检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Pang, Yahao Wu, Xingyuan Zhang, Xiaojin Chen, Wei Jin, Hai 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 Wuhan430074 China Huazhong University of Science and Technology Wuhan China

Significant advancements have been made by Large Language Models (LLMs) in the domains of natural language understanding and automated content creation. However, they still face persistent problems, including substantial computational costs and inadequate availability of training data. The combination of Federated Learning (FL) and LLMs (federated LLMs) offers a solution by leveraging distributed data while protecting privacy, which positions it as an ideal choice for sensitive domains. However, Federated LLMs still suffer from robustness challenges, including data heterogeneity, malicious clients, and adversarial attacks, which greatly hinder their applications. We first introduce the robustness problems in federated LLMs, to address these challenges, we propose FedEAT (Federated Embedding space Adversarial Training), a novel framework that applies adversarial training in the embedding space of client LLM and employs a robust aggregation approach, specifically geometric median aggregation, to enhance the robustness of Federated LLMs. Our experiments demonstrate that FedEAT effectively improves the robustness of Federated LLMs with minimal performance loss. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Genetic Auto-prompt Learning for Pre-trained Code Intelligence Language Models

arXiv

引用

arXiv 2024年

作者： Feng, Chengzhe Sun, Yanan Li, Ke Zhou, Pan Lv, Jiancheng Lu, Aojun The College of Computer Science Sichuan University Chengdu610065 China The Department of Computer Science University of Exeter ExeterEX4 4QF United Kingdom The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

As Pre-trained Language Models (PLMs), a popular approach for code intelligence, continue to grow in size, the computational cost of their usage has become prohibitively expensive. Prompt learning, a recent development in the field of natural language processing, emerges as a potential solution to address this challenge. In this paper, we investigate the effectiveness of prompt learning in code intelligence tasks. We unveil its reliance on manually designed prompts, which often require significant human effort and expertise. Moreover, we discover existing automatic prompt design methods are very limited to code intelligence tasks due to factors including gradient dependence, high computational demands, and limited applicability. To effectively address both issues, we propose Genetic Auto Prompt (GenAP), which utilizes an elaborate genetic algorithm to automatically design prompts. With GenAP, non-experts can effortlessly generate superior prompts compared to meticulously manual-designed ones. GenAP operates without the need for gradients or additional computational costs, rendering it gradient-free and cost-effective. Moreover, GenAP supports both understanding and generation types of code intelligence tasks, exhibiting great applicability. We conduct GenAP on three popular code intelligence PLMs with three canonical code intelligence tasks including defect prediction, code summarization, and code translation. The results suggest that GenAP can effectively automate the process of designing prompts. Specifically, GenAP outperforms all other methods across all three tasks (e.g. improving accuracy by an average of 2.13% for defect prediction). To the best of our knowledge, GenAP is the first work to automatically design prompts for code intelligence PLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

LLM App Store Analysis: A Vision and Roadmap

arXiv

引用

arXiv 2024年

作者： Zhao, Yanjie Hou, Xinyi Wang, Shenao Wang, Haoyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China Huazhong University of Science and Technology Wuhan China

The rapid growth and popularity of large language model (LLM) app stores have created new opportunities and challenges for researchers, developers, users, and app store managers. As the LLM app ecosystem continues to evolve, it is crucial to understand the current landscape and identify potential areas for future research and development. This paper presents a forward-looking analysis of LLM app stores, focusing on key aspects such as data mining, security risk identification, development assistance, and market dynamics. Our comprehensive examination extends to the intricate relationships between various stakeholders and the technological advancements driving the ecosystem's growth. We explore the ethical considerations and potential societal impacts of widespread LLM app adoption, highlighting the need for responsible innovation and governance frameworks. By examining these aspects, we aim to provide a vision for future research directions and highlight the importance of collaboration among stakeholders to address the challenges and opportunities within the LLM app ecosystem. The insights and recommendations provided in this paper serve as a foundation for driving innovation, ensuring responsible development, and creating a thriving, user-centric LLM app landscape. Copyright © 2024, The Authors. All rights reserved.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Transmission Line Transient Faults Based on Graph Convolutional Neural Network

引用

CSEE Journal of Power and Energy Systems 2021年第3期7卷 456-471页

作者： Houjie Tong Robert C.Qiu Dongxia Zhang Haosen Yang Qi Ding Xin Shi Department of Electrical Engineering Center for Big Data and Artificial IntelligenceShanghai Jiao Tong UniversityShanghai 200240China School of Electronic Information and Communication Huazhong University of Science and TechnologyWuhan 430000China Electric Power Research Institute Haidian DistrictBeijing 100192China School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China

We present a novel transient fault detection and classification approach in power transmission lines based on graph convolutional neural *** with the existing techniques,the proposed approach considers explicit spatial information in sampling sequences as prior knowledge and it has stronger feature extraction *** this basis,a framework for transient fault detection and classification is *** structure is generated to provide topology information to the *** approach takes the adjacency matrix of topology graph and the bus voltage signals during a sampling period after transient faults as inputs,and outputs the predicted classification results ***,the proposed approach is tested in various situations and its generalization ability is verified by experimental *** results show that the proposed approach can detect and classify transient faults more effectively than the existing techniques,and it is practical for online transmission line protection for its rapidness,high robustness and generalization ability.

