检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Yi Yu Shengyue Yao Tianchen Zhou Yexuan Fu Jingru Yu Ding Wang Xuhong Wang Cen Chen Yilun Lin Urban Computing Lab Shanghai Artificial Intelligence Laboratory Shanghai China School of Data Science and Engineering East China Normal University Shanghai China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In the digital era, data has become a pivotal asset, advancing technologies such as autonomous driving. Despite this, data trading faces challenges like the absence of robust pricing methods and the lack of trustworthy trading mechanisms. To address these challenges, we introduce a traffic-oriented data trading platform named data on The Move (DTM), integrating traffic simulation, data trading, and Artificial Intelligent (AI) agents. The DTM platform supports evident-based data value evaluation and AI-based trading mechanisms. Leveraging the common sense capabilities of Large Language Models (LLMs) to assess traffic state and data value, DTM can determine reasonable traffic data pricing through multi-round interaction and simulations. Moreover, DTM provides a pricing method validation by simulating traffic systems, multi-agent interactions, and the heterogeneity and irrational behaviors of individuals in the trading market. Within the DTM platform, entities such as connected vehicles and traffic light controllers could engage in information collecting, data pricing, trading, and decision-making. Simulation results demonstrate that our proposed AI agent-based pricing approach enhances data trading by offering rational prices, as evidenced by the observed improvement in traffic efficiency. This underscores the effectiveness and practical value of DTM, offering new perspectives for the evolution of data markets and smart cities. To the best of our knowledge, this is the first study employing LLMs in data pricing and a pioneering data trading practice in the field of intelligent vehicles and smart cities.

关键词： Connected vehicles Smart cities Simulation Large language models Decision making Pricing Traffic control

来源：评论

学校读者我要写书评

暂无评论

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars

arXiv

引用

arXiv 2025年

作者： Hua, Yuncheng Qu, Lizhen Li, Zhuang Xue, Hao Salim, Flora D. Haffari, Gholamreza Department of Data Science & AI Monash University Australia School of Computer Science Engineering University of New South Wales Australia School of Computing Technologies Royal Melbourne Institute of Technology Australia

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment—factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca-eval task (from 4.50 → 4.60), a 0.22 enhancement on the just-eval-instruct benchmark (from 4.34 → 4.56), and a maximum improvement of 0.32 (from 3.53 → 3.85) on the MT-Bench dataset. We release the code and data at https://***/AnonymousCode-ComputerScience/RIDE. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Improving multi-view document clustering: leveraging multi-structure processor and hybrid ensemble clustering module 30

Improving multi-view document clustering: leveraging multi-s...

引用

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

作者： Bai, Ruina Bai, Qi Huang, Ruizhang Chen, Yanping Qin, Yongbin Text Computing & Cognitive Intelligence Engineering Research Center National Education Ministry College of Computer Science and Technology Guizhou University Guiyang550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China School of Mathematical Sciences Zhejiang University Hangzhou310058 China

ISBN: (纸本)9782493814104

We introduce a multi-view document clustering model called DMsECN (Deep Multi-structure Ensemble Clustering Network), comprising a multi-structure processor and a hybrid ensemble clustering module. Unlike existing models, DMsECN distinguishes itself by creating a consensus structure from multiple clustering structures. The multi-structure processor comprises two stages, each contributing to the extraction of clustering structures that preserve both consistency and complementarity across multiple views. Representation learning extracts both view and view-fused representations from multi-views through the use of contrastive learning. Subsequently, multi-structure learning employs distinct view clustering guidance to generate the corresponding clustering structures. The hybrid ensemble clustering module merges two ensemble methods to amalgamate multiple structures, producing a consensus structure that guarantees both the separability and compactness of clusters within the clustering results. The attention-based ensemble primarily concentrates on learning the contribution weights of diverse clustering structures, while the similarity-based ensemble employs cluster assignment similarity and cluster classification dissimilarity to guide the refinement of the consensus structure. Experimental results demonstrate that DMsECN outperforms other models, achieving new state-of-the-art results on four multi-view document clustering datasets. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Structure (composition)

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

Why Does Little Robustness Help? A Further Step Towards Unde...

引用

IEEE Symposium on Security and Privacy

作者： Yechao Zhang Shengshan Hu Leo Yu Zhang Junyu Shi Minghui Li Xiaogeng Liu Wei Wan Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University School of Software Engineering Huazhong University of Science and Technology Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

Adversarial examples for deep neural networks (DNNs) are transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical *** this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient *** on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifests in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other, and emphasize the

关键词： Training Privacy Buildings Closed box Minimization data augmentation Robustness

来源：评论

学校读者我要写书评

暂无评论

xGCN: An Extreme Graph Convolutional Network for Large-scale Social Link Prediction 23

xGCN: An Extreme Graph Convolutional Network for Large-scale...

