检索结果-内蒙古大学图书馆

Learning label-specific features for decomposition-based multi-class classification

Frontiers of computer Science 2023年第6期17卷 101-110页

作者： Bin-Bin JIA Jun-Ying LIU Jun-Yi HANG Min-Ling ZHANG College of Electrical and Information Engineering Lanzhou University of TechnologyLanzhou 730050China School of Computer Science and Engineering Southeast UniversityNanjing 210096China Key Laboratory of Computer Network and Information Integration(Ministry of Education) Southeast UniversityNanjing 210096China

Multi-class classification can be solved by decomposing it into a set of binary classification problems according to some encoding rules,e.g.,one-vs-one,one-vs-rest,error-correcting output *** works solve these binary classification problems in the original feature space,while it might be suboptimal as different binary classification problems correspond to different positive and negative *** this paper,we propose to learn label-specific features for each decomposed binary classification problem to consider the specific characteristics containing in its positive and negative ***,to generate the label-specific features,clustering analysis is respectively conducted on the positive and negative examples in each decomposed binary data set to discover their inherent information and then label-specific features for one example are obtained by measuring the similarity between it and all cluster *** clearly validate the effectiveness of learning label-specific features for decomposition-based multi-class classification.

关键词： machine learning multi-class classification error-correcting output codes label-specific features

来源：评论

学校读者我要写书评

暂无评论

Securing STAR-FC-RIS empowered integrated sensing and multiuser communications against target eavesdropping

引用

Science China(Information Sciences) 2024年第11期67卷 335-346页

作者： Shuying LIN Yulong ZOU Fu XIAO Bin LI School of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications School of Computer Science Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications

This paper investigates a simultaneous-transmitting-and-reflecting fully-connected reconfigurable intelligent surface(STAR-FC-RIS) empowered integrated sensing and multiuser communications(ISAMC) network, where a dual-functional radar-communication base station detects a malicious radar target nearby and communicates with multiple legitimate users on the other side of the STAR-RIS. We utilize an integrated architecture that combines the fully-connected(FC)-RIS, an emerging type of beyond-diagonal(BD)-RIS, with the time-switching(TS)-STAR-RIS to enhance both the sensing and communications at the cost of possible target intercepting and propose the simultaneous-transmitting-and-reflecting fully-connected RIS(STAR-FCR) schemes to strike a balance between sensing and communications performance. Thereafter, observing the security-reliability performance tradeoff of the downlink ISAMC, we conduct closed-form analyses to compare COPs of round-robin scheduling(RS) and multiuser scheduling(MS) with the aid of a TS-based STAR-FC-RIS. Furthermore, we derive closed-form expressions of the sensing outage probability, communications outage probability(COP), and communications intercept probability, where an average of the three probabilities is exploited to obtain an optimized time allocation(OTA) of the *** results verify that the STAR-FCR-MS scheme outperforms the STAR-FCR-RS scheme in terms of sensing reliability and communications security. Moreover, an OTA remarkably enhances the overall performance of the STAR-FCR schemes of ISAMC systems.

关键词： simultaneous-transmitting-and-reflecting reconfigurable intelligent surface (RIS) fully-connected beyond-diagonal RIS integrated sensing and communications multiuser scheduling security

来源：评论

学校读者我要写书评

暂无评论

Text-Guided Portrait Image Matting

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4149-4162页

作者： Xu, Yong Yao, Xin Liu, Baoling Quan, Yuhui Ji, Hui South China University of Technology School of Computer Science and Engineering Guangzhou510000 China Communication and Computer Network Laboratory of Guangdong Guangzhou510641 China Peng Cheng Laboratory Shenzhen518000 China National University of Singapore Department of Mathematics 119076 Singapore

Image matting is a technique used to separate the foreground of an image from the background, which estimates an alpha matte that indicates pixel-wise degree of transparency. To precisely extract target objects and address the ambiguity of solutions in image matting, many existing approaches employ a trimap or background image provided by the user as additional input to guide the matting process. This article introduces a novel matting paradigm termed text-guided image matting, utilizing a textual description of the foreground object as a guiding element. In contrast to trimap or background-based methods, text-guided matting offers a user-friendly interface, providing semantic clues for the objects of interest. Moreover, it facilitates batch processing across multiple frames featuring the same objects of interest. The proposed text-guided matting approach is implemented through a deep neural network (NN) comprising three-stage cross-modal feature fusion and two-step alpha matte prediction. Experimental results on portrait matting demonstrate the competitive performance of our text-guided approach compared to existing trimap-based and background-based methods. © 2020 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Traffic Flow Prediction Based Task Offloading Method in Vehicular Edge Computing 18th

A Traffic Flow Prediction Based Task Offloading Method in V...

