检索结果-内蒙古大学图书馆

D^(2)-GCN:a graph convolutional network with dynamic disentanglement for node classification

Frontiers of Computer science 2025年第1期19卷 145-161页

作者： Shangwei WU Yingtong XIONG Hui LIANG Chuliang WENG School of Data Science and Engineering East China Normal UniversityShanghai 200062China

Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation. Disentangled GCNs have been proposed to divide each node’s representation into several feature units. However, current disentangling methods do not try to figure out how many inherent factors the model should assign to help extract the best representation of each node. This paper then proposes D^(2)-GCN to provide dynamic disentanglement in GCNs and present the most appropriate factorization of each node’s mixed features. The convergence of the proposed method is proved both theoretically and experimentally. Experiments on real-world datasets show that D^(2)-GCN outperforms the baseline models concerning node classification results in both single- and multi-label tasks.

关键词： graph convolutional networks dynamic disentanglement label entropy node classification

来源：评论

学校读者我要写书评

暂无评论

Agents with foundation models:advance and vision

引用

Frontiers of Computer science 2025年第4期19卷 119-120页

作者： Chenghua GONG Xiang LI School of Data Science and Engineering East China Normal UniversityShanghai 200062China

1 Introduction With rapid development in computing power and breakthroughs in deep learning,the concept of“foundation models”has been introduced into the AI ***,foundation models are large models trained on massive data and can be easily adapted to different domains for various *** specific prompts,foundation models can generate texts and images,or even animate scenarios based on the given *** to powerful capabilities,there is a growing trend to build agents based on foundation *** this paper,we conduct an investigation into agents empowered by the foundation models.

关键词： computing power foundation models adapted different domains animate scenarios deep learningthe massive data generate texts imagesor deep learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain with drug traceability in medical supply chain with Henry gas solubility optimisation algorithm

引用

International Journal of Wireless and Mobile Computing 2025年第2期28卷 135-148页

作者： Devi, P. Yamini Sriramya, P. Department of Computer Science and Engineering Saveetha School of Engineering Thandalam Tamil Nadu Chennai India Department of Data Science Saveetha School of Engineering SIMATS Tamil Nadu Chennai India

The drug traceability model is used for ensuring drug quality and its safety for customers in the medical supply chain. The healthcare supply chain is a complex network, which is susceptible to failures and leakage of information because of cyber security attacks. Hence, this research aims to design a blockchain to perform traceability of drugs using Henry Gas Solubility Optimisation (HGSO). The entities include distributors, wholesalers, retailers, blockchain and patients. This model comprises initialisation, registration, key generation, authentication, drug distribution with traceability and key generation phases. Any exchange of medicines needs the approval of both sender and receiver. The drugs are registered in the blockchain, which then generates a secret key that is obtained using HGSO. The verification and authentication of drugs are performed after the authentication process. The implemented model outperformed with the response time, memory, normalised variance, and privacy of 32.678 sec, 84 MB, 0.958 and 0.958. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： authentication blockchain drug traceability key generation medical supply chain

来源：评论

学校读者我要写书评

暂无评论

Knowledge Probabilization in Ensemble Distillation: Improving Accuracy and Uncertainty Quantification for Object Detectors

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 221-233页

作者： Yang, Yang Wang, Chao Gong, Lei Wu, Min Chen, Zhenghua Li, Xiang Chen, Xianglan Zhou, Xuehai University of Science and Technology of China School of Computer Science and Technology Hefei230026 China 138632 Singapore East China Normal University School of Data Science and Engineering Shanghai200062 China

Ensemble object detectors have demonstrated remarkable effectiveness in enhancing prediction accuracy and uncertainty quantification. However, their widespread adoption is hindered by significant computational and storage demands, limiting their feasibility in resource-constrained settings. To overcome this, researchers have focused on distilling the knowledge from ensemble object detectors into a single model. In this article, we introduce probabilization based ensemble distillation (ProbED), an innovative ensemble distillation framework that consolidates knowledge from multiple object detectors into a single, resource-efficient model. Unlike traditional ensemble distillation methods that average the outputs of subteachers, ProbED captures comprehensive outcome distributions from all subteachers, providing a more nuanced approach to knowledge transfer. ProbED employs knowledge probabilization to achieve a sophisticated and refined aggregation of teacher knowledge, including feature knowledge, semantic knowledge, and localization knowledge, resulting in dual improvements in prediction accuracy and uncertainty quantification for the student model. In particular, ProED's novel knowledge probabilization-based approach to aggregating teacher knowledge is inspired by our empirical observations, which demonstrate that knowledge probabilization excels in effectively representing uncertainty, improving prediction, and facilitating robust knowledge transfer. Furthermore, we introduce a random smoothing perturbation technique to modify inputs within ProbED, further enhancing the distillation process. Extensive experiments highlight ProbED's ability to significantly enhance the prediction accuracy and uncertainty quantification of various object detectors, demonstrating its superior performance compared to other state-of-the-art techniques. © 2024 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

DeepSwarm:towards swarm deep learning with bi-directional optimization of data acquisition and processing

引用

Frontiers of Computer science 2025年第3期19卷 125-127页

作者： Sicong LIU Bin GUO Ziqi WANG Lehao WANG Zimu ZHOU Xiaochen LI Zhiwen YU School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’an 710072China School of Data Science City University of Hong KongHong Kong 999077China College Of Computer Science And Technology Harbin Engineering UniversityHarbin 150001China

1 Introduction On-device deep learning(DL)on mobile and embedded IoT devices drives various applications[1]like robotics image recognition[2]and drone swarm classification[3].Efficient local data processing preserves privacy,enhances responsiveness,and saves ***,current ondevice DL relies on predefined patterns,leading to accuracy and efficiency *** is difficult to provide feedback on data processing performance during the data acquisition stage,as processing typically occurs after data acquisition.

