-behaved and highly structured, providing a strong motion prior for various applications in the field of human motion. Through qualitative and quantitative experiments, MOOT achieves state-of-the-art results surpassing the latest methods, validating its superiority in unconditional human motion generation. © 2024 ACM.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2022年

作者： Liu, Bin Papadopoulos, Dimitrios Malliaros, Fragkiskos D. Tsoumakas, Grigorios Papadopoulos, Apostolos N. Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and Telecommunications Chongqing400065 China School of Informatics Aristotle University of Thessaloniki Thessaloniki54124 Greece Gif-sur-Yvette91190 France

The discovery of drug-target interactions (DTIs) is a very promising area of research with great potential. The accurate identification of reliable interactions among drugs and proteins via computational methods, which typically leverage heterogeneous information retrieved from diverse data sources, can boost the development of effective pharmaceuticals. Although random walk and matrix factorization techniques are widely used in DTI prediction, they have several limitations. Random walk-based embedding generation is usually conducted in an unsupervised manner, while the linear similarity combination in matrix factorization distorts individual insights offered by different views. To tackle these issues, we take a multi-layered network approach to handle diverse drug and target similarities, and propose a novel optimization framework, called Multiple similarity DeepWalk-based Matrix Factorization (MDMF), for DTI prediction. The framework unifies embedding generation and interaction prediction, learning vector representations of drugs and targets that not only retain higher-order proximity across all hyper-layers and layer-specific local invariance, but also approximate the interactions with their inner product. Furthermore, we develop an ensemble method (MDMF2A) that integrates two instantiations of the MDMF model, optimizing the area under the precision-recall curve (AUPR) and the area under the receiver operating characteristic curve (AUC) respectively. The empirical study on real-world DTI datasets shows that our method achieves statistically significant improvement over current state-of-the-art approaches in four different settings. Moreover, the validation of highly ranked non-interacting pairs also demonstrates the potential of MDMF2A to discover novel DTIs. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The roles of urban buildings and vegetation in adjusting seasonal and daily air temperature 4

The roles of urban buildings and vegetation in adjusting sea...

引用

4th ISPRS Geospatial Week 2019

作者： Lan, Y. Huang, Z. Guo, R. Zhan, Q. Research Institute for Smart Cities School of Architecture and Urban Planning Shenzhen University Shenzhen China Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services Shenzhen University China Guangdong Key Laboratory of Urban Informatics Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Urban Design Wuhan University Wuhan China

Exploring the spatiotemporal patterns of the relationships between urban indicators and urban temperature is essential to improve the mitigation effectiveness when we intend to adjust built environment for moderating urban thermal environment. In this study, RS, GIS technology and statistical methods were involved to investigate the spatiotemporal patterns of the impacts of urban buildings and vegetation on Air Temperature (AT). Building Density (BD) and Normalized Difference Vegetation Index (NDVI) are the indicators for urban buildings and vegetation respectively. The objectives of this study are: 1) to determine an appropriate scale for examining the building-AT relationships and vegetation-AT relationships;2) to explore the seasonal and daily characteristics of these relationships;and 3) to compare the effects of urban buildings and vegetation. The results show that, for both summer and winter, a scale of 200–250 m is optimal for examining building-AT relationships, and 960–1020 m is the desirable scale for studying vegetation-AT relationships. Based on the optimal scales, we find that for both buildings and vegetation, they only significantly impact night-time temperature in both summer and winter. For seasonal comparison, the building-AT relationships and vegetation-AT relationships are relatively stronger in summer than in winter, which are indicated by R-square of the regression results. When comparing the effects of urban building and vegetation, we find that increasing vegetation is more effective than reduce buildings to achieve the same air temperature reduction. Our findings are conducive to generating space-time targeted Urban Heat Island (UHI) mitigation strategies. © Authors 2019.

关键词： Vegetation

来源：评论

学校读者我要写书评

暂无评论

Joint Sparsification and Quantization for Wireless Federated Learning under Communication Constraints 24

Joint Sparsification and Quantization for Wireless Federated...

