检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Person Re-Identification and Trajectory Tracking in Cross-Device Edge Environments

A Method for Person Re-Identification and Trajectory Trackin...

引用

International Conference on Mobile Ad-hoc and Sensor networks, MSN

作者： Jian An Yunxiang Zhao Feifei Wang Xin He Xiaolin Gui School of Computer Science and Technology Shaanxi Provincial Key Laboratory of Computer Networks Xi’an Jiaotong University Xi’an China Henan Jiaoyuan Engineering Technology Group Co. LTD Henan China School of Software Henan University Henan China

ISBN: (数字)9798350358261

ISBN: (纸本)9798350358278

Addressing expanded surveillance scopes, cross-device person re-identification emerges as a crucial issue. Traditional approaches to re-identification and tracking confront challenges in feature matching challenges, and fail to harness the potential of edge computing environments, which offer viable solutions to bandwidth and latency constraints. The paper introduces a novel, edge computing and shared cache-based method for person re-identification and tracking. In this framework, edge nodes exploit deep learning method to execute image recognition for person re-identification and trajectory tracking. Edge nodes are deployed within a tri-layered architecture, encompassing Hierarchical Edge Cloud (HEC), Mobile Edge Computing (MEC), and Central Cloud (CC). Emphasizing part feature significance for person re-identification, the approach employs a refined Part-based Convolutional Baseline model guided by the triplet loss function. Experimental outcomes validate the high re-identification precision and efficacious load balancing capability of this method in person re-identification and tracking operations. Achieving a harmonized trade-off between task accuracy and response time, the proposed framework offers a robust solution for person re-identification and tracking within edge computing contexts.

关键词： Accuracy Trajectory tracking Image edge detection Computational modeling computer architecture Trajectory Time factors

来源：评论

学校读者我要写书评

暂无评论

A Fast Beam Training Method with Adaptive Feedback for Holographic Communications

A Fast Beam Training Method with Adaptive Feedback for Holog...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Yutong Zhang Boya Di Hongliang Zhang Lingyang Song State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China

Holographic communication is recently envisioned to be a promising technology to handle the exponentially increasing data transmission demands, utilizing a large number of compact and tunable antenna elements. In this paper, we consider a holographic communication system where the beam-forming scheme is developed by the codebook design and beam training to avoid the high overhead of acquiring perfect channel state information. Given the large-scale antenna array, users are expected to be distributed in both the near and far fields of the base station, and thus, we design a near-far field codebook to apply to all users in unknown locations. However, the fine-grained beam training using narrow beams capable of enhancing received signal power at the expense of a high overhead which occupies significant time resources. To tackle such a conflict, we propose the adaptive beam training that leverages user feedback to train user-densely distributed regions at a fine-grained level and user-sparsely distributed ones in a coarse manner, thereby improving the throughput. Under a general setting including both the near-field and far-field users, simulation results show that the proposed scheme achieves a higher sum rate and throughput compared to the state-of-the-art schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CSLP: Collaborative Solution to Long-Tail Problem and Popularity Bias in Sequential Recommendation

CSLP: Collaborative Solution to Long-Tail Problem and Popula...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yan Huang Zhenyu Yang Wenyue Hu Baojie Xu Zhibo Zhang The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Sequential Recommender Systems (SRS), leveraging the temporal information from users' behaviors, have noticeably improved user experience against traditional systems. However, these behaviors often follow long-tail distribution, making the systems biased towards popular items (i.e., popularity bias). Moreover, popularity bias would amplify the neglect of long-tail recommendations, thereby sharpening the long-tail problem. Previous researches usually address these challenges independently, focusing on reducing the over-recommendation of popular items or enhancing the representation quality of tail items. Indeed, it is possible to incorporate their merits to achieve the best of both worlds. Thus, we propose a novel and unified framework, named Collaborative Solution to Long tailed problem and Popularity bias (CSLP), to tackle both the long-tail problem and popularity bias simultaneously. To achieve this, we first introduce a representation enhancement module featuring dual generators to enhance user and item representations, particularly for those in the tail. On the other hand, a debiasing module incorporating an Inverse Propensity Score (IPS) with a clipping strategy is introduced to further alleviate the popularity bias. Specifically, this clipping strategy demonstrates a clear decrease in the original IPS method's variance, effectively improving the recommendation for stability and accuracy. Experiments on three widely-used datasets show CSLP's effectiveness in solving both issues. CSLP surpasses all baselines (traditional, popularity bias, and long-tail problem) in overall performance, significantly enhancing recommendation accuracy for both tail users and items, and achieving a more balanced ratio of recommendations between popular and tail items. Code is available at https://***/Echohuangyan/CSLP.