关键词： Graph convolutional network(GCN) power transmission line fault detection and classification spatio-temporal data topology information

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for 6G:Applications,Challenges,and Opportunities

引用

engineering 2022年第1期8卷 33-41页

作者： Zhaohui Yang Mingzhe Chen Kai-Kit Wong H.Vincent Poor Shuguang Cui Department of Electronic and Electrical Engineering University College LondonLondon WC1E 6BTUK Department of Electrical and Computer Engineering Princeton UniversityPrincetonNJ 08544USA Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhen 518172China School of Science and Engineering and Future Network of Intelligence Institute The Chinese University of Hong KongShenzhen 518172China

Standard machine-learning approaches involve the centralization of training data in a data center,where centralized machine-learning algorithms can be applied for data analysis and ***,due to privacy restrictions and limited communication resources in wireless networks,it is often undesirable or impractical for the devices to transmit data to parameter *** approach to mitigate these problems is federated learning(FL),which enables the devices to train a common machine learning model without data sharing and *** paper provides a comprehensive overview of FL applications for envisioned sixth generation(6G)wireless *** particular,the essential requirements for applying FL to wireless communications are first *** potential FL applications in wireless communications are *** main problems and challenges associated with such applications are ***,a comprehensive FL implementation for wireless communications is described.

关键词： Federated learning 6G Reconfigurable intelligent surface Semantic communication Sensing Communication and computing

来源：评论

学校读者我要写书评

暂无评论

Variable projection algorithms with sparse constraint for separable nonlinear models

引用

Control Theory and Technology 2024年第1期22卷 135-146页

作者： Hui-Lang Xu Guang-Yong Chen Si-Qing Cheng Min Gan Jing Chen College of Computer and Data Science Fuzhou UniversityFuzhou350116FujianChina Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350116FujianChina Key Laboratory of Intelligent Metro of Universities in Fujian Fuzhou UniversityFuzhou350116FujianChina Engineering Research Center of Big Data Intelligence Ministry of EducationFuzhou UniversityFuzhou350116FujianChina School of Science Jiangnan UniversityWuxi214122JiangsuChina

Separable nonlinear models are widely used in various fields such as time series analysis, system modeling, and machine learning, due to their flexible structures and ability to capture nonlinear behavior of data. However, identifying the parameters of these models is challenging, especially when sparse models with better interpretability are desired by practitioners. Previous theoretical and practical studies have shown that variable projection (VP) is an efficient method for identifying separable nonlinear models, but these are based on \(L_2\) penalty of model parameters, which cannot be directly extended to deal with sparse constraint. Based on the exploration of the structural characteristics of separable models, this paper proposes gradient-based and trust-region-based variable projection algorithms, which mainly solve two key problems: how to eliminate linear parameters under sparse constraint;and how to deal with the coupling relationship between linear and nonlinear parameters in the model. Finally, numerical experiments on synthetic data and real time series data are conducted to verify the effectiveness of the proposed algorithms.

关键词： Variable projection(VP) Non-smooth constraint Separable nonlinear models

来源：评论

学校读者我要写书评

暂无评论

RAUIE: A Relation-Augmented Document-Level Event Extraction Model Based on UIE

RAUIE: A Relation-Augmented Document-Level Event Extraction ...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Yiyuan Liang Hong Jia Licai Wang Yangchen Huang Zhe Yang Big data research and development center North China Institute of Computing Technology Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

In document-level event extraction tasks, multiple event types often coexist within a document (the multi-event problem), and arguments may play different roles across different events (the argument intertwining problem). Existing methods often suffer from significantly reduced event extraction accuracy, mainly when focusing on scenarios with scarce annotated data and imbalanced event-type distributions. This paper emphasizes enhancing the correlation between event triggers and arguments to address these challenges. Therefore, we propose the Relation-Augmented UIE Model (RADIE), which introduces entity relationships into prompts using prompt-based learning and designs a relation-augmentation algorithm to improve the accuracy and completeness of event extraction. Experimental results demonstrate that this approach significantly outperforms baseline methods, mainly showcasing excellent performance on datasets with long-tail distributions.

关键词： Seminars Accuracy Correlation Focusing Feature extraction data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack

3DHacker: Spectrum-based Decision Boundary Generation for Ha...