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Su, Junshen Wang, Xijun Chen, Xiang Cheng, Ray-Guang Sun Yat-Sen University School of Electronics and Information Technology Guangzhou China The Chinese University of HongKong Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen China National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei Taiwan

ISBN: (纸本)9781665496261

Communication efficiency is one of the key bottlenecks in Federated Learning (FL). Compression techniques, such as sparsification and quantization, are used to reduce communication overhead. However, joint designs of these techniques under communication constraints are not well-explored. This paper investigates the joint uplink compression problem in communication-constrained FL systems. We propose a Block-TopK sparsification scheme to reduce the proportion of bits used for locating entries of a sparsified vector. Considering the communication constraints, an optimization formulation is proposed to minimize the compression error. By solving the optimization problem, our joint compression method provides a better trade-off between sparsity budget and bit width. Numerical results demonstrate that our approach achieves 99.96% of baseline accuracy with only 1.56% of the baseline communication overhead when training ResNet-18 on CIFAR-10. © 2023 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

MedX-Net: Hierarchical Transformer with Large Kernel Convolutions for 3D Medical Image Segmentation

MedX-Net: Hierarchical Transformer with Large Kernel Convolu...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Lin Zou, Qingzhi Key Laboratory of Computing Power Network and Information Se-curity Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Due to the exceptional performance of Transform-ers in 2D medical image segmentation, recent work has also introduced them into 3D medical segmentation tasks. For instance, Swin UNETR and other hierarchical Transformers have reintroduced prior knowledge from several convolutional networks, further enhancing the volume segmentation capabilities of models. The efficacy of these hybrid methodologies is primarily attributed to the substantial quantity of parameters and the nonlocal self-attention mechanism with a large receptive field. We argue that the behavior of these methods' large receptive fields can be simulated by employing fewer parameters through the utilization of depth-wise convolutions with large kernel. Within this manuscript, we introduce a lightweight volume segmentation model called MedX-Net, which uses convolutional network modules to simulate hierarchical Transformers for robust volume segmentation. Firstly, inspired by the hierarchical Transformer module of Swin UNETR, we investigate large-kernel depth-wise convolutions with different sizes to achieve a reduced model parameter count while maintaining a large global receptive field. Secondly, we replace the multilayer perceptron (MLP) in the hierarchical Transformer module with Inverted Bottleneck with Depthwise Convolution Enhancement(DWCE) to improve model performance with fewer activation and normalization layers, further reducing the parameter count. We validate the effectiveness and efficiency of our model for volume segmentation on three public datasets: Synapse, BTCV and ACDC. On the Synapse dataset, compared to Swin UNETR, our model achieves an improvement from 83.48% to 87.21% in Dice score. Compared to the result of 86.57% achieved by nnFormer, our model achieves superior performance while reducing the model parameter count by 64%. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploring deep gradient information for biometric image feature representation

引用

Neurocomputing 2016年 213卷 162-171页

作者： Jianjun Qian Jian Yang Ying Tai Hao Zheng School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiaozhuang University China

This paper presents a novel but simple biometric image feature representation method, called exploring deep gradient information (DGI). DGI first captures the local structure of an image by computing the histogram of gradient orientation of each macro-pixel (local patch around the reference pixel). Thus, one image can be decomposed into L sub-images (sub-orientation images) according to the gradient information of each macro-pixel since there are L bins in the local histogram. To enrich the gradient information, we also consider the gradient orientation and magnitude of original image as sub-images. For each sub-image, histogram of oriented gradient (HOG) is used to further explore the gradient orientation information. All HOG features are concatenated into one augmented super-vector. Finally, fisher linear discriminate analysis (FLDA) is applied to obtain the low-dimensional and discriminative feature vector. We evaluated the proposed method on the real-world face image datasets NUST-RWFR, Pubfig and LFW, the PolyU Finger-Knuckle-Print database and the PolyU Palmprint database. Experimental results clearly demonstrate the effectiveness of the proposed DGI compared with state-of-the-art algorithms, e.g., SIFT, HOG, LBP, POEM, LARK and IDLS.

