检索结果-内蒙古大学图书馆

Binary relevance for multi-label learning： an overview

Frontiers of computer Science 2018年第2期12卷 191-202页

作者： Min-Ling ZHANG Yu-Kun LI Xu-Ying LIU Xin GENG School of Computer Science and Engineering Southeast University Nanjing 210096 China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China Collaborative Innovation Center for Wireless Communications Technology Nanjing 211100 China

Multi-label learning deals with problems where each example is represented by a single instance while being associated with multiple class labels simultaneously. Binary relevance is arguably the most intuitive solution for learning from multi-label examples. It works by decomposing the multi-label learning task into a number of independent binary learning tasks （one per class label）. In view of its potential weakness in ignoring correlations between labels, many correlation-enabling extensions to binary relevance have been proposed in the past decade. In this paper, we aim to review the state of the art of binary relevance from three perspectives. First, basic settings for multi-label learning and binary relevance solutions are briefly summarized. Second, representative strategies to provide binary relevance with label correlation exploitation abilities are discussed. Third, some of our recent studies on binary relevance aimed at issues other than label correlation exploitation are introduced. As a conclusion, we provide suggestions on future research directions.

关键词： machine learning multi-label learning binary relevance label correlation class-imbalance relative labeling-importance

来源：评论

学校读者我要写书评

暂无评论

Variable strength combinatorial testing of concurrent programs

引用

Frontiers of computer Science 2016年第4期10卷 631-643页

作者： Xiaofang QI Jun HE Peng WANG Huayang ZHOU School of Computer Science and Engineering Southeast University Nanjing 211189 China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing 211189 China NARI Relays Electric Cooperation Nanjing 211102 China

Reachability testing is an important approach to testing concurrent programs. It generates and exercises syn- chronization sequences automatically and on-the-fly without saving any test history. Existing reach, ability testing can be classified into exhaustive and t-way testing. Exhaustive testing is impractical in many cases whilie t-way testing may decrease the capability of fault detection in some cases. In this paper, we present a variable strengda reachability testing strategy, which adopts the dynamic framework of reachability testing and uses a variable strength combinatorial strategy. Different parameter groups are provided with different covering strength. Variable strength testing covers no t-way combinations but the necessary combinations of parameters having mutual interactions in a concurrent program. It is more reasonable than t-way testing because uniform interactions between parameters do not often exist in concurrent systems. We propose a merging algorithm that implements the variable strength combinatorial testing strategy and conduct our experiment on several concurrent programs. The experimental results indicate that our variable strength reachability testing reaches a good tradeoff between the effectiveness and efficiency. It can keep the same capability of fault detection as exhaustive reachability testing while substantially reducing the number of synchronization sequences and decreasing the execution time in most cases.

关键词： software testing variable strength combinatorial testing concurrency testing reachability testing

来源：评论

学校读者我要写书评

暂无评论

Restrictive mechanism of flow control among non-cooperative Internet users

引用

Science China(information Sciences) 2011年第1期54卷 12-22页

作者： TAO Jun1,2,ZHONG Xiao1,2 & LU YiFei1,2 1key laboratory of computer network and information integration,southeast university, Ministry of Education,Nanjing 210096,China 2School of computer Science and Engineering,southeast university,Nanjing 210096,China 1. Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing 210096 China2. School of Computer Science and Engineering Southeast University Nanjing 210096 China

The flow and congestion control methods based on one-shot game model with non-cooperative game theory can explain the non-cooperative behavior of Internet ***,the low effciency of equilibrium solutions affects their *** the behavior of flow and congestion control based on infinitely repeated game models is addressed;the repeated and infinitely repeated flow and congestion control game model is presented; the existence and optimization of the Nash equilibrium point are proved;the discount factor in repeated game is discussed;the punishment and threat strategy to users'misbehavior is studied in N-users infinitely flow control game;the punishment restrictive method of users'behavior is designed in infinitely and finitely games;finally,a flow control algorithm based on repeated game,FCAR,is provided based on the conclusions of repeated game *** results of experiment and simulation show that FCAR algorithm could regularize and restrict users' misbehavior *** algorithm can also make non-cooperative Internet users achieve cooperation in order to optimize the utility of the whole flow and congestion control system.

