检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Cao, Yi Xu, Wei-Jie Shen, Yucheng Shi, Weijie Chan, Chi-Min Xu, Jiajie School of Computer Science and Technology Soochow University China State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

The rapid increase in the parameter counts of Large Language Models (LLMs), reaching billions or even trillions, presents significant challenges for their practical deployment, particularly in resource-constrained environments. To ease this issue, we propose PIP (Perturbation-based Iterative Pruning), a novel double-view structured pruning method to optimize LLMs, which combines information from two different views: the unperturbed view and the perturbed view. With the calculation of gradient differences, PIP iteratively prunes those that struggle to distinguish between these two views. Our experiments show that PIP reduces the parameter count by approximately 20% while retaining over 85% of the original model’s accuracy across varied benchmarks. In some cases, the performance of the pruned model is within 5% of the unpruned version, demonstrating PIP’s ability to preserve key aspects of model effectiveness. Moreover, PIP consistently outperforms existing state-of-the-art (SOTA) structured pruning methods, establishing it as a leading technique for optimizing LLMs in environments with constrained resources. Our code is available at: https://***/caoyiiiiii/PIP. 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

On Optimizing Inter-and Intra-Chiplet Interconnection Topologies for Robust Multi-Chiplet Systems

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Wang, Xiaohang Xu, Miao Singh, Amit Kumar Jiang, Yingtao Yang, Mei Zhejiang University State Key Laboratory of Blockchain and Data Security China Hangzhou China South China University of Technology School of Software Engineering China University of Essex School of Computer Science and Electronic Engineering United Kingdom University of Nevada Department of Electrical and Computer Engineering Las Vegas United States

Inter-and intra-chiplet interconnection networks play a vital role in the operation of many core systems made of multiple chiplets. However, these networks are susceptible to faults caused by manufacturing defects and attacks resulting from the malicious insertion of hardware Trojans and backdoors. Unlike conventional fault-tolerant or countermeasure methods, this paper focuses on optimizing network robustness to withstand both faults and attacks, while considering the constraints of chiplet area and power budget. To achieve this, this paper first defines network robustness as a quantifiable measure based on various network parameters, after which an optimization problem is formulated to optimize the robustness of the network topology. To efficiently solve this problem, a reinforcement learning algorithm is proposed. Experimental results demonstrate that the proposed method is capable of generating inter-and intra-chiplet interconnection networks that are significantly more robust than existing topology generation methods. Specifically, the proposed method improves robustness over ButterDonut and Kite, respectively by an average of 10.88% and 14.06% under random faults and by 9.37% and 7.81% under targeted attacks. These experimental results confirm that the proposed method is capable of generating robust inter-and intra-chiplet interconnection networks that can withstand both faults and attacks. By optimizing the network topology’s robustness, it provides a valuable contribution to the design and security of chiplet-based core systems. © 2025 IEEE. All rights reserved

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Validity-Preserving Delta Debugging via Generator Trace Reduction

arXiv

引用

arXiv 2024年

作者： Ren, Luyao Zhang, Xing Hua, Ziyue Jiang, Yanyan He, Xiao Xiong, Yingfei Xie, Tao Key Laboratory of High Confidence Software Technologies Ministry of Education School of Computer Science Peking University Beijing China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China School of Computer and Communication Engineering University of Science and Technology Beijing China

Reducing test inputs that trigger bugs is crucial for efficient debugging. Delta debugging is the most popular approach for this purpose. When test inputs need to conform to certain specifications, existing delta debugging practice encounters a validity problem: it blindly applies reduction rules, producing a large number of invalid test inputs that do not satisfy the required specifications. This overall diminishing effectiveness and efficiency becomes even more pronounced when the specifications extend beyond syntactical structures. Our key insight is that we should leverage input generators, which are aware of these specifications, to generate valid reduced inputs, rather than straightforwardly performing reduction on test inputs. In this paper, we propose a generator-based delta debugging method, namely GReduce, which derives validity-preserving reducers. Specifically, given a generator and its execution, demonstrating how the bug-inducing test input is generated, GReduce searches for other executions on the generator that yield reduced, valid test inputs. The evaluation results on five benchmarks (i.e., graphs, DL models, JavaScript programs, SymPy, and algebraic data types) show that GReduce substantially outperforms state-of-the-art syntax-based reducers including Perses and T-PDD, and also outperforms QuickCheck, SmartCheck, as well as the state-of-the-art choice-sequence-based reducer Hypothesis, demonstrating the effectiveness, efficiency, and versatility of GReduce. Copyright © 2024, The Authors. All rights reserved.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Question Selection for Multi-Modal Code Search Synthesis using Probabilistic Version Spaces

