检索结果-内蒙古大学图书馆

Partial multi-label learning via label-specific feature corrections

Science China(Information Sciences) 2025年第3期68卷 95-109页

作者： Jun-Yi HANG Min-Ling ZHANG School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education

Partial multi-label learning（PML） allows learning from rich-semantic objects with inaccurate annotations, where a set of candidate labels are assigned to each training example but only some of them are valid. Existing approaches rely on disambiguation to tackle the PML problem, which aims to correct noisy candidate labels by recovering the ground-truth labeling information ahead of prediction model induction. However, this dominant strategy might be suboptimal as it usually needs extra assumptions that cannot be fully satisfied in real-world scenarios. Instead of label correction, we investigate another strategy to tackle the PML problem, where the potential ambiguity in PML data is eliminated by correcting instance features in a label-specific manner. Accordingly, a simple yet effective approach named PASE, i.e., partial multi-label learning via label-specific feature corrections, is proposed. Under a meta-learning framework, PASElearns to exert label-specific feature corrections so that potential ambiguity specific to each class label can be eliminated and the desired prediction model can be induced on these corrected instance features with the provided candidate labels. Comprehensive experiments on a wide range of synthetic and real-world data sets validate the effectiveness of the proposed approach.

关键词： machine learning multi-label learning partial multi-label learning label-specific features feature correction

来源：评论

学校读者我要写书评

暂无评论

Meta label associated loss for fine-grained visual recognition

引用

Science China(Information Sciences) 2024年第6期67卷 230-247页

作者： Yanchao LI Fu XIAO Hao LI Qun LI Shui YU School of Computer Science Nanjing University of Posts and Telecommunications School of Network Engineering Zhoukou Normal University School of Computer Science University of Technology Sydney

Recently, intensive attempts have been made to design robust models for fine-grained visual recognition, most notably are the impressive gains for training with noisy labels by incorporating a reweighting strategy into a meta-learning framework. However, it is limited to up or downweighting the contribution of an instance for label reweighting approaches in the learning process. To solve this issue, a novel noise-tolerant method with auxiliary web data is proposed. Specifically, first, the associations made from embeddings of well-labeled data with those of web data and back at the same class are measured. Next, its association probability is employed as a weighting fusion strategy into angular margin-based loss, which makes the trained model robust to noisy datasets. To reduce the influence of the gap between the well-labeled and noisy web data, a bridge schema is proposed via the corresponding loss that encourages the learned embeddings to be coherent. Lastly, the formulation is encapsulated into the meta-learning framework, which can reduce the overfitting of models and learn the network parameters to be noise-tolerant. Extensive experiments are performed on benchmark datasets, and the results clearly show the superiority of the proposed method over existing state-of-the-art approaches.

关键词： label associated loss weighting noisy samples fine-grained visual recognition noise-tolerant learning meta-learning

来源：评论

学校读者我要写书评

暂无评论

Secure beamforming and deployment design for rate-splitting multiple access-based UAV communications

引用

Science China(Information Sciences) 2025年第1期68卷 342-356页

作者： Bing WANG Xiaofeng TAO Shujun HAN Huici WU Kai YANG Zhu HAN National Engineering Research Center of Mobile Network Technologies Beijing University of Posts and Telecommunications Peng Cheng Laboratory Department of Electrical and Computer Engineering University of Houston

Rate-splitting multiple access(RSMA) has recently gained attention as a potential robust multiple access(MA)scheme for upcoming wireless networks. Given its ability to efficiently utilize wireless resources and design interference management strategies, it can be applied to unmanned aerial vehicle(UAV) networks to provide convenient services for large-scale access ground users. However, due to the line-of-sight(LoS) broadcast nature of UAV transmission, information is susceptible to eavesdropping in RSMA-based UAV networks. Moreover, the superposition of signals at the receiver in such networks becomes complicated. To cope with the challenge, we propose a two-user multi-input single-output(MISO) RSMA-based UAV secure transmission framework in downlink communication networks. In a passive eavesdropping scenario, our goal is to maximize the sum secrecy rate by optimizing the transmit beamforming and deployment location of the UAV-base station(UAV-BS),while considering quality-of-service(QoS) constraints, maximum transmit power, and flight space limitations. To address the non-convexity of the proposed problem, the optimization problem is first decoupled into two subproblems. Then, the successive convex approximation(SCA) method is employed to solve each subproblem using different propositions. In addition, an alternating optimization(AO)-based location RSMA(L-RSMA) beamforming algorithm is developed to implement joint optimization to obtain the suboptimal solution. Numerical results demonstrate that(1) the proposed L-RSMA scheme yields a28.97% higher sum secrecy rate than the baseline L-space division multiple access(SDMA) scheme;(2) the proposed L-RSMA scheme improves the security performance by 42.61% compared to the L-non-orthogonal multiple access(NOMA) scheme.

