检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Fu Liu, He Li, Zehan Cheng, Jingwei School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Zero-shot Relation Extraction (ZSRE) aims to predict novel relations from sentences with given entity pairs, where the relations have not been encountered during training. Prototype-based methods, which achieve ZSRE by aligning the sentence representation and the relation prototype representation, have shown great potential. However, most existing works focus solely on improving the quality of prototype representations, neglecting sentence representations, and lacking interaction between different types of relation side information. In this paper, we propose a novel ZSRE framework named CE-DA, which includes two modules: Custom Embedding and Dynamic Aggregation. We employ a two-stage approach to obtain customized embeddings of sentences. In the first stage, we train a sentence encoder through unsupervised contrastive learning, and in the second stage, we highlight the potential relations between entities in sentences using carefully designed entity emphasis prompts to further enhance sentence representations. Additionally, our dynamic aggregation method assigns different weights to different types of relation side information through a learnable network to enhance the quality of relation prototype representations. In contrast to traditional methods that treat the importance of all side information equally, our dynamic aggregation method further strengthens the interaction between different types of relation side information. Our method demonstrates competitive performance across various metrics on two ZSRE datasets. © 2025 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction 31

Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Re...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Li, Zehan Zhang, Fu Lyu, Kailun Cheng, Jingwei Peng, Tianyue School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Zero-shot Relation Triplet Extraction (ZSRTE) aims to extract triplets from the context where the relation patterns are unseen during training. Due to the inherent challenges of the ZSRTE task, existing extractive ZSRTE methods often decompose it into named entity recognition and relation classification, which overlooks the interdependence of two tasks and may introduce error propagation. Motivated by the intuition that crucial entity attributes might be implicit in the relation labels, we propose a Relation-Centric joint ZSRTE method named Re-Cent. This approach uses minimal information, specifically unseen relation labels, to extract triplets in one go through a unified model. We develop two span-based extractors to identify the subjects and objects corresponding to relation labels, forming span-pairs. Additionally, we introduce a relation-based correction mechanism that further refines the triplets by calculating the relevance between span-pairs and relation labels. Experiments demonstrate that Re-Cent achieves state-of-the-art performance with fewer parameters and does not rely on synthetic data or manual labor. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Feature Selection With Multi-Scale Fuzzy Information Fusion: From Both Global and Local Perspectives

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1825-1839页

作者： Zhou, Nan Liao, Shujiao Chen, Hongmei Ding, Weiping Lu, Yaqian Minnan Normal University School of Mathematics and Statistics Fujian Key Laboratory of Granular Computing and Applications Zhangzhou363000 China Southwest Jiaotong University School of Computing and Artificial Intelligence National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multi-scale data have received widespread attention due to its rich knowledge representation. However, current research on multi-scale data primarily focuses on supervised learning environments, while semi-supervised feature selection for multi-scale data with limited labels remains inadequately explored. Meanwhile, existing studies on multi-scale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multi-scale fuzzy information fusion mechanism, this article proposes two new semi-supervised feature selection approaches for multi-scale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multi-scale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semi-supervised feature selection algorithms are developed based on global and local multi-scale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multi-scale data with limited labels and exhibit superior classification performance, computational efficiency and robustness. © 1993-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Image Registration: Magic or Mirage? 38

Deep Learning in Medical Image Registration: Magic or Mirage...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jena, Rohit Sethi, Deeksha Chaudhari, Pratik Gee, James C. Computer and Information Science United States Electrical and Systems Engineering United States Radiology United States Penn Image Computing and Science Laboratory United States

Classical optimization and learning-based methods are the two reigning paradigms in deformable image registration. While optimization-based methods boast generalizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature. In this paper, we make an explicit correspondence between the mutual information of the distribution of per-pixel intensity and labels, and the performance of classical registration methods. This strong correlation hints to the fact that architectural designs in learning-based methods is unlikely to affect this correlation, and therefore, the performance of learning-based methods. This hypothesis is thoroughly validated with state-of-the-art classical and learning-based methods. However, learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods. Next, we show that this high-fidelity feature learning does not translate to invariance to domain shift, and learning-based methods are sensitive to such changes in the data distribution. We reassess and recalibrate performance expectations from classical and DLIR methods under access to label supervision, training time, and its generalization capabilities under minor domain shifts. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DSAFF-Net:A Backbone Network Based on Mask R-CNN for Small Object Detection