关键词： Nash equilibrium utility infinitely and finitely repeated game flow and congestion control

来源：评论

学校读者我要写书评

暂无评论

information Leakage Problem in High-Capacity Quantum Secure Communication with Authentication Using Einstein-Podolsky-Rosen Pairs

引用

Chinese Physics Letters 2016年第7期33卷 14-15页

作者：刘志昊陈汉武刘文杰 School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration(Ministry of Education) Southeast University Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information TechnologyUniversity of Technology Sydney School of Computer and Software Nanjing University of Information Science & Technology

The information leakage problem often exists in bidirectional quantum secure direct communication or quantum dialogue. In this work, we find that this problem also exists in the one-way quantum secure communication protocol [Chin. Phys. Lett. 32 （2015） 050301]. Specifically, the first bit of every four-bit message block is leaked out without awareness. A way to improve the information leakage problem is given.

关键词： in or of is that with

来源：评论

学校读者我要写书评

暂无评论

LIFT+: Lightweight Fine-Tuning for Long-Tail Learning

arXiv

引用

arXiv 2025年

作者： Shi, Jiang-Xin Wei, Tong Li, Yu-Feng National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Artificial Intelligence Nanjing University Nanjing210023 China School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remains unexplored. In this work, we disclose that existing paradigms exhibit a profound misuse of fine-tuning methods, leaving significant room for improvement in both efficiency and accuracy. Specifically, we reveal that heavy fine-tuning (fine-tuning a large proportion of model parameters) can lead to non-negligible performance deterioration on tail classes, whereas lightweight fine-tuning demonstrates superior effectiveness. Through comprehensive theoretical and empirical validation, we identify this phenomenon as stemming from inconsistent class conditional distributions induced by heavy fine-tuning. Building on this insight, we propose LIFT+, an innovative lightweight fine-tuning framework to optimize consistent class conditions. Furthermore, LIFT+ incorporates semantic-aware initialization, minimalist data augmentation, and test-time ensembling to enhance adaptation and generalization of foundation models. Our framework provides an efficient and accurate pipeline that facilitates fast convergence and model compactness. Extensive experiments demonstrate that LIFT+ significantly reduces both training epochs (from ∼100 to ≤15) and learned parameters (less than 1%), while surpassing state-of-the-art approaches by a considerable margin. The source code is available at https://***/shijxcs/LIFT-plus. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional Classification via Selective Feature Augmentation

引用

Machine Intelligence Research 2022年第1期19卷 38-51页

作者： Bin-Bin Jia Min-Ling Zhang School of Computer Science and Engineering Southeast UniversityNanjing 210096China College of Electrical and Information Engineering Lanzhou University of TechnologyLanzhou 730050China Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of EducationChina

In multi-dimensional classification(MDC), the semantics of objects are characterized by multiple class spaces from different dimensions. Most MDC approaches try to explicitly model the dependencies among class spaces in output space. In contrast, the recently proposed feature augmentation strategy, which aims at manipulating feature space, has also been shown to be an effective solution for MDC. However, existing feature augmentation approaches only focus on designing holistic augmented features to be appended with the original features, while better generalization performance could be achieved by exploiting multiple kinds of augmented *** this paper, we propose the selective feature augmentation strategy that focuses on synergizing multiple kinds of augmented ***, by assuming that only part of the augmented features is pertinent and useful for each dimension′s model induction, we derive a classification model which can fully utilize the original features while conduct feature selection for the augmented features. To validate the effectiveness of the proposed strategy, we generate three kinds of simple augmented features based on standard k NN, weighted k NN, and maximum margin techniques, respectively. Comparative studies show that the proposed strategy achieves superior performance against both state-of-the-art MDC approaches and its degenerated versions with either kind of augmented features.

关键词： Machine learning multi-dimensional classification feature augmentation feature selection class dependencies

来源：评论

学校读者我要写书评

暂无评论

Transfer synthetic over-sampling for class-imbalance learning with limited minority class data

引用

Frontiers of computer Science 2019年第5期13卷 996-1009页

作者： Xu-Ying LIU Sheng-Tao WANG Min-Ling ZHANG School of Computer Science and Engineering Southeast University Nanjing 210096 China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing 210096 China Collaborative Innovation Center for Wireless Communications Technology Nanjing 210096 China

The problem of limited minority class data is encountered in manyclass imbalanced applications, but has received little attention. Synthetic over-sampling, as popular class-imbalance learning methods, could introduce much noise when minority class has limited data since the synthetic samples are not i.i.d. samples of minority class. Mos t sophisticated synthetic sampling methods tackle this problem by denoising or generating samples more consistent with ground-truth data distribution. But their assumptions about true noise or ground-truth data distribution may not hold. To adapt synthetic sampling to the problem of limited minority class data, the proposed Traso framework treats synthetic minority class samples as an additional data source, and exploits transfer learning to transfer knowledge from them to minority class. As an implementation, TrasoBoost method firstly generates synthetic samples to balance class sizes. Then in each boosting iteration, the weights of synthetic samples and original data decrease and increase respectively when being misclassified, and remain unchanged otherwise. The misclassified synthetic samples are potential noise, and thus have smaller influence in the following iterations. Besides, the weights of minority class instances have greater change than those of majority class instances to be more influential. And only original data are used to estimate error rate to be immune from noise. Finally, since the synthetic samples are highly related to minority class, all of the weak learners are aggregated for prediction. Experimental results show TrasoBoost outperforms many popular class-imbalance learning methods.