关键词： rate-splitting multiple access UAV communication precoding optimization deployment location physical layer security

来源：评论

学校读者我要写书评

暂无评论

LT-DBFT: A Hierarchical Blockchain Consensus Using Location and Trust in IoT

引用

IEEE Internet of Things Journal 2025年第12期12卷 19574-19589页

作者： Wang, Yang Xing, Xiaofei Li, Peiqiang Wang, Guojun Guangzhou University School of Computer Science and Cyber Engineering Guangzhou510006 China Guangzhou University School of Computer Science and Network Engineering Guangzhou510006 China

The exponential growth of IoT devices has led to the proposal of edge computing for data processing. The decentralized nature of edge computing servers and IoT devices makes blockchain ideal for connecting IoT users and servers. The consensus protocol, a core technology in blockchain, ensures node agreement and operational efficiency. However, as node numbers increase and spread geographically, traditional consensus protocols face deployment challenges, significantly reducing efficiency. To address this, we propose a hierarchical blockchain consensus protocol based on geographic location and a trust model called Location and Trust Delegated-BFT (LT-DBFT). This protocol reduces global communication delays caused by wide geographic distribution by assigning consensus nodes to different clusters based on their locations. A trust model is also designed to elect active nodes for consensus voting, thereby reducing the consensus overhead within clusters. Subsequently, the primary nodes of each cluster form a global shared layer to achieve the final ordering and execution of transactions. Through theoretical and experimental analysis, our scheme demonstrates lower latency and higher throughput performance than traditional PBFT and GeoBFT, making it more suitable for efficient deployment in large-scale and geographically widespread IoT environments. © 2014 IEEE.

关键词： Internet of Things Blockchains Security Protocols Consensus protocol Complexity theory Fault tolerant systems Fault tolerance Servers Scalability

来源：评论

学校读者我要写书评

暂无评论

Multi-instance partial-label learning: towards exploiting dual inexact supervision

引用

Science China(Information Sciences) 2024年第3期67卷 48-61页

作者： Wei TANG Weijia ZHANG Min-Ling ZHANG School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Physical Sciences The University of Newcastle

Weakly supervised machine learning algorithms are able to learn from ambiguous samples or labels, e.g., multi-instance learning or partial-label learning. However, in some real-world tasks, each training sample is associated with not only multiple instances but also a candidate label set that contains one groundtruth label and some false positive labels. Specifically, at least one instance pertains to the ground-truth label while no instance belongs to the false positive labels. In this paper, we formalize such problems as multi-instance partial-label learning(MIPL). Existing multi-instance learning algorithms and partial-label learning algorithms are suboptimal for solving MIPL problems since the former fails to disambiguate a candidate label set, and the latter cannot handle a multi-instance bag. To address these issues, a tailored algorithm named MIPLGP, i.e., multi-instance partial-label learning with Gaussian processes, is *** first assigns each instance with a candidate label set in an augmented label space, then transforms the candidate label set into a logarithmic space to yield the disambiguated and continuous labels via an exclusive disambiguation strategy, and last induces a model based on the Gaussian processes. Experimental results on various datasets validate that MIPLGP is superior to well-established multi-instance learning and partial-label learning algorithms for solving MIPL problems.

关键词： machine learning multi-instance partial-label learning multi-instance learning partial-label learning Gaussian processes

来源：评论

学校读者我要写书评

暂无评论

Foundation models for topic modeling: a case study

引用

Frontiers of computer Science 2025年第2期19卷 129-131页

作者： Han ZENG Jia-Ming SUN Chun-Shu LI Zhuying LI Tong WEI School of Computer Science and Engineering Southeast UniversityNanjing 210096China Key Laboratory of Computer Network and Information Integration Southeast UniversityNanjing 210096China

1 Introduction In Natural Language Processing(NLP),topic modeling is a class of methods used to analyze and explore textual corpora,i.e.,to discover the underlying topic structures from text and assign text pieces to different *** NLP,a topic means a set of relevant words appearing together in a particular pattern,representing some specific *** is beneficial for tracking social media trends,constructing knowledge graphs,and analyzing writing *** modeling has always been an area of extensive research in *** methods like Latent Semantic Analysis(LSA)and Latent Dirichlet Allocation(LDA),based on the“bag of words”(BoW)model,often fail to grasp the semantic nuances of the text,making them less effective in contexts involving polysemy or data noise,especially when the amount of data is small.