引用

18th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2023

作者： Xie, Liqiong Chen, Long Li, Xiaoping Wang, Shuang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing211189 China

ISBN: (纸本)9789819996391

Vehicular Edge Computing (VEC) emerges as a promising paradigm by deploying computation and storage resources on edge servers located in close proximity to vehicles, such as roadside units or base stations. This proximity enables VEC to provide abundant resources and low-latency services, catering to the computational needs of vehicles. However, the dynamic nature of traffic flow presents new challenges in terms of task offloading decisions and resource allocation within VEC environments. This paper addresses the task offloading problem in VEC systems, considering the impact of dynamic traffic flow. To address this problem, we formulate an integer programming model that captures the essence of the studied scenario. To devise an efficient solution, we propose a novel traffic flow prediction-based heuristic algorithm (TFPVTO). TFPVTO incorporates different rules and strategies to generate an optimal offloading task sequence, make informed offloading decisions, and allocate resources effectively. To assess the performance of the proposed algorithm, we utilize a real-world traffic flow dataset. In order to fine-tune and optimize the algorithm’s components, we employ a multi-factor analysis of variance (ANOVA) technique. The proposed TFPVTO algorithm is then rigorously compared against other state-of-the-art algorithms, namely TAVF, MONSA, and RANDOM. Through extensive experiments and statistical analysis, we demonstrate the effectiveness and efficiency of the proposed algorithm in terms of task offloading performance. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Learning a generalizable re-identification model from unlabelled data with domain-agnostic expert

引用

Visual Intelligence 2024年第1期2卷 1-13页

作者： Liu, Fangyi Ye, Mang Du, Bo National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan 430072 China

In response to real-world scenarios, the domain generalization (DG) problem has spurred considerable research in person re-identification (ReID). This challenge arises when the target domain, which is significantly different from the source domains, remains unknown. However, the performance of current DG ReID relies heavily on labor-intensive source domain annotations. Considering the potential of unlabeled data, we investigate unsupervised domain generalization (UDG) in ReID. Our goal is to create a model that can generalize from unlabeled source domains to semantically retrieve images in an unseen target domain. To address this, we propose a new approach that trains a domain-agnostic expert (DaE) for unsupervised domain-generalizable person ReID. This involves independently training multiple experts to account for label space inconsistencies between source domains. At the same time, the DaE captures domain-generalizable information for testing. Our experiments demonstrate the effectiveness of this method for learning generalizable features under the UDG setting. The results demonstrate the superiority of our method over state-of-the-art techniques. We will make our code and models available for public use. © The Author(s) 2024.

关键词： Domain generalization (DG) Domain-agnostic expert (DaE) Label space inconsistencies Unlabeled source domains

来源：评论

学校读者我要写书评

暂无评论

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Hao, Yijun Yang, Shusen Li, Fang Zhang, Yifan Zhao, Cong Ren, Xuebin Zhao, Peng Xu, Chenren Wang, Shibo Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Xi’an710049 China Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China Peking University School of Computer Science Beijing100871 China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong National Engineering Laboratory for Big Data Analytics Xi'an Jiaotong University Xi'an710049 China

network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports 3.12x more demand when compared to related existing approaches. © 1983-2012 IEEE.

关键词： network topology

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning 30

Few-Shot Semantic Dependency Parsing via Graph Contrastive L...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Li, Bin Fan, Yunlong Sataer, Yikemaiti Shi, Chuanqi Gao, Miao Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education China

ISBN: (纸本)9782493814104

Graph neural networks (GNNs) have achieved promising performance on semantic dependency parsing (SDP), owing to their powerful graph representation learning ability. However, training a high-performing GNN-based model requires a large amount of labeled data and it is prone to over-fitting in the absence of sufficient labeled data. To address this drawback, we propose a syntax-guided graph contrastive learning framework to pre-train GNNs with plenty of unlabeled data and fine-tune pre-trained GNNs with few-shot labeled SDP data. Through extensive experiments conducted on the SemEval-2015 Task 18 English dataset in three formalisms (DM, PAS, and PSD), we demonstrate that our framework achieves promising results when few-shot training samples are available. Furthermore, benefiting from the pre-training process, our framework exhibits notable advantages in the out-of-domain test sets. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-class Bitcoin mixing service identification based on graph classification

引用

Digital Communications and networks 2024年第6期10卷 1881-1893页

作者： Xiaoyan Hu Meiqun Gui Guang Cheng Ruidong Li Hua Wu School of Cyber Science&Engineering Southeast UniversityNanjing 211189China Purple Mountain Laboratories for Network and Communication Security Nanjing 211111China Jiangsu Provincial Engineering Research Center of Security for Ubiquitous Network Nanjing 211189China Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of EducationChina Research Base of International Cyberspace Governance Southeast UniversityNanjing 211189China Institute of Science and Engineering Kanazawa UniversityKakumaKanazawa920-1192Japan