引用

Computers, Materials & Continua 2023年第2期74卷 3405-3419页

作者： Jian Peng Yifang Zhao Dengyong Zhang Feng Li Arun Kumar Sangaiah Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computing Science and Engineering Vellore Institute of Technology(VIT)Vellore632014India

Recently,object detection based on convolutional neural networks(CNNs)has developed *** backbone networks for basic feature extraction are an important component of the whole detection ***,we present a new feature extraction strategy in this paper,which name is *** this strategy,we design:1)a sandwich attention feature fusion module(SAFF module).Its purpose is to enhance the semantic information of shallow features and resolution of deep features,which is beneficial to small object detection after feature fusion.2)to add a new stage called D-block to alleviate the disadvantages of decreasing spatial resolution when the pooling layer increases the receptive *** method proposed in the new stage replaces the original method of obtaining the P6 feature map and uses the result as the input of the regional proposal network(RPN).In the experimental phase,we use the new strategy to extract *** experiment takes the public dataset of Microsoft Common Objects in Context(MS COCO)object detection and the dataset of Corona Virus Disease 2019(COVID-19)image classification as the experimental object *** results show that the average recognition accuracy of COVID-19 in the classification dataset is improved to 98.163%,and small object detection in object detection tasks is improved by 4.0%.

关键词： Small object detection classification RPN MS COCO COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Utility-Adjustable Reverse Auction Mechanism for UAV Data Collection Task Allocation 20th

A Utility-Adjustable Reverse Auction Mechanism for UAV Data...

引用

20th IFIP WG 10.3 International Conference on Network and Parallel computing, NPC 2024

作者： Chen, Peng Zhang, Jixian School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (纸本)9789819628636

Due to their low cost, easy deployment, and high flexibility, unmanned aerial vehicles(UAV) have become widely utilized for various data collection tasks across different fields. In particular, virtual service providers(VSP) recruit UAVs to collect data in their regions of interest(ROI), and leverage this data to offer a range of services, such as metaverse, traffic management, etc. To attract UAV owners to participate in the recruitment activities, VSP need to provide participating users with payments as rewards to motivate their participation. However, the recruitment demands of different VSPs for UAVs can vary significantly. For instance, time-sensitive tasks require timely recruitment of sufficient UAVs to ensure prompt completion of data collection tasks, necessitating higher payments to increase user enthusiasm. Conversely, in other types of tasks, the VSP’s objective might be to maximize its own utility. However, designing a general incentive mechanism for VSPs with different tasks that satisfies incentive compatibility(IC) and individual rationality(IR) to address the issues of UAV task allocation and payment is challenging. If VSP offer insufficient payments to users, it will be difficult to attract enough users to share their UAVs;conversely, offering excessive payments to users will harm the VSP’ profits. To address this problem, we propose a utility-adjustable reverse auction mechanism based on reverse Vickrey-Clarke-Groves(VCG) auction and affine maximizer auction(AMA) theory to cope with different task scenarios. This incentive mechanism can maximize social welfare while flexibly adjusting the utility allocation between VSP and users, ensuring non-negative utility for both parties. Experimental results show that the mechanism has excellent performance. © IFIP International Federation for Information Processing 2025.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data 38

Revealing Distribution Discrepancy by Sampling Transfer in U...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Zhilin Cao, Longbing Fan, Xuhui Zheng, Wei-Shi School of Computing Macquarie University Australia School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

There are increasing cases where the class labels of test samples are unavailable, creating a significant need and challenge in measuring the discrepancy between training and test distributions. This distribution discrepancy complicates the assessment of whether the hypothesis selected by an algorithm on training samples remains applicable to test samples. We present a novel approach called Importance Divergence (I-Div) to address the challenge of test label unavailability, enabling distribution discrepancy evaluation using only training samples. I-Div transfers the sampling patterns from the test distribution to the training distribution by estimating density and likelihood ratios. Specifically, the density ratio, informed by the selected hypothesis, is obtained by minimizing the Kullback-Leibler divergence between the actual and estimated input distributions. Simultaneously, the likelihood ratio is adjusted according to the density ratio by reducing the generalization error of the distribution discrepancy as transformed through the two ratios. Experimentally, I-Div accurately quantifies the distribution discrepancy, as evidenced by a wide range of complex data scenarios and tasks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HM-QCNN: Hybrid Multi-branches Quantum-Classical Neural Network for Image Classification 9th