关键词： Hands Heavily-tailed distribution Accuracy Collaboration Tail Linear programming Generators User experience IP networks Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Multi-Modal Semantic Communication in UAV Collaborative networks

引用

IEEE Transactions on Communications 2025年

作者： Hu, Han Zhu, Xingwu Zhou, Fuhui Wu, Wei Hu, Rose Qingyang Zhu, Hongbo Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Wireless Communications Nanjing210003 China Nanjing University of Posts and Telecommunications Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Ministry of Education Nanjing210003 China Southeast University School of Cyber Science and Engineering Nanjing211189 China Nanjing University of Aeronautics and Astronautics College of Artificial Intelligence Nanjing210000 China Xidian University State Key Laboratory of Integrated Services Networks Xian710071 China Nanjing University of Posts and Telecommunications College of Communication and Information Engineering China Utah State University Department of Electrical and Computer Engineering LoganUT210003 United States

Semantic communication is envisioned as a potential communication paradigm enabled by artificial intelligence and is promising to break the Shannon limit for future 6G networks. This paradigm benefits unmanned aerial vehicles (UAVs) to conserve communication resources and minimize latency by only transmitting task-relevant semantic information. However, resource allocation in the multiple collaborative UAV scenarios remains unexplored, particularly regarding multi-modal semantic communication. To tackle this challenge, this paper investigates a semantic-aware intelligent resource allocation method for multi-UAV-assisted semantic communication networks in the UAV image-sensing task-oriented scenario. A multi-modal semantic communication framework with multi-UAV relay collaboration is developed. At the semantic level, a novel quality of experience (QoE) and the transmission cost model are introduced, based on which a semantic-aware resource allocation problem is formulated, aiming to maximize QoE while minimizing the transmission cost by jointly optimizing the UAV trajectory, the spectrum bandwidth, the transmit power and the number of the transmitted semantic symbols. To deal with optimization challenges involving hybrid variables and coordination among UAVs, a multi-UAV hybrid decision-controlled deep reinforcement learning (DRL) scheme is proposed. Simulation results demonstrate the effectiveness of the proposed scheme compared with the benchmark schemes in achieving a good balance between the QoE and the transmission cost. © 1972-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Disentangling Interest and Conformity Representation to Mitigate Popularity Bias for Sequential Recommendation

Disentangling Interest and Conformity Representation to Miti...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Wenyue Hu Zhenyu Yang Yan Huang Zhibo Zhang Baojie Xu Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The objective of sequential recommendation is to predict user preferences for items based on historical interaction sequences. This process often leads to a phenomenon known as popularity bias, where popular items are excessively recommended. Conformity, the tendency of users to follow popular items, is a significant factor contributing to this issue. Previous methods have not adequately disentangled conformity and interest, failing to accurately model users’ true intent. To address this, we propose a novel Disentangled Interest and Conformity Sequential Recommendation method (DICSRec) to mitigate the popularity bias. Specifically, we first design an Intent Encoding Module (IEM), which includes two independent encoders for conformity and interest to model their representations. To better disentangle these two factors, we design a disentangling task with proxy-based self-supervised learning and orthogonal regularization. Furthermore, to provide the Intent Encoding Module with more global information, we design a Global Conformity-aware Module (GCM), which supplies item popularity information and aids in enhancing user conformity representation. Lastly, recognizing the varying significance of user conformity and interest, we propose an adaptive Fusion Prediction Module (FPM) that adaptively aggregates user conformity and interest representations for final prediction. Experiments on four real-world datasets consistently demonstrate the superiority of our method over advanced sequential recommendation models. Code implementation is available at: https://***/lyra0611/DICSRec.

关键词： Adaptation models Codes Fuses Aggregates Neural networks Self-supervised learning Multitasking

来源：评论

学校读者我要写书评

暂无评论

A Cross-Modal Interactive Memory Network Based on Fine-Grained Medical Feature Extraction for Radiology Report Generation

A Cross-Modal Interactive Memory Network Based on Fine-Grain...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xitong Ma Yuansen Kuang Lin Yuan Cheng Tian Yijie Zeng Song Liu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Radiology report generation is an essential task in the medical field, which aims to automate the generation of medical terminology descriptions of radiology images. However, this task currently suffers from several problems: 1) existing methods need to manually build knowledge graphs or templates (consuming time and effort) to introduce medical or prior knowledge to assist in report generation; 2) previous models cannot handle the problem of data bias well (anomaly reports and anomaly descriptions make up only a tiny portion of the dataset), causing the models to ignore the learning of anomaly descriptions easily; 3) existing approaches cannot robustly supervise the model, resulting in incomplete and inconsistent reports being generated. To address these issues, we propose a cross-modal interactive memory network based on fine-grained medical feature extraction. In our model, we design a cross-modal interactive memory network to automatically store and remember the required medical text knowledge and use this medical knowledge to help generate reports. Furthermore, we design an abnormal medical knowledge enhancement module to enhance the learning of abnormal fine-grained knowledge through the interaction of disease topics and their states to interact with text features. In addition, we design a cross-modal joint semantic loss unit to reduce semantic differences between different features and improve the visual representation ability of the model. We experimented and evaluated our model on MIMIC-CXR and IU-Xray datasets to compare with other baseline models.

关键词： Knowledge engineering Visualization Terminology Semantics MIMICs Memory management Radiology Feature extraction Data models Biomedical imaging

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

IEEE International Conference on Systems, Man and Cybernetics

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

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Due to the exceptional performance of Transform-ers in 2 $D$ 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%.