Due to its anonymity and decentralization,Bitcoin has long been a haven for various illegal *** generally legalize illicit funds by Bitcoin mixing ***,it is critical to investigate the mixing services in cryptocurrency anti-money *** studies treat different mixing services as a class of suspicious Bitcoin ***,they are limited by relying on expert experience or needing to deal with large-scale *** far,multi-class mixing service identification has not been explored *** is challenging since mixing services share a similar procedure,presenting no sharp ***,mixing service identification facilitates the healthy development of Bitcoin,supports financial forensics for cryptocurrency regulation and legislation,and provides technical means for fine-grained blockchain *** paper aims to achieve multi-class Bitcoin Mixing Service Identification with a Graph Classification(BMSI-GC)***,BMSI-GC constructs 2-hop ego networks(2-egonets)of mixing services based on their historical ***,it applies graph2vec,a graph classification model mainly used to calculate the similarity between graphs,to automatically extract address features from the constructed ***,it trains a multilayer perceptron classifier to perform classification based on the extracted ***-GC is flexible without handling the full-size network and handcrafting address ***,the differences in transaction patterns of mixing services reflected in the 2-egonets provide adequate information for *** experimental study demonstrates that BMSI-GC performs excellently in multi-class Bitcoin mixing service identification,achieving an average identification F1-score of 95.08%.

关键词： Bitcoin Anti-money laundering Mixing service Ego network Graph classification

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Prequalification Scheme of a Distribution System Operator for Supporting Market Participation of Multiple Distributed Energy Resource Aggregators

IEEE Transactions on Energy Markets, Policy and Regulation

引用

IEEE Transactions on Energy Markets, Policy and Regulation 2024年第4期2卷 465-475页

作者： Jeong, Chang Min Moon, Hee Seung Kim, Seung Wan Seoul National University Electric Power Network Economics Laboratory Department of Electrical and Computer Engineering Seoul08826 Korea Republic of Lawrence Berkeley National Laboratory Energy Technology Area BerkeleyCA94720 United States Chungnam National University Smart Energy Network Design Laboratory Department of Electrical Engineering Daejeon34134 Korea Republic of

This paper addresses the need for distribution system operators to effectively manage uncertainties related to distributed energy resources. We propose a probabilistic approach using Polynomial Chaos Expansion, allowing the operator to balance economic efficiency with system reliability by setting a pre-determined acceptable violation probability. This approach provides efficient computation and high accuracy in the representation of uncertainties. Moreover, we introduce a framework for integrating the capability of distributed energy resources aggregators to manage uncertainties through the uncertainty band commodity. This allows these aggregators to bid for both energy and a specified uncertainty range, thereby contributing to their active role in the management of system uncertainties. Our methodology fairly distributes responsibility for constraint violations among various stakeholders by employing two allocation strategies: one based on Shapley Value and another based on sensitivity factors. The proposed system significantly improves the overall decision-making process by considering both economic and reliability factors within the prequalification process of distribution system operator. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Enhancing Parameter-Efficient Transformers with Contrastive Syntax and Regularized Dropout for Neural Machine Translation 21st

Enhancing Parameter-Efficient Transformers with Contrastive...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Fan, Yunlong Yang, Zhiheng Li, Baixuan Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

ISBN: (纸本)9789819601219

Transformers have significantly improved Neural Machine Translation (NMT) models, accompanied by the inherent space complexity of O(n2). While recent approaches aim to be parameter-efficient, they often exhibit limited generalization capabilities with fewer parameters and decreased performances in longer sentences. To this end, we propose two methods, Syntax-enhanced Contrastive Learning (Syn-CL) and JS divergence-based Regularized Dropout (JSR-Drop) for the cross-layer parameter-sharing Transformer (baseline) in NMT. In Syn-CL, we add the corresponding target-to-source instances for the same batch in an extra bidirectional training phase, and minimize the distances of syntax-enhanced representation between the bilingual sentence-pair while maximizing the ones among others. In JSR-Drop, we refine the regularized dropout strategy with JS divergence, and improve generalization capabilities by reducing Transformers’ inconsistencies between training and inference introduced by dropout. Extensive experiments on six NMT tasks, IWSLT2014 (German↔English) and IWSLT2017 (English↔French and English↔Romanian), show an average BLEU score of 37.55, surpassing the vanilla Transformer and the baseline up to 1.75 BLEU, and outperforming models with 1.5×, 2.0× parameters in translating long sentences. Our code is available at https://***/Anon1214/EnPeNMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive 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：