引用

2023 World Wide Web Conference, WWW 2023

作者： Song, Xiran Lian, Jianxun Huang, Hong Luo, Zihan Zhou, Wei Lin, Xue Wu, Mingqi Li, Chaozhuo Xie, Xing Jin, Hai Huazhong University of Science and Technology Wuhan China Microsoft Research Asia Beijing China Microsoft Gaming Redmond United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781450394161

Graph neural networks (GNNs) have seen widespread usage across multiple real-world applications, yet in transductive learning, they still face challenges in accuracy, efficiency, and scalability, due to the extensive number of trainable parameters in the embedding table and the paradigm of stacking neighborhood aggregations. This paper presents a novel model called xGCN for large-scale network embedding, which is a practical solution for link predictions. xGCN addresses these issues by encoding graph-structure data in an extreme convolutional manner, and has the potential to push the performance of network embedding-based link predictions to a new record. Specifically, instead of assigning each node with a directly learnable embedding vector, xGCN regards node embeddings as static features. It uses a propagation operation to smooth node embeddings and relies on a Refinement neural Network (RefNet) to transform the coarse embeddings derived from the unsupervised propagation into new ones that optimize a training objective. The output of RefNet, which are well-refined embeddings, will replace the original node embeddings. This process is repeated iteratively until the model converges to a satisfying status. Experiments on three social network datasets with link prediction tasks show that xGCN not only achieves the best accuracy compared with a series of competitive baselines but also is highly efficient and scalable. © 2023 ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Compression and Deadline Optimization for Communication-Efficient Federated Edge Learning

Joint Compression and Deadline Optimization for Communicatio...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Zhang, Maojun Cai, Zhijie Liu, Dongzhu Jin, Richeng Zhu, Guangxu Zhong, Caijun Shenzhen Research Institute of Big Data Shenzhen China School of Computing Science University of Glasgow United Kingdom College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Peng Cheng Laboratory Guangdong Shenzhen China Guangdong Guangzhou China

ISBN: (纸本)9798350370218

The federated edge learning (FEEL) framework is a popular approach for privacy-preserving collaborative model training, where edge devices and the server exchange learning updates frequently. In this vein, FEEL can cause a heavy burden on the communication system due to the limited bandwidth and severe interference between devices. Moreover, under the common FEEL framework, the server needs to wait for the update from the slowest device before starting the aggregation process, leading to the straggler issue that causes prolonged communication time. In this paper, we propose to accelerate FEEL from two aspects: i.e., 1) performing data compression on the edge devices and 2) setting a deadline on the edge server to exclude the straggler devices. However, undesired gradient compression errors and transmission outage are introduced by the aforementioned operations respectively, affecting the convergence of FEEL as well. To address these practical issues, we formulate a training time minimization problem that optimizes the compression ratio and deadline. To this end, the impact of compression error and transmission outage on the overall training time are quantified through convergence analysis. Then, the formulated problem is simplified and solved in an alternating manner, based on which, the novel joint compression and deadline optimization (JCDO) algorithm is derived. Numerical experiments show that the proposed method can greatly accelerate the vanilla FedAVG algorithm, and outperforms the state-of-the-art schemes. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuroimaging Precision: Crafting a Stacked VGG19-Logistic Fusion for Breakthrough Early Detection of Alzheimer's

Neuroimaging Precision: Crafting a Stacked VGG19-Logistic Fu...

引用

International Conference on Science Technology engineering and Management (ICONSTEM)

作者： G. Anbu Selvi T. Karthick Department of Computer Science and Engineering SRMIST Kattankulathur Chennai India Department of Data Science and Business Systems SRMIST Kattankulathur School of Computing Chennai India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

Several medical investigations have demonstrated that Alzheimer's disease (AD) manifests itself long before the formal diagnosis of dementia. These studies have led to the identification of numerous ideal biomarkers associated with Alzheimer's symptoms. Consequently, the imperative for early diagnosis has become evident, necessitating a high-performance computational tool capable of efficiently processing vast amounts of data. Early detection of AD not only offers valuable insights into the condition's progression but also presents a significant opportunity to benefit from timely and effective treatment. This ground-breaking study pioneers an innovative approach to the early detection and diagnosis of AD by crafting a sophisticated model SVGGL, which blends the power of stacked VGG19 neural networks with the interpretability of logistic regression. Leveraging neuro-imaging data, specifically the insights provided MRI, and our model aims to discern subtle structural and functional alterations in the brains of individuals at risk for or in the early stages of AD. The combination of feature extraction from stacked VGG19 models and subsequent logistic regression classification yields a precise and efficient classifier with an outstanding accuracy of 98.24%. With such a high degree of accuracy, the model can reliably differentiate among healthy people and those with Alzheimer's, opening the door to potential early intervention and individualized treatment plans. The study not only sheds light on the intricate neuro pathological landscape of AD but also propels us toward a future where cutting-edge technology and data-driven insights, exemplified by our high-accuracy model, converge to tackle the challenges posed by this prevalent neurodegenerative disorder.

