检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 301-316页

作者： Chen, Leiming Zhao, Dehai Tao, Liping Wang, Kai Qiao, Sibo Zeng, Xingjie Tan, Chee Wei China University of Petroleum School of Computer Science and Technology East China Qingdao266580 China CSIRO's Data61 Sydney2015 Australia Hefei University of Technology Anhui230009 China Nanyang Technological University School of Computer Science and Engineering Singapore639798 Singapore Tiangong University School of Software Tianjin300387 China Southwest Petroleum University School of Computer Science Chengdu610500 China

Federated learning (FL) enables cooperative computation between multiple participants while protecting user privacy. Currently, FL algorithms assume that all participants are trustworthy and their systems are secure. However, the following problems arise in real-world scenarios: 1) Malicious clients disrupt FL through model poisoning and data poisoning attacks. Although some research has proposed secure aggregation methods to solve this problem, most methods have limitations. 2) The current method cannot fairly evaluate client contribution in some scenarios. Some clients exhibit free-rider behavior, seeking to cheat the reward system and manipulate global models. Evaluating client contribution and distributing rewards also present challenges. To address these challenges, we design a trustworthy federated framework to ensure secure computing throughout the federated task process. First, we propose a method of detecting malicious models to guarantee secure model aggregation. Then, we propose a fair method of assessing contribution to identify client-side free-riding behavior. Finally, we implement a computation process based on blockchain and smart contracts to guarantee the trustworthiness and fairness of federated tasks. To validate the performance of our framework, we simulate different types of client attacks and contribution evaluation scenarios on several open-source datasets. The experiments show that our framework ensures the credibility of federated tasks and achieves a fair evaluation of client contributions. © 2020 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching 38

GoMatching: A Simple Baseline for Video Text Spotting via Lo...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： He, Haibin Ye, Maoyuan Zhang, Jing Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University China College of Computing & Data Science Nanyang Technological University Singapore

Beyond the text detection and recognition tasks in image text spotting, video text spotting presents an augmented challenge with the inclusion of tracking. While advanced end-to-end trainable methods have shown commendable performance, the pursuit of multi-task optimization may pose the risk of producing sub-optimal outcomes for individual tasks. In this paper, we identify a main bottleneck in the state-of-the-art video text spotter: the limited recognition capability. In response to this issue, we propose to efficiently turn an off-the-shelf query-based image text spotter into a specialist on video and present a simple baseline termed GoMatching, which focuses the training efforts on tracking while maintaining strong recognition performance. To adapt the image text spotter to video datasets, we add a rescoring head to rescore each detected instance's confidence via efficient tuning, leading to a better tracking candidate pool. Additionally, we design a long-short term matching module, termed LST-Matcher, to enhance the spotter's tracking capability by integrating both long- and short-term matching results via Transformer. Based on the above simple designs, GoMatching delivers new records on ICDAR15-video, DSText, BOVText, and our proposed novel test set with arbitrary-shaped text termed ArTVideo, which demonstrates GoMatching's capability to accommodate general, dense, small, arbitrary-shaped, Chinese and English text scenarios while saving considerable training budgets. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Controlling update distance and enhancing fair trainable prototypes in federated learning under data and model heterogeneity

引用

Defence Technology(防务技术) 2025年第5期47卷 15-31页

作者： Kangning Yin Zhen Ding Xinhui Ji Zhiguo Wang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China Institute of Public Security Kash Institute of Electronics and Information IndustryKash 844000China Shanghai New Energy Vehicle Public Data Collection and Monitoring Research Center Shanghai 200241China

Heterogeneous federated learning(HtFL)has gained significant attention due to its ability to accommodate diverse models and data from distributed combat *** prototype-based HtFL methods were proposed to reduce the high communication cost of transmitting model *** methods allow for the sharing of only class representatives between heterogeneous clients while maintaining ***,existing prototype learning approaches fail to take the data distribution of clients into consideration,which results in suboptimal global prototype learning and insufficient client model personalization *** address these issues,we propose a fair trainable prototype federated learning(FedFTP)algorithm,which employs a fair sampling training prototype(FSTP)mechanism and a hyperbolic space constraints(HSC)mechanism to enhance the fairness and effectiveness of prototype learning on the server in heterogeneous ***,a local prototype stable update(LPSU)mechanism is proposed as a means of maintaining personalization while promoting global consistency,based on contrastive *** experimental results demonstrate that FedFTP achieves state-of-the-art performance in HtFL scenarios.