引用

IEEE Transactions on software engineering 2025年

作者： Wu, Jiarong Jiang, Yanyan Wei, Lili Xu, Congying Cheung, Shing-Chi Xu, Chang The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong McGill University Department of Electrical and Computer Engineering Montreal Canada Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing China

Searching the occurrences of specific code patterns (code search) is a common task in software engineering, and programming by example (PBE) techniques have been applied to ease customizing code patterns. However, previous PBE tools only synthesize programs meeting the input-output examples, which may not always align with the user intent. To bridge this gap, this paper proposes Excalibur, a multi-modal (example and natural language description) and interactive synthesizer for code search. Excalibur ensures that the generated programs are correct for the provided examples (soundness) and include the user-intended program (bounded completeness). Furthermore, Excalibur helps the user identify the user-intended program through question-answer interaction. To minimize the required interaction efforts, question selection is crucial. To improve question selection for code search, we propose probabilistic version spaces (ProbVS), in which the user-intended program’s probability is high and others are low. ProbVS combines traditional version spaces for compactly representing extensive programs and large language models (on the user-provided natural language description) for adjusting programs’ probabilities to align with users’ intents. Extensive experiments on a benchmark of 44 tasks demonstrated the effectiveness of Excalibur and ProbVS and demystified how ProbVS affects probability distributions and how the configurable parameters affect ProbVS. © 1976-2012 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Multiple Classifier Aggregation

SSRN

引用

SSRN 2024年

作者： Zheng, Shaifeng Zhu, Qingling Lin, Qiuzhen Liu, Songbai Wong, Ka-Chun Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science City University of Hong Kong Hong Kong

Personalized federated learning (PFL) has garnered attention due to its capability to address statistical heterogeneity among clients. Typically, prevailing PFL methods aggregate a single global model for personalization, which may be inadequate for clients with diverse data distributions. Furthermore, in the local update, each private dataset is used to optimize the model independently, which increases the risk of overfitting the current data distribution and losing previously acquired knowledge, resulting in knowledge forgetting. In this study, personalized federated learning with multiple classifier aggregation is proposed. The method involves splitting the client model into its head and base, then optimizing them respectively using an alternating optimization strategy that first optimizes the head and then the base. Initially, to address the suboptimal model problem, the proposed approach aggregates multiple classifiers using data distribution and employs knowledge distillation to impart positive and negative classifier knowledge for learning the most suitable personalized model head. Additionally, to mitigate knowledge forgetting, a learnable personalization layer is introduced, and hidden loss is utilized to learn the knowledge of the global base and prevent overfitting of the model base. empirical results demonstrate that the proposed method achieves competitive performance across various benchmarks, outperforming the majority of state-of-the-art PFL algorithms. The source code is publicly available at \href{https://***/xiaye-maker/FedMCA}{https://***/xiaye-maker/FedMCA} © 2024, The Authors. All rights reserved.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dynamic Multimodal Optimzation

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dy...

引用

Congress on Evolutionary Computation

作者： Xunfeng Wu Songbai Liu Junkai Ji Lijia Ma Victor C. M. Leung College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases.

关键词： Training Heuristic algorithms Computational modeling Sociology Clustering algorithms Evolutionary computation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

PLAME: Piecewise-Linear Approximate Measure for Additive Kernel SVM (Extended abstract)

PLAME: Piecewise-Linear Approximate Measure for Additive Ker...

引用

International Conference on Data engineering

作者： Tsz Nam Chan Zhe Li Leong Hou U Reynold Cheng Department of Computer Science and Software Engineering Shenzhen University Alibaba Cloud Department of Computer and Information Science State Key Laboratory of Internet of Things for Smart City University of Macau Department of Computer Science and Musketeers Foundation Institute of Data Science The University of Hong Kong

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Additive Kernel SVM has been extensively used in many applications, including human activity detection and pedestrian detection. Since training an additive kernel SVM model is very time-consuming, which is not scalable to largescale datasets, many efficient solutions have been developed in the past few years. However, most of the existing methods normally fail to achieve one of these three important conditions which are (1) low classification error, (2) low memory space, and (3) low training time. In order to simultaneously fulfill these three conditions, we develop the new piecewise-linear approximate measure (PLAME) for training additive kernel SVM models. Experimental results verify that this approach can achieve the best trade-off between accuracy, memory space, and training time compared with different types of state-of-the-art methods.

