检索结果-内蒙古大学图书馆

丛书名： SpringerBriefs in Computer science

1000年

作者： Yu Zhou Xiao Zhang Sam Kwong

ISBN: (数字)9789819626878

ISBN: (纸本)9789819626861

This book focuses on the modelling and optimization aspects of the feature selection problem through computational intelligence methods in complex, high-dimensional supervised machine learning. To aid readers in conducting research in this field, it covers fundamental concepts and state-of-the-art algorithms. This book also provides a detailed insight into applying these algorithms into real-world applications. The authors begin by introducing the definition high-dimensional machine learning (ML) problems and the challenges they pose. Subsequently, they delve into dimension reduction methods for high-dimensional ML, including global and local feature selection (FS) techniques. This book also comprehensively presents computational intelligence methods such as evolutionary computation and deep neural networks for FS, supported by both theoretical and empirical evidence. Furthermore, this book explores real-world scenario applications involving high-dimensional ML, particularly in the context of smart cities, bioinformatics and industrial informatics. This book is a suitable read for postgraduates and researchers who are interested in the research areas of computational intelligence, soft computing, machine learning and deep learning. Professionals and practitioners within these related fields will also benefit from this book.

关键词： Artificial Intelligence Machine Learning Computers and Society Theory of Computation Computer Applications

来源：评论

学校读者我要写书评

暂无评论

Conceptual Modeling for Advanced Application Domains 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： Shan Wang Katsumi Tanaka Shuigeng Zhou Tok-Wang Ling Jihong Guan Dong-qing Yang Fabio Grandi Eleni E. Mangina Il-Yeol Song Heinrich C. Mayr

来源：评论

学校读者我要写书评

暂无评论

Interpreting Deep Forest through Feature Contribution and MDI Feature Importance

引用

ACM Transactions on Knowledge Discovery from data 1000年

作者： Yi-Xiao He Shen-Huan Lyu Yuan Jiang National Key Laboratory for Novel Software Technology and School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology of Ministry of Water Resources and College of Computer Science and Software Engineering Hohai University China

Deep forest is a non-differentiable deep model that has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks. Many of the application fields prefer explainable models, such as random forests with feature contributions that can provide a local explanation for each prediction, and Mean Decrease Impurity (MDI) that can provide global feature importance. However, deep forest, as a cascade of random forests, possesses interpretability only at the first layer. From the second layer on, many of the tree splits occur on the new features generated by the previous layer, which makes existing explaining tools for random forests inapplicable. To disclose the impact of the original features in the deep layers, we design a calculation method with an estimation step followed by a calibration step for each layer, and propose our feature contribution and MDI feature importance calculation tools for deep forest. Experimental results on both simulated data and real-world data verify the effectiveness of our methods.

关键词： deep forest feature importance interpretability

来源：评论

学校读者我要写书评

暂无评论

Feature Disentanglement Based Heterogeneous Defect Prediction

引用

ACM Transactions on software engineering and Methodology 1000年

作者： Xu Yu Jiaqi Yan Qinqin Gao Qinglong Peng Bin Yu Junwei Du Ying Xing Dunwei Gong Qingdao Institute of Software China University of Petroleum East China) Qingdao China College of Computer Science and Technology China University of Petroleum East China) Qingdao China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software China University of Petroleum East China) Qingdao China School of Data Science Qingdao University of Science and Technology Qingdao China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Changchun China School of Data Science Qingdao University of Science and Technology Qingdao China School of Computer and Information Technology Beijing Jiaotong University Beijing China School of Data Science Qingdao University of Science and TechnologyQingdao China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Yunnan Key Laboratory of Software Engineering Kunming China College of Automation and Electronic Engineering Qingdao University of Science and Technology Qingdao China

Cross-project defect prediction (CPDP) utilizes the existing labeled data in the source project to assist with the prediction of unlabeled projects in the target dataset, which effectively improves the prediction performance and has become a research hotspot in software engineering. At present, CPDP can be categorized into homogeneous cross-project defect prediction and heterogeneous cross-project defect prediction (HDP), in which HDP doesn’t require that the source project and the target project have the same feature space, thus, it is more widely used in the actual CPDP. Most of current HDP methods map the original features to the latent feature space and reduce the inter-project variation by transferring domain-independent features, but the transferring process ignores the use of domain-related features, which affects the prediction performance of the model. Moreover, the mapped latent features are not conducive to the model’s interpretability. Based on these, this paper proposes a heterogeneous defect prediction method based on feature disentanglement (FD-HDP). We disentangle the features using domain-related and domain-independent feature extractors, respectively, to improve the interpretability of the model by maximizing the domain adversarial loss during training and guiding the feature extractors to produce accurate domain-related and domain-independent features. The weighted sum of the prediction results from domain-related and domain-independent predictors is used as the final prediction result of the project during the prediction process, which realizes the combination of domain-independent and domain-related features and effectively improves the prediction performance. In this paper, we conducted experiments using four publicly available defect datasets to construct heterogeneous scenarios. The results demonstrate that the FD-HDP model shows significant advantages over state-of-the-art methods in six metrics.