引用

International Conference on computer Vision (ICCV)

作者： Yunbo Tao Daizong Liu Pan Zhou Yulai Xie Wei Du Wei Hu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wangxuan Institute of Computer Technology Peking University

With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the white-box setting to iteratively update the coordinate perturbations based on gradients, or utilize the output model logits to estimate noisy gradients in the black-box setting. However, these attack methods are hard to be deployed in real-world scenarios since realistic 3D applications will not share any model details to users. Therefore, we explore a more challenging yet practical 3D attack setting, i.e., attacking point clouds with black-box hard labels, in which the attacker can only have access to the prediction label of the input. To tackle this setting, we propose a novel 3D attack method, termed 3D Hard-label attacker (3DHacker), based on the developed decision boundary algorithm to generate adversarial samples solely with the knowledge of class labels. Specifically, to construct the class-aware model decision boundary, 3DHacker first randomly fuses two point clouds of different classes in the spectral domain to craft their intermediate sample with high imperceptibility, then projects it onto the decision boundary via binary search. To restrict the final perturbation size, 3DHacker further introduces an iterative optimization strategy to move the intermediate sample along the decision boundary for generating adversarial point clouds with smallest trivial perturbations. Extensive evaluations show that, even in the challenging hard-label setting, 3DHacker still competitively outperforms existing 3D attacks regarding the attack performance as well as adversary quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Passive Beamforming and Deployment Design for Multi-Intelligent Refracting Surface Aided High-Speed Railway Communication

引用

IEEE Wireless Communications Letters 2025年

作者： Wang, Lei Zhu, Lipeng Sun, He Niu, Yong Ai, Bo Zhang, Rui Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China 117583 Singapore School of Science and Engineering Shenzhen Research Institute of Big Data Chinese University of Hong Kong Guangdong Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore

This letter investigates a multi-intelligent refracting surface (IRS) aided high-speed railway communication system that can provide cooperative passive beamforming gains without incurring additional channel estimation overhead. A novel multi-IRS passive beamforming framework is designed to simultaneously track the time-varying channels between the remote radio head and a number of IRSs mounted on the top of the train. These IRSs cooperatively enhance the signal coverage within the train carriage. Specifically, the multi-IRS passive beamforming and deployment are jointly optimized to maximize the minimum average channel power across all discretized grids within the carriage, thereby ensuring fair coverage throughout the train. An alternating optimization algorithm, utilizing the semidefinite relaxation and one-dimensional line search techniques, is employed to solve this non-convex optimization problem efficiently. Numerical results reveal that the proposed distributed IRS deployment scheme outperforms its centralized deployment counterpart with the same total number of IRS elements. Moreover, the proposed multi-IRS passive beamforming and deployment joint design can significantly improve the signal coverage performance in the train carriage. © 2012 IEEE.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Intelligent larval zebrafish phenotype recognition via attention mechanism for high-throughput screening

引用

computers in Biology and Medicine 2025年 188卷 109892-109892页

作者： Wang, Baihua Sun, Qi Liu, Yujia Zhang, Jiheng Li, Gaozheng Wu, Sifang Zheng, Houbing Ye, Jialin Zhou, Meihua Zheng, Haisu Yu, Yongqiang Zhong, Yi Wu, Yuanzi Huang, Da Wang, Biao Weng, Zuquan College of Biological Science and Engineering Fuzhou University Fujian Fuzhou China Department of Plastic and Cosmetic Surgery The First Affiliated Hospital of Fujian Medical University Fujian Fuzhou China The Center for Big Data Research in Burns and Trauma College of Computer and Data Science/College of Software Fuzhou University Fujian China

Background: Larval zebrafish phenotypes serve as critical research indicators in fields such as ecotoxicology and safety assessment since phenotypic defects are closely related to alterations of underlying pathway. However, identifying these defects is time-consuming and requires specialized knowledge. Method: We proposed a deep network model called RECNet, which combines attention mechanisms and residual structures. In terms of data processing, we applied the mixup data augmentation technique and accumulated a collection of 6805 larval zebrafish phenotype images, mostly generated from our laboratory. Our proposed model was deployed to execute two distinct tasks, including a four-classification of zebrafish phenotypes and a seven-classification involving mixed labels for abnormalities. Results: In the four-class classification task, the RECNet model achieved an accuracy of 0.949, with a mean area under the curve of 0.986 and an F1-score of 0.966. Through interpretable research, attention mechanisms enable the model to focus more accurately on regions of interest. In the mixed-label seven-classification task for anomalies, our model achieved an accuracy of 0.913 and a mean average precision value of 0.847 by employing the weighted loss function (DFBLoss). Furthermore, in a new test dataset, the RECNet model achieved accuracy rates of 0.924 and 0.876 for the two tasks, respectively. Our RECNet model was trained by orders of magnitude larger dataset than previous studies and also showed better accuracy rates. Conclusions: Our method holds promise for diverse applications within zebrafish laboratories and fields such as toxicology, providing indispensable support to scientific research. © 2025 Elsevier Ltd

关键词： Invertebrates

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：