关键词： Image representation Deep gradients Feature extraction Biometrics

来源：评论

学校读者我要写书评

暂无评论

Boosting Performance and QoS for Concurrent GPU B+trees by Combining-Based Synchronization 23

Boosting Performance and QoS for Concurrent GPU B+trees by C...

引用

28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, PPoPP 2023

作者： Zhang, Weihua Zhao, Chuanlei Peng, Lu Lin, Yuzhe Zhang, Fengzhe Lu, Yunping School of Computer Science Fudan University China Institute of Big Data Fudan University China State Key Laboratory of Mathematical Engineering and Advanced Computing China Parallel Processing Institute Fudan University China Department of Computer Science Tulane University United States

ISBN: (纸本)9798400700156

Concurrent B+trees have been widely used in many systems. With the scale of data requests increasing exponentially, the systems are facing tremendous performance pressure. GPU has shown its potential to accelerate concurrent B+trees performance. When many concurrent requests are processed, the conflicts should be detected and resolved. Prior methods guarantee the correctness of concurrent GPU B+trees through lock-based or software transactional memory (STM)-based approaches. However, these methods complicate the request processing logic, increase the number of memory accesses and bring execution path divergence. They lead to performance degradation and variance in response time increasing. Moreover, previous methods do not guarantee linearizability among concurrent requests. In this paper, we design a combined-based concurrency control framework, called Eirene, for GPU B+tree to reduce the overhead of conflict detection and resolution. First, a combining-based synchronization method is designed to combine and issue requests. It combines the requests with the same key, constructs their dependence, decides the issued request, and determines their return values. Since only one request for each key is issued, key conflicts are eliminated. Then, an optimistic STM method is used to reduce structure conflicts. The query and the update requests are partitioned into different kernels. For the update kernels, STM is involved only when the number of the retry reaches a threshold. Finally, a locality-aware warp reorganization optimization is proposed to improve memory behavior and reduce conflicts by exploiting the locality among requests. Evaluations on an NVIDIA A100 GPU show that Eirene is efficient (a throughput of 2.4 billion per second) and can guarantee linearizability. Compared to the state-of-the-art GPU B+tree, it can achieve a speedup of 7.43X and reduce the response time variance from 36% to 5%. © 2023 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Review on application progress of federated learning model and security hazard protection

引用

Digital Communications and Networks 2023年第1期9卷 146-158页

作者： Aimin Yang Zezhong Ma Chunying Zhang Yang Han Zhibin Hu Wei Zhang Xiangdong Huang Yafeng Wu Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and TechnologyTangshanHebeiChina Hebei Key Laboratory of Data Science and Application North China University of Science and TechnologyTangshanHebeiChina The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and TechnologyTangshanHebeiChina Tangshan Intelligent Industry and Image Processing Technology Innovation Center North China University of Science and TechnologyTangshanHebeiChina College of Science North China University of Science and TechnologyTangshanHebeiChina College of Artificial Intelligence North China University of Science and TechnologyTangshanHebeiChina

Federated learning is a new type of distributed learning framework that allows multiple participants to share training results without revealing their data *** data privacy becomes more important,it becomes difficult to collect data from multiple data owners to make machine learning predictions due to the lack of data *** is forced to be stored independently between companies,creating“data silos”.With the goal of safeguarding data privacy and security,the federated learning framework greatly expands the amount of training data,effectively improving the shortcomings of traditional machine learning and deep learning,and bringing AI algorithms closer to our *** the context of the current international data security issues,federated learning is developing rapidly and has gradually moved from the theoretical to the applied *** paper first introduces the federated learning framework,analyzes its advantages,reviews the results of federated learning applications in industries such as communication and healthcare,then analyzes the pitfalls of federated learning and discusses the security issues that should be considered in applications,and finally looks into the future of federated learning and the application layer.

关键词： data silos Machine learning Federated learning Privacy protection Learning framework

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：