关键词： Training Support vector machines Additives Pedestrians Accuracy Data engineering Kernel

来源：评论

学校读者我要写书评

暂无评论

Adaptive Deep Learning Model to Enhance Smart Greenhouse Agriculture

引用

computers, Materials & Continua 2023年第11期77卷 2545-2564页

作者： Medhat A.Tawfeek Nacim Yanes Leila Jamel Ghadah Aldehim Mahmood A.Mahmood Department of Computer Science College of Computer and Information SciencesJouf UniversityP.O.Box 72314SkakaSaudi Arabia Department of Computer Science Faculty of Computers and InformationMenoufia UniversityP.O.Box 6121890MenoufiaEgypt Department of Software Engineering College of Computer and Information SciencesJouf UniversityP.O.Box 72314SkakaSaudi Arabia RIADI Laboratory La Manouba UniversityP.O.Box2010ManoubaTunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems and Technology Faculty of Graduate Studies and ResearchCairo UniversityP.O.Box 3753450GizaEgypt

The trend towards smart greenhouses stems from various factors,including a lack of agricultural land area owing to population concentration and housing construction on agricultural land,as well as water *** study proposes building a full farming adaptation model that depends on current sensor readings and available datasets from different agricultural research *** proposed model uses a one-dimensional convolutional neural network(CNN)deep learning model to control the growth of strategic crops,including cucumber,pepper,tomato,and *** proposed model uses the Internet of Things(IoT)to collect data on agricultural operations and then uses this data to control and monitor these operations in real *** helps to ensure that crops are getting the right amount of fertilizer,water,light,and temperature,which can lead to improved yields and a reduced risk of crop *** dataset is based on data collected from expert farmers,the photovoltaic construction process,agricultural engineers,and research *** experimental results showed that the precision,recall,F1-measures,and accuracy of the one-dimensional CNN for the tested dataset were approximately 97.3%,98.2%,97.25%,and 97.56%,*** new smart greenhouse automation system was also evaluated on four crops with a high turnover *** system has been found to be highly effective in terms of crop productivity,temperature management and water conservation.

关键词： Greenhouse wireless sensor network deep learning Internet of Things strategic crops monitoring smart irrigation

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Transportation Systems-Based Machine Learning-Enhanced Traffic Prediction Model using Time Series Analysis and Regression Techniques*

An Intelligent Transportation Systems-Based Machine Learning...

引用

IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA)

作者： Klea Elmazi Donald Elmazi Eugen Musta Fatjon Mehmeti Florenc Hidri Department of Computer Engineering Faculty of Engineering University of Rijeka University Luarasi Tirana Albania Department of Computer Engineering Faculty of Computer Science and IT Artificial Intelligence Laboratory University Metropolitan Tirana Tirana Albania Department of Finance Faculty of Economy Canadian Institute of Technology Tirana Albania Department of Computer Engineering University Metropolitan Tirana Tirana Albania Department of Software Engineering Faculty of Engineering Canadian Institute of Technology Tirana Albania

ISBN: (数字)9798350368130

ISBN: (纸本)9798350368147

Traffic congestion represents a daunting challenge for all facets of urban development, as well as represents a universal problem in all urban areas, to various extents. In recent years, many cities have adopted the use of Intelligent Transport Systems (ITS) to manage traffic congestion. These systems are indeed useful, but they are mainly geared to predict real-time traffic congestion, yielding to a certain short-sightedness in our prediction model. Through the use of Time Series Analysis, and Regression models for traffic congestion prediction, we posit that we can address the issue. The data that these models were trained on derives from two datasets, namely a dataset from Kaggle and another from the road traffic footage of Tirana. The data then points to Gated Recurrent Units (GRU) being a more accurate time series category, and Support Vector Regression (SVR) to be a better performer than linear regression.

关键词： Support vector machines Analytical models Technological innovation Time series analysis Urban areas Transportation Predictive models

来源：评论

学校读者我要写书评

暂无评论

Enabling Generalized Zero-Shot Vulnerability Classification

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Hu, Jinghao Guo, Jinsong Luo, Chen Hu, Yang Lanzinger, Matthias Li, Zhanshan Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Software Changchun130012 China University College London Department of Computer Science United Kingdom Amazon United States United Kingdom University of Oxford Department of Computer Science United Kingdom Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Changchun130012 China

Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This paper introduces VulnSense, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem. VulnSense learns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically, VulnSense learns from three main resources: (1) seen classes with labeled code instances;(2) descriptions of these seen classes;and (3) descriptions of "unseen"classes which have no labeled instances. Our experiments underscore VulnSense's superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities. VulnSense demonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work. © 2004-2012 IEEE.

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：