关键词： Heterogeneous Defect Prediction Feature Disentanglement Domain-related Features Domain-independent Features

来源：评论

学校读者我要写书评

暂无评论

Secure Collaborative Learning for Self-Adaptive Systems on Connected Autonomous Vehicles

引用

ACM Transactions on Autonomous and Adaptive Systems 1000年

作者： Xiaotong Wu Yuwen Liu Xiaoxiao Chi Rong Jiang Xiaokang Zhou Wajid Rafique Maqbool Khan Alibaba Business School Hangzhou Normal University China College of Computer Science and Technology China University of Petroleum (East China) China Department of Computing Macquarie University Australia Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics China Faculty of Business Data Science Kansai University Japan and RIKEN Center for Advanced Intelligence Project Japan Department of Electrical and Software Engineering University of Calgary Canada Software Competence Center Hagenberg Austria

As an advanced carrier of on-board sensors, connected autonomous vehicle (CAV) can be viewed as an aggregation of self-adaptive systems with monitor-analyze-plan-execute (MAPE) for vehicle-related services. Meanwhile, machine learning (ML) has been applied to enhance analysis and plan functions of MAPE so that self-adaptive systems have optimal adaption to changing conditions. However, most of ML-based approaches don’t utilize CAVs’ connectivity to collaboratively generate an optimal learner for MAPE, because of sensor data threatened by gradient leakage attack (GLA). In this article, we first design an intelligent architecture for MAPE-based self-adaptive systems on Web 3.0-based CAVs, in which a collaborative machine learner supports the capabilities of managing systems. Then, we observe by practical experiments that importance sampling of sparse vector technique (SVT) approaches cannot defend GLA well. Next, we propose a fine-grained SVT approach to secure the learner in MAPE-based self-adaptive systems, that uses layer and gradient sampling to select uniform and important gradients. At last, extensive experiments show that our private learner spends a slight utility cost for MAPE (e.g., \(0.77\%\) decrease in accuracy) defending GLA and outperforms the typical SVT approaches in terms of defense (increased by \(10\%\sim 14\%\) attack success rate) and utility (decreased by \(1.29\%\) accuracy loss).

关键词： collaborative learning optimal adaption vehicle application data security self-adaptive system

来源：评论

学校读者我要写书评

暂无评论

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning

引用

ACM Transactions on software engineering and Methodology 1000年

作者： Boyang Yang Haoye Tian Jiadong Ren Hongyu Zhang Jacques Klein Tegawende Bissyande Claire Le Goues Shunfu Jin School of Information Science and Engineering Yanshan University China School of Computing and Information Systems University of Melbourne Australia School of Big Data and Software Engineering Chongqing University China SnT University of Luxembourg Luxembourg School of Computer Science Carnegie Mellon University USA

Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models (LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair, we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective ➊), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective ➋). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality *** apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.

关键词： Program Repair Fine-tuning Large Language Model Open Source

来源：评论

学校读者我要写书评

暂无评论

Hardening Active Directory Graphs via Evolutionary Diversity Optimization based Policies

引用

ACM Transactions on Evolutionary Learning and Optimization 1000年

作者： Diksha Goel Max Ward Aneta Neumann Frank Neumann Hung Nguyen Mingyu Guo CSIRO’s Data61 Australia Department of Computer Science and Software Engineering University of Western Australia Australia School of Computer and Mathematical Sciences University of Adelaide Australia

Active Directory (AD) is the default security management system for Windows domain networks. An AD environment can be described as a cyber-attack graph, with nodes representing computers, accounts, etc., and edges indicating existing accesses or known exploits that enable attackers to move from one node to another. This paper explores a Stackelberg game model between one attacker and one defender on an AD attack graph. The attacker’s goal is to maximize their chances of successfully reaching the destination before getting detected. The defender’s aim is to block a constant number of edges to minimize the attacker’s chance of success. The paper shows that the problem is #P-hard and, therefore, intractable to solve exactly. To defend the AD graph from cyber attackers, this paper proposes two defensive approaches. In the first approach, we convert the attacker’s problem to an exponential sized Dynamic Program that is approximated by a Neural Network (NN). Once trained, the NN serves as an efficient fitness function for defender’s Evolutionary Diversity Optimization based defensive policy. The diversity emphasis on the defender’s solution provides a diverse set of training samples, improving the training accuracy of our NN for modeling the attacker. In the second approach, we propose a RL based policy to solve the attacker’s problem and Critic network assisted Evolutionary Diversity Optimization based defensive policy to solve defender’s problem. Experimental results on synthetic AD graphs show that the proposed defensive policies are scalable, highly effective, approximate attacker’s problem accurately, and generate good defensive plans.