HM-QCNN: Hybrid Multi-branches Quantum-Classical Neural Netw...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Liu, Haowen Gao, Yufei Shi, Lei Wei, Lin Shan, Zheng Zhao, Bo School of Cyber Science and Engineering Songshan Laboratory Zhengzhou University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9783031466632

Quantum machine learning has been developing in recent years, demonstrating great potential in various research domains and promising applications for pattern recognition. However, due to the constraints of quantum hardware, the input qubits are restricted caused by small circuit size, and the fuzziness in all dimensions caused by the features that are difficult to be effectively mined. Besides, previous studies focus on binary classification, but multi-classification received little attention. To address the difficulty in multi-classification, this paper proposed a hybrid multi-branches quantum-classical neural network (HM-QCNN) that utilizes a multi-branch strategy to construct the convolutional part. The part consists of three branches to extract the features of different scales and morphologies. Two quantum convolutional layers apply quantum CRZ gates and rotational gates to design a random quantum circuit (RQC) with 4 qubits and full qubits measurements. The experiments on three public datasets (MNIST, Fashion MNIST, and MedMNIST) demonstrate that HM-QCNN outperforms other prevalent methods with accuracy, precision, and convergence speed. Compared with the classical CNN and the hybrid neural network without multi-branches, HM-QCNN reached 97.40% and improved the accuracy of classification by 6.45% and 1.36% on the MNIST dataset, respectively. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Few-shot image recognition based on multi-scale features prototypical network

引用

High Technology Letters 2024年第3期30卷 280-289页

作者： LIU Jiatong DUAN Yong School of Information Science Engineering Shenyang University of TechnologyShenyang 110870P.R.China Shenyang Key Laboratory of Advanced Computing and Application Innovation Shenyang 110870P.R.China

In order to improve the model􀆳s capability in expressing features during few-shot learning,a multi-scale features prototypical network(MS-PN)algorithm is *** metric learning algo-rithm is employed to extract image features and project them into a feature space,thus evaluating the similarity between samples based on their relative distances within the metric *** sufficiently extract feature information from limited sample data and mitigate the impact of constrained data vol-ume,a multi-scale feature extraction network is presented to capture data features at various scales during the process of image feature ***,the position of the prototype is fine-tuned by assigning weights to data points to mitigate the influence of outliers on the *** loss function integrates contrastive loss and label-smoothing to bring similar data points closer and separate dissimilar data points within the metric *** evaluations are conducted on small-sample datasets mini-ImageNet and *** method in this paper can achieve higher classification ***,in the 5-way 1-shot experiment,classification accuracy reaches 50.13%and 66.79%respectively on these two ***,in the 5-way 5-shot ex-periment,accuracy of 66.79%and 85.91%are observed,respectively.

关键词： few-shot learning multi-scale feature prototypical network channel attention label-smoothing

来源：评论

学校读者我要写书评

暂无评论

A deep learning driven hybrid beamforming method for millimeter wave MIMO system

引用

Digital Communications and Networks 2023年第6期9卷 1291-1300页

作者： Jienan Chen Jiyun Tao Siyu Luo Shuai Li Chuan Zhang Wei Xiang The National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of ChinaChengduSichuan611731China National Mobile Communications Research Laboratory Southeast UniversityPurple Mountain LaboratoriesNanjing210096China School of Computing Engineering and Mathematical SciencesLa Trobe UniversityMelbourneVIC3086Australia

The hybrid beamforming is a promising technology for the millimeter wave MIMO system,which provides high spectrum efficiency,high data rate transmission,and a good balance between transmission performance and hardware *** most existing beamforming systems transmit multiple streams by formulating multiple orthogonal ***,the Neural network Hybrid Beamforming(NHB)adopts a totally different strategy,which combines multiple streams into one and transmits by employing a high-order non-orthogonal modulation *** by the Deep Learning(DL)hybrid beamforming,in this work,we propose a DL-driven nonorthogonal hybrid beamforming for the single-user multiple streams *** first analyze the beamforming strategy of NHB and prove it with better Bit Error Rate(BER)performance than the orthogonal hybrid beamforming even with the optimal power *** by the NHB,we propose a new DL-driven beamforming scheme to simulate the NHB behavior,which avoids time-consuming neural network training and achieves better BERs than traditional hybrid ***,our simulation results demonstrate that the DL-driven nonorthogonal beamforming outperforms its traditional orthogonal beamforming counterpart in the presence of subconnected schemes and imperfect Channel State Information(CSI).

关键词： Hybrid beamforming Neural network Deep learning driven Non-orthogonal beamforming

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：