关键词： drone swarm classification efficient local data processing data processing deep learning dl device deep learning bi directional optimization iot devices swarm deep learning

来源：评论

学校读者我要写书评

暂无评论

CBIR: a novel identification approach for college students in need based on consumer behavior psychology theory

引用

Neural Computing and Applications 2025年第6期37卷 4663-4677页

作者： Liu, Xinze Liu, Shixi Hu, Xiaojing Zhang, Yudong Fang, Xianwen School of Computer and Information Engineering Chuzhou University Chuzhou239000 China School of Computer Science and Engineering Southeast University Nanjing210096 China School of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

The accurate identification of students in need is crucial for governments and colleges to allocate resources more effectively and enhance social equity and educational fairness. Existing approaches to identifying students in need rely on manual operations that include manually extracting consumption behavior information, statistical consumption characteristics and principal component analysis. However, this issue may lead to low prediction accuracy and inefficiency in identifying students in need. We design a three-stage framework to accurately identify college students in need from the perspective of consumer behavior psychology. The consumption behavior information is first obtained from the student consumption records using the consumption behavior clustering approach. The consumption behavior matrix is then built by extracting consumption and spatiotemporal information in different periods. Finally, a novel consumption behavior identification ResNeSt (CBIR) model is proposed to identify college students in need accurately. The experimental results on real datasets show that the CBIR model has higher prediction accuracy than the baseline models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Social psychology

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

science China(Information sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

引用

science China(Information sciences) 2025年第2期68卷 103-119页

作者： Wenyu CAI Mengfan LI Xuanhua SHI Yuanxin FAN Quntao ZHU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and Technology

Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.

关键词： knowledge graph reasoning temporal knowledge graph Hawkes process semantic evidence

来源：评论

学校读者我要写书评

暂无评论

Crack-DETR: Complex Pavement Crack Detection by Multifrequency Feature Extraction and Fusion

引用

IEEE Sensors Journal 2025年第9期25卷 16349-16360页

作者： Liu, Guoxi Liu, Guozhi Chai, Xinzhuo Li, Lecheng Dai, Fei Huang, Bi Southwest Forestry University School of Big Data and Intelligent Engineering Kunming650233 China South China University of Technology School of Computer Science and Engineering Guangdong Guangzhou510006 China

Automated detection of pavement cracks plays a crucial role in road maintenance and traffic safety. However, pavement crack detection under noisy conditions is challenging due to the complex expression forms of pavement cracks and the presence of multitype background noise. In this article, we propose Crack-DETR, an efficient pavement crack detection deep learning network, that can detect complex pavement cracks from complex background noise. In this network, we first propose a multifrequency feature extraction and fusion (MFEF) block to enhance pavement crack features and suppress background noise from both high-frequency and low-frequency perspectives in two stages: multifrequency feature extraction and multifrequency feature fusion. In the multifrequency feature extraction stage, we design a high-frequency attention mechanism to extract high-frequency features from high-level features. Then, we propose a low-frequency attention mechanism to capture low-frequency features of high-level features. In the multifrequency feature fusion stage, we fuse the high- and low-frequency features through intrafrequency feature fusion and cross-frequency feature fusion. Second, we propose an evaluating metric, diagonal intersection over union (DIoU), to enhance the loss function of Crack-DETR, improving the learning effectiveness of the model. Finally, we conduct extensive experiments on three real-world datasets with different scenarios, and the experimental results show that our method can improve the frames per second (FPS) by about 33.4% and mAP@50 by about 6.78% on average compared with baseline model in the YN dataset. Consequently, Crack-DETR achieves higher accuracy while reducing computational complexity, paving the way for the development of sensor-based real-time pavement crack detection. © 2001-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Prompt Learning for Few-Shot Question Answering via Self-Context data Augmentation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 589-603页

作者： Qiu, Jian-Qiang Zhang, Chun-Yang Chen, C. L. Philip Fuzhou University College of Computer and Data Science Fuzhou350108 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China

Pretrained language models (PLMs) have shown remarkable performance on question answering (QA) tasks, but they usually require fine-tuning (FT) that depends on a substantial quantity of QA pairs. Therefore, improving the performance of PLMs in scenarios with only a small number of training examples, also known as a few-shot setting, is of great practical significance. Current mitigation strategies for the few-shot QA task largely rely on pretraining a QA task-specific language model from scratch, overlooking the potential of foundational PLMs to generate QA pairs, particularly in the few-shot setting. To address this issue, we propose a prompt-based QA data augmentation method aimed at automating the creation of high-quality QA pairs. It employs the PFT method, adapting the question generation process of PLMs to the few-shot setting. Additionally, we introduce a dynamic text filling training strategy. This strategy simulates the progressive human learning process, thereby alleviating overfitting of PLMs in the few-shot setting and enhancing their reasoning capability to tackle complex questions. Extensive experiments demonstrate that the proposed method outperforms existing approaches across various few-shot configurations. 2691-4581 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://***/publications/rights/*** for more information.

关键词： Zero-shot learning

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：