关键词： Image segmentation Solid modeling Visualization Three-dimensional displays Current transformers Multilayer perceptrons Convolutional neural networks Kernel Synapses Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Co‑packaged optics(CPO):status,challenges,and solutions

引用

Frontiers of Optoelectronics 2023年第1期16卷 1-40页

作者： Min Tan Jiang Xu Siyang Liu Junbo Feng Hua Zhang Chaonan Yao Shixi Chen Hangyu Guo Gengshi Han Zhanhao Wen Bao Chen Yu He Xuqiang Zheng Da Ming Yaowen Tu Qiang Fu Nan Qi Dan Li Li Geng Song Wen Fenghe Yang Huimin He Fengman Liu Haiyun Xue Yuhang Wang Ciyuan Qiu Guangcan Mi Yanbo Li Tianhai Chang Mingche Lai Luo Zhang Qinfen Hao Mengyuan Qin School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyHong KongChina HKUST Fok Ying Tung Research Institute Guangzhou 511462China The Hong Kong University of Science and Technology(Guangzhou) Guangzhou 511462China Chongqing United Micro-Electronics Center(CUMEC) Chongqing 401332China Hisense Broadband Multimedia Technologies Co. Ltd.Qingdao 266000China Institute of Microelectronics Chinese Academy of SciencesBeijing 100029China State Key Laboratory of Superlattices and Microstructures Institute of SemiconductorsChinese Academy of SciencesBeijing 100083China School of Microelectronics Xi’an Jiaotong UniversityXi’an 710049China Zhangjiang Laboratory Shanghai 201210China The State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghai 200240China Huawei Technologies Co. Ltd.Shenzhen 440307China College of Computer National University of Defense TechnologyChangsha 410073China Institute of Computing Technology Chinese Academy of SciencesBeijing 100086China

Due to the rise of 5G,IoT,AI,and high-performance computing applications,datacenter trafc has grown at a compound annual growth rate of nearly 30%.Furthermore,nearly three-fourths of the datacenter trafc resides within *** conventional pluggable optics increases at a much slower rate than that of datacenter *** gap between application requirements and the capability of conventional pluggable optics keeps increasing,a trend that is *** optics(CPO)is a disruptive approach to increasing the interconnecting bandwidth density and energy efciency by dramatically shortening the electrical link length through advanced packaging and co-optimization of electronics and *** is widely regarded as a promising solution for future datacenter interconnections,and silicon platform is the most promising platform for large-scale *** international companies(e.g.,Intel,Broadcom and IBM)have heavily investigated in CPO technology,an inter-disciplinary research feld that involves photonic devices,integrated circuits design,packaging,photonic device modeling,electronic-photonic co-simulation,applications,and *** review aims to provide the readers a comprehensive overview of the state-of-the-art progress of CPO in silicon platform,identify the key challenges,and point out the potential solutions,hoping to encourage collaboration between diferent research felds to accelerate the development of CPO technology.

关键词： Co-packaged optics Silicon photonics High-performance computing Advanced packaging External laser Optical power delivery Co-simulation Standardization Transmitter Receiver

来源：评论

学校读者我要写书评

暂无评论

An Incentive Mechanism for Privacy Preserved Data Trading with Verifiable Data Disturbance

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Zhang, Man Li, Xinghua Luo, Bin Ren, Yanbing Miao, Yinbin Liu, Ximeng Deng, Robert H. State Key Laboratory of Integrated Services Networks the School of Cyber Engineering Xidian University Xi’an710071 China Engineering Research Center of Big data Security Ministry of Education Xi’an710071 China The College of Mathematics and Computer Science Fuzhou University Fujian350108 China The Department of Information Systems Singapore Management University 80 Stamford Road Singapore

To motivate data owners’ (DOs’) trading willingness, the existing incentive mechanisms allow DOs to independently disturb data following data consumer’s (DC’s) availability requirement. However, they cannot motivate DOs’ honest disturbance, which is attributed to DOs’ independent disturbance without any supervision. Thus, we implement an incentive mechanism for privacy preserved data trading with verifiable data disturbance where an honest-but-curious disturbance generator (DG) is additionally introduced to supervise DOs’ local disturbance and assist disturbance verification between DOs and DC. Specifically, DG generates the disturbance strategies and secretly distributes to DOs following private information retrieval, guaranteeing DOs’s local disturbance’s privacy and verifiability with our proposed three-level verification algorithm. Subsequently, we model the trading as a game and disturbance verification results determine the compensation and punishment for trading bilateral utilities following Nash Equilibrium where DOs honestly disturb data. Theoretical analysis shows that DOs are motivated to honestly disturb data and their raw data privacy is preserved. Extensive experiments using the real-world dataset demonstrate that the deviating DOs in our scheme can be verified with a probability of more than 90% and the statistical result accuracy can be improved by more than 80% compared with the existing works. © 2004-2012 IEEE. All rights reserved.

关键词： Differential privacy

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：