关键词： Heterogeneous federated learning Model heterogeneity data heterogeneity Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Privacy Protection with Large Language Model in Social Networks 24th

Dynamic Privacy Protection with Large Language Model in So...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Xie, Yizhe Zhu, Congcong Zhang, Xinyue Hu, Xiangyu Liu, Xuan School of Data Science City University of Macau Macau China Hainan International College Minzu University of China Hainan China School of Information Engineering Minzu University of China Beijing China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan China

ISBN: (纸本)9789819615445

In contemporary social networks, dynamic privacy protection remains a pivotal yet challenging endeavor due to the intricate and evolving nature of information exchange. Traditional privacy models, predominantly static, falter in effectively safeguarding privacy amidst the complex interplay of continuously changing network interactions and structures. Addressing these deficiencies, this study introduces a novel dynamic privacy protection system anchored by large language model (LLM). Leveraging the natural language processing prowess of LLM, this system excels in real-time, context-sensitive analysis and protection of textual data within vast and variable social networks. By integrating closed-loop control theory, the system adeptly balances robust privacy safeguards with the requisite fluidity of information exchange. Experimental validations on large network datasets illustrate the system’s adeptness in balancing privacy leaks and information distortion through intelligent adaptations to privacy thresholds and strategic noise injection. The outcomes highlight the system’s utility in enhancing data security and operational efficiency, promising significant implications for future applications in broader domains such as mobile computing and IoT. This study not only propels forward the capabilities of dynamic privacy protection mechanisms but also sets a foundational architecture for subsequent innovations in privacy-sensitive, data-intensive environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Survey on Evolutionary Computation Based Drug Discovery

引用

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Yu, Qiyuan Lin, Qiuzhen Ji, Junkai Zhou, Wei He, Shan Zhu, Zexuan Tan, Kay Chen College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Computer Science University of Birmingham Bir-mingham UK Department of Computing The Hong Kong Poly-technic University Hong Kong Hong Kong

Drug discovery is an expensive and risky process. To combat the challenges in drug discovery, an increasing number of researchers and pharmaceutical companies recognize the benefits of utilizing computational techniques. Evolutionary computation (EC) offers promise as most drug discovery problems are essentially complex optimization problems beyond conventional optimization algorithms. EC methods have been widely applied to solve these complex optimization problems especially in lead com-pound generation and molecular virtual evaluation, substantially speeding up the process of drug discovery and development. This article presents a comprehensive survey of EC-based drug discovery methods. Particularly, a new taxonomy of the methods is provided and the advantages and limitations of the methods are reviewed. In addition, the potential future directions of EC-based drug discovery are discussed and the publicly available resources including databases and computational tools are compiled for the convenience of researchers seeking to pursue this field. IEEE

关键词： Lead compounds

来源：评论

学校读者我要写书评

暂无评论

SConE: Simplified Cone Embeddings with Symbolic Operators for Complex Logical Queries 61

SConE: Simplified Cone Embeddings with Symbolic Operators fo...

引用

Findings of the Association for Computational Linguistics, ACL 2023

作者： Nguyen, Chau Duc Minh French, Tim Liu, Wei Stewart, Michael ARC Centre for Transforming Maintenance through Data Science Department of Computer Science and Software Engineering School of Physics Mathematics and Computing The University of Western Australia

ISBN: (纸本)9781959429623

Geometric representation of query embeddings (using points, particles, rectangles and cones) can effectively achieve the task of answering complex logical queries expressed in first-order logic (FOL) form over knowledge graphs, allowing intuitive encodings. However, current geometric-based methods depend on the neural approach to model FOL operators (conjunction, disjunction and negation), which are not easily explainable with considerable computation cost. We overcome this challenge by introducing a symbolic modeling approach for the FOL operators, emphasizing the direct calculation of the intersection between geometric shapes, particularly sector-cones in the embedding space, to model the conjunction operator. This approach reduces the computation cost as a non-neural approach is involved in the core logic operators. Moreover, we propose to accelerate the learning in the relation projection operator using the neural approach to emphasize the essential role of this operator in all query structures. Although empirical evidence for explainability is challenging, our approach demonstrates a significant improvement in answering complex logical queries (both non-negative and negative FOL forms) over previous geometric-based models. © 2023 Association for Computational Linguistics.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Vanadium dioxide-based phase gradient-switchable coding metasurface

Vanadium dioxide-based phase gradient-switchable coding meta...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Zhang, Yujie Wei, Tao Sun, Zhenyu Ge, Hongyi Ji, Xiaodi Jiang, Yuying Bu, Yuwei Wu, Xuyang Jia, Keke HAUT College of Information Science and Engineering Zhengzhou450001 China HAUE College of Information Science and Engineering School of Software HAUT Zhengzhou450001 China HAUT College of Intelligence and Big Data Zhengzhou450001 China