关键词： words semantic textual

来源：评论

学校读者我要写书评

暂无评论

FSCIL-EACA: Few-Shot Class-Incremental Learning network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

引用

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education Department Information Network Engineering Research Center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Training Adaptation models Visualization Image recognition Prototypes Self-supervised learning Power capacitors

来源：评论

学校读者我要写书评

暂无评论

Conservative Design with High-Performance COTS Architectures - Beyond Traditional Approaches 29

Conservative Design with High-Performance COTS Architectures...

引用

29th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2024

作者： Hapka, Robin Ernst, Rolf Institute of Computer and Network Engineering Tu Braunschweig Germany

ISBN: (纸本)9798350361230

Safety-critical industrial systems are subject to many stringent requirements, including non-functional design constraints that are essential for robustness, reliability, and safety. System timing is often treated as an afterthought, even though data age, race conditions, or missed deadlines can affect functional safety. This challenge has been addressed in real-time system design, but the situation has worsened in recent system designs. Many applications require high performance to achieve behavioral safety goals, i.e., safety of intended functionality, using complex heterogeneous architectures with multi-level memory, interconnected chiplets, and accelerators based on the latest technologies. Machine learning applications in factory automation, robotics, and autonomous systems are important examples. The timing of such architectures is heavily influenced by the physical effects of temperature control and chip variations, including aging, leading to even more complex chip-specific software execution timing. The paper shows that identical chips differ in their timing behavior, and that most of the timing variation of a single chip can be effectively modeled using additive white Gaussian noise. We explain how such timing behavior can be exploited in high-assurance design for safety and reliability, following established reliability analysis, test, and redundancy techniques. © 2024 IEEE.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Representation Spatial-Temporal Graph Convolutional networks for network Traffic Prediction

引用

IEEE Internet of Things Journal 2025年第13期12卷 23085-23099页

作者： Yang, Yang He, Yechen Zhao, Binnan Wu, Celimuge Gao, Zhipeng Rui, Lanlan Beijing University of Posts and Telecommunications School of Computer Science Beijing100876 China University of Electro-Communications Department of Computer and Network Engineering Tokyo1828585 Japan

With the rapid proliferation of the Internet of Things, network traffic prediction has become crucial for intelligent network management, enabling more reliable and flexible services for a vast array of IoT devices and applications. The heterogeneous and dynamic nature of IoT networks introduces complex spatial relations and underlying periodic dependencies in spatial-temporal graphs that existing methods struggle to model effectively. In this paper, we propose Multi-Representation Spatial-Temporal Graph Convolutional networks (MRSTGCN), a novel unified framework specifically designed to address these challenges. MRSTGCN integrates a Multi-Representation Graph Convolutional network (MRGCN) module to model node heterogeneity and complex traffic propagation, and two complementary embedding modules - Historical Embedding and Temporal Embedding - to capture and fuse periodic dependencies across different fine-grained temporal cycles. Extensive experiments are conducted on two network traffic datasets, and the results demonstrate that MRSTGCN achieves state-of-the-art performance with obvious improvements in MAE, RMSE and MAPE on three prediction horizons. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

YOLO-CORE: Contour Regression for Efficient Instance Segmentation

引用

Machine Intelligence Research 2023年第5期20卷 716-728页

作者： Haoliang Liu Wei Xiong Yu Zhang School of Computer Science and Engineering and the Key Laboratory of Computer Network and Information Integration(Ministry of Education) Southeast UniversityNanjing 211189China

Instance segmentation has drawn mounting attention due to its significant ***,high computational costs have been widely acknowledged in this domain,as the instance mask is generally achieved by pixel-level *** this paper,we present a conceptually efficient contour regression network based on the you only look once(YOLO)architecture named YOLO-CORE for instance *** mask of the instance is efficiently acquired by explicit and direct contour regression using our designed multiorder constraint consisting of a polar distance loss and a sector *** proposed YOLO-CORE yields impressive segmentation performance in terms of both accuracy and *** achieves 57.9%AP@0.5 with 47 FPS(frames per second)on the semantic boundaries dataset(SBD)and 51.1%AP@0.5 with 46 FPS on the COCO *** superior performance achieved by our method with explicit contour regression suggests a new technique line in the YOLO-based image understanding ***,our instance segmentation design can be flexibly integrated into existing deep detectors with negligible computation cost(65.86 BFLOPs(billion float operations per second)to 66.15 BFLOPs with the YOLOv3 detector).

关键词： computer vision instance segmentation object shape prediction contour regression polar distance.

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：