关键词： Attack graph active directory reinforcement learning evolutionary diversity optimization

来源：评论

学校读者我要写书评

暂无评论

Large Scale Management of Distributed Systems 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： Radu State Sven Meer Declan O’Sullivan Tom Pfeifer

ISBN: (数字)9783540476627

ISBN: (纸本)9783540476597

th This volume presents the proceedings of the 17 IFIP/IEEE International Workshop on Distributed Systems: Operations and Management (DSOM 2006), which was held rd th in Dublin, Ireland during October 23 to 25 , 2006. In line with its reputation as one of the pre-eminent fora for the discussion and debate of advances of distributed systems management, the 2006 iteration of DSOM brought together an international audience of researchers and practitioners from both industry and academia. th DSOM 2006 was the 17 in a series of annual workshops, and it followed the footsteps of highly successful previous meetings, the most recent of which were held in Barcelona, Spain (DSOM 2005), Davis, USA (DSOM 2004), Heidelberg, Germany (DSOM 2003), Montreal, Canada (DSOM 2002) and Nancy, France (DSOM 2001). The goal of the DSOM workshops is to bring together researchers in the areas of networks, systems and services management, from both industry and academia, to discuss recent advances and foster future growth in these ?elds. In contrast to the larger management symposia, such as Integrated Management (IM) and Network Operations and Management (NOMS), the DSOM workshops are organised as sing- track programmes in order to stimulate interaction among participants. Following the excellent experiences from the previous year, DSOM was for the th

关键词： Theory of Computation Computer Communication Networks Programming Techniques Operating Systems Management of Computing and Information Systems Computers and Society

来源：评论

学校读者我要写书评

暂无评论

Edge AI 1

引用

1000年

作者： Xiaofei Wang Yiwen Han Victor C. M. Leung Dusit Niyato Xueqiang Yan Xu Chen

ISBN: (数字)9789811561863

ISBN: (纸本)9789811561856;9789811561887

As an important enabler for changing people’s lives, advances in artiﬁcial intelligence (AI)-based applications and services are on the rise, despite being hindered by efﬁciency and latency issues. By focusing on deep learning as the most representative technique of AI, this book provides a comprehensive overview of how AI services are being applied to the network edge near the data sources, and demonstrates how AI and edge computing can be mutually beneficial. To do so, it introduces and discusses: 1) edge intelligence and intelligent edge; and 2) their implementation methods and enabling technologies, namely AI training and inference in the customized edge computing framework. Gathering essential information previously scattered across the communication, networking, and AI areas, the book can help readers to understand the connections between key enabling technologies, e.g. a) AI applications in edge; b) AI inference in edge; c) AI training for edge; d) edge computing for AI; and e)using AI to optimize edge. After identifying these five aspects, which are essential for the fusion of edge computing and AI, it discusses current challenges and outlines future trends in achieving more pervasive and fine-grained intelligence with the aid of edge computing.

关键词： Artificial Intelligence Computer Communication Networks Computer Systems Organization and Communication Networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal Large Language Model with LoRA Fine-Tuning for Multimodal Sentiment Analysis

引用

ACM Transactions on Intelligent Systems and Technology 1000年

作者： Jie Mu Wei Wang Wenqi Liu Tiantian Yan Guanglu Wang School of Data Science and Artificial Intelligence Dongbei University of Finance and Economics China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University China the National and Local Joint Engineering Laboratory of Computer Aided Design Dalian University China School of Software Dalian University of Technology China

Multimodal sentiment analysis has become a popular research topic in recent years. However, existing methods have two unaddressed limitations: (1) they use limited supervised labels to train models, which makes it impossible for model to fully learn sentiments in different modal data; (2) they employ text and image pre-trained models trained in different unimodal tasks to extract different modal features, so that the extracted features cannot take into account the interactive information between image and text. To solve these problems, in this paper we propose a Vision-Language Contrastive Learning network (VLCLNet). First, we introduce a pre-trained Large Language Model (LLM), which is trained from vast quantities of multimodal data, has better understanding ability for image and text contents, thus being effectively applied to different tasks while requiring few amount of labelled training data. Second, we adapt a Multimodal Large Language Model (MLLM), BLIP-2 (Bootstrapping Language-Image Pre-training) network, to extract multimodal fusion feature. Such MLLM can fully consider the correlation between images and texts when extracting features. In addition, due to the discrepancy between the pre-training task and the sentiment analysis task, the pre-trained model will output the suboptimal prediction results. We use LoRA (Low-Rank Adaptation) fine-tuning strategy to update the model parameters on sentiment analysis task, which avoids the issue of inconsistent task between pre-training task and downstream task. Experiments verify that the proposed VLCLNet is superior to other strong baselines.

关键词： Deep learning Large language model Multimodal representation learning Sentiment analysis

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：