ISBN: (纸本)9798350355581

In this paper, we design a phase gradient switchable coding metasurface based on vanadium dioxide (VO2). Each unit structure of the metasurface consists of three layers: a metal-VO2 composite structural layer, a polytetrafluoroethylene dielectric layer and a metal reflective layer. The metasurface utilizes the phase transition property of VO2 to dynamically reconstruct the phase gradient of the metasurface and realize the switching of two far-field beam functions. Simulation results show that when VO2 is in the insulating state, the phase difference between the units of the metasurface at 1.5 THz frequency is 90°, which can realize the anomalous deflection function of the 2-bit coding metasurface. When VO2 is transformed into a metallic state, the phase difference between the metasurfaces at the 2.1 THz frequency is 180°, which reconfigures the metasurface into a 1-bit phase-gradient coding metasurface and realizes the dual-beam beam splitting function. The phase gradient switchable coding metasurface designed in this paper enriches the flexibility of beam modulation and provides a new efficient and flexible beam modulation scheme for terahertz communication with potential applications. © 2024 IEEE.

关键词： Vanadium dioxide

来源：评论

学校读者我要写书评

暂无评论

Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild 38

Locating What You Need: Towards Adapting Diffusion Models to...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yang, Jianan Gao, Chenchao Xiao, Zhiqing Zhao, Junbo Wu, Sai Chen, Gang Wang, Haobo College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China School of Software Technology Zhejiang University China International School of Information Science and Engineering Dalian University of Technology China

The recent large-scale text-to-image generative models have attained unprecedented performance, while people established adaptor modules like LoRA and DreamBooth to extend this performance to even more unseen concept tokens. However, we empirically find that this workflow often fails to accurately depict the out-of-distribution concepts. This failure is highly related to the low quality of training data. To resolve this, we present a framework called Controllable Adaptor Towards Out-of-Distribution Concepts (CATOD). Our framework follows the active learning paradigm which includes high-quality data accumulation and adaptor training, enabling a finer-grained enhancement of generative results. The aesthetics score and concept-matching score are two major factors that impact the quality of synthetic results. One key component of CATOD is the weighted scoring system that automatically balances between these two scores and we also offer comprehensive theoretical analysis for this point. Then, it determines how to select data and schedule the adaptor training based on this scoring system. The extensive results show that CATOD significantly outperforms the prior approaches with an 11.10 boost on the CLIP score and a 33.08% decrease on the CMMD metric. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CIFD: A Distance for Complex Intuitionistic Fuzzy Set 4th

CIFD: A Distance for Complex Intuitionistic Fuzzy Set

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhao, Yangyang Xiao, Fuyuan School of Computer and Information Science Southwest University Chongqing400715 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China

ISBN: (纸本)9783031200953

Intuitionistic fuzzy set (IFS) has attracted much attention because it can deal with fuzziness and uncertainty more flexibly than traditional fuzzy set. Complex intuitionistic fuzzy set (CIFS) extends intuitionistic fuzzy to the complex plane, which can better express and process uncertain information. In this paper, a novel distance measure complex intuitionistic fuzzy distance (CIFD) is proposed for CIFSs. Firstly, inspired by Tanimoto coefficient, a new similarity measure between CIFSs is proposed. Then, based on the similarity measure, the CIFD is proposed and its non-negativity, non-degeneracy, and symmetry are analyzed. Moreover, when CIFS degenerates into classical IFS, CIFD is also applicable to measure the differences between IFSs. Finally, to illustrate the effectiveness of CIFD, an example is given at the end. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based QoS Prediction with Dimensional Correlation 18th

Convolutional Neural Network Based QoS Prediction with Dime...

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Cao, Weihao Cheng, Yong Xue, Shengjun Dai, Fei School of Software Nanjing University of Information Science and Technology Nanjing210044 China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650224 China

ISBN: (纸本)9789819998951

In recent years, massive services that provide similar functions continue to emerge. Since services sensitive to latency and throughput are often expected to have high Quality of Service (QoS), how to accurately predict QoS has become a challenging issue. Some current deep learning (DL) based approaches usually simply concatenate the embedding vectors, without considering the correlation between embedding dimensions. Besides, the high-order feature interactions are not sufficiently learned. To this end, this paper proposes a Convolutional Neural Network based QoS prediction model with Dimensional Correlation, named QPCN. First, the two dimensional interaction features is explicitly obtained by modeling the embedding vectors. Then, the convolutional neural network is utilized to perform feature extraction and complete QoS prediction. Compared with the fully connected network, QPCN can build a deeper model and learn high-order features. In addition, the parameters of QPCN are significantly reduced, which will reduce the time and energy consumption of inference. The effectiveness of QPCN is validated by experiments on a real-world dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Quality of service

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：