关键词： machine learning data mining class imbalance over sampling boosting transfer learning

来源：评论

学校读者我要写书评

暂无评论

Precise slicing of interprocedural concurrent programs

引用

Frontiers of computer Science 2017年第6期11卷 971-986页

作者： Xiaofang QI Zhenliang JIANG School of Computer Science and Engineering Southeast University Nanjing 211189 China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing 211189 China China Huawei Technologies Co. Ltd Nanjing 210012 China

Program slicing is an effective technique for an- alyzing concurrent programs. However, when a conventional closure-based slicing algorithm for sequential programs is ap- plied to a concurrent interprocedural program, the slice is usually imprecise owing to the intransitivity of interference dependence. Interference dependence arises when a state- ment uses a variable defined in another statement executed concurrently. In this study, we propose a global dependence analysis approach based on a program reachability graph, and construct a novel dependence graph called marking-statement dependence graph （MSDG）, in which each vertex is a 2-tuple of program state and statement. In contrast to the conven- tional program dependence graph where the vertex is a state- ment, the dependence relation in MSDG is transitive. When traversing MSDG, a precise slice will be obtained. To en- hance the slicing efficiency without loss of precision, our slic- ing algorithm adopts a hybrid strategy. The procedures con- taining interaction statements between threads are inlined and sliced by the slicing algorithm based on program reachability graphs while allowing other procedures to be sliced as se- quential programs. We have implemented our algorithm and three other representative slicing algorithms, and conducted an empirical study on concurrent Java programs. The exper- imental results show that our algorithm computes more pre- cise slices than the other algorithms. Using partial-order re- duction techniques, which are effective for reducing the size of a program reachability graph without loss of precision, ouralgorithm is optimized, thereby improving its performance to some extent.

关键词： program slicing concurrent programs reacha-bility analysis context sensitivity dependence analysis

来源：评论

学校读者我要写书评

暂无评论

Clustering algorithm design optimization and routing protocols based on leach

引用

Journal of Computational information Systems 2015年第12期11卷 4343-4352页

作者： Wang, Honglin Shen, Jun School of Computer Science and Engineering of Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration of Southeast University Nanjing China School of Electronic & Information Engineering of Nanjing University of Information Science & Technology Nanjing China

Special long-distance communication environment, the standard protocol is optimized for Leach mine tunnel, an improved protocol TLeach base on Leach. Including: optimized clustering scheme, we propose a clustering method of determining the number of optimization;and the cluster head directly communicate with the base station is adjusted to the cluster head by routing forwards the data to the base station;Cluster head to the base station using the routing depth or breadth-first search algorithm to form, in order to find the shortest path from the source node to the base station node in order to Reduce network energy consumption and prolong the survival time of the network. Experimental results show that the optimized protocol has better stability, significantly extending the lifetime of the network. ©, 2015, Binary information Press. All right reserved.

关键词： Base stations

来源：评论

学校读者我要写书评

暂无评论

Non-uniform spacing clustering interval multi-hop routing leach algorithms for wireless sensor network

引用

Journal of Computational information Systems 2015年第10期11卷 3613-3622页

作者： Wang, Honglin Shen, Jun School of computer Science and Engineering of Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration of Southeast University Nanjing China School of Electronic & Information Engineering of Nanjing University of Information Science & Technology Nanjing China

For mine tunnel distances ribbon special communications environment, proposed a non-uniform spacing clustering multi-hop routing algorithm. The core idea is: to change the cluster head election strategy, considering the position of the node, energy and networks, such as the number of current network cluster heads forming weighting function, optimize partitions, away from the base station to partition larger than the nearby district comprehensive node energy consumption;the original single-hop communication mode optimized for single-hop and multi-hop mixed-mode, single-hop and multi-hop network choices to lower the overall energy consumption of the standard;in order to protect the communication mode of the multi-hop cluster heads near the base station using the multi-hop mode interval, so that a larger area of nodes sharing a base station adjacent to a node energy consumption. Experiments show that the protocol has better stability and significantly extend the life cycle of the network. ©, 2015, Binary information Press. All right reserved.

关键词： Base stations

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：