关键词： Neuroimaging Logistic regression Accuracy Computational modeling Brain modeling Feature extraction data models

来源：评论

学校读者我要写书评

暂无评论

data Insights as data: Quick Overview and Exploration of Automated data Insights

Data Insights as Data: Quick Overview and Exploration of Aut...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI EA 2025

作者： Wu, Shangxuan Luan, Wendi Wang, Yong Zeng, Dan Shen, Qiaomu Tang, Bo Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore Singapore Singapore School of Artificial Intelligence Sun Yat-Sen University Guangdong Zhuhai China

ISBN: (纸本)9798400713958

Automated data insight mining and visualization have been widely used in various business intelligence applications (e.g., market analysis and product promotion). However, automated insight mining techniques often output the same mining results to different analysts without considering their personal preferences, while interactive insight discovery requires significant manual effort. This paper fills the gap by integrating automated insight mining with interactive data visualization and striking a proper balance between them to facilitate insight discovery and exploration. Specifically, we regard data insights as a special type of data and further present InsightMap, a novel visualization approach that uses the map metaphor to provide a quick overview and in-depth exploration of different data insights, where a metric is proposed to measure the similarity between different insights. The effectiveness and usability of InsightMap are demonstrated through extensive case studies and in-depth user interviews. © 2025 Copyright held by the owner/author(s).

关键词： data Insights Glyph Multidimensional data Visual Analytics

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Business data Fusion in the engineering Management of Oil and Gas Storage and Transportation Station 4

Research on the Application of Business Data Fusion in the E...

引用

4th International Conference on Computer Science and Management Technology, ICCSMT 2023

作者： Xie, Rui Fan, Bo Ma, Jianlin Pan, Meng Southwest Pipeline Ltd. PipeChina ChengDu610213 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu610031 China Chengdu Aerospace Science and Industry Big Data Institute Ltd. Casic Chengdu610213 China National Engineering Laboratory of Industrial Big-Data Application Technology Casic Chengdu610218 China

ISBN: (纸本)9798400709517

Due to challenges such as complex contractor personnel, a large amount of scattered form data, a cumbersome business implementation process, low levels of digitalization and security, and difficult management in the engineering management business of oil and gas storage and transportation stations, this paper proposes a study on business data fusion application in the engineering management of oil and gas storage and transportation stations. Focused on the business processes and data of engineering management in oil and gas storage and transportation stations, this research establishes and analyzes an architecture for engineering management business in these stations. Using an Artifact-centric data fusion method, the research constructs an information model for the engineering management business, identifying the data topics for this area. Finally, the research applies and verifies the study of business data fusion through real-world business management scenarios. As researchers in the field of business data fusion, this study utilizes digital technologies and methods to enhance the overall safety management of engineering operations, thereby promoting the transformation and upgrading of engineering management business in oil and gas storage and transportation stations © 2023 ACM.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A Dual-Port, and Single-Element Planar Inverted-F Antenna for Current 4G/5G Portable Applications

A Dual-Port, and Single-Element Planar Inverted-F Antenna fo...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Saqer S. Alja'afreh Amjaad T. Altakhaineh Mallak H. Al-shamaileh Aser M Matarneh Omar R. Daoud Mohammad Al-Khawaldah I Electrical and Computing Engineering School of Engineering and Computing American International University Al-Jahra Kuwait Data Science and Machine Learning Dept. Pioneers International Academy Amman Jordan Communications and Computer Engineering Al-Ahliyya Amman University Amman Jordan

ISBN: (数字)9798350374131

ISBN: (纸本)9798350374148

A first-hand, low-profile, two-port planar inverted-F antenna is proposed for current 4G/5G sub-3 GHz hand-portable multiple-input and multiple-output (MIMO) applications. The design features a profile of about 5 mm and dual-coplanar feeds, which are isolated using only a modified top plate, while the shared ground plane is not perturbed as in previous designs. An open-edge slot on the top of the PIFA provides a 3λ/4 current path. The proposed antenna covers approximately a 15% impedance bandwidth fraction in the range of 2.45-2.85 GHz. The simulated results, including scattering parameters, far-field radiation patterns, and the envelope correlation coefficient, all exhibit excellent features.

关键词： Wireless communication Correlation coefficient Simulation Bandwidth Specific absorption rate Impedance MIMO communication

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：