检索结果-内蒙古大学图书馆

Prompting Large Language Models with Knowledge-Injection for Knowledge-Based Visual Question Answering

Big Data Mining and Analytics 2024年第3期7卷 843-857页

作者： Zhongjian Hu Peng Yang Fengyuan Liu Yuan Meng Xingyu Liu School of Computer Science and Engineering Southeast University the Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education of the People’s Republic of ChinaNanjing 211189China Southeast University-Monash University Joint Graduate School(Suzhou) Southeast UniversitySuzhou 215125China

Previous works employ the Large Language Model(LLM)like GPT-3 for knowledge-based Visual Question Answering(VQA).We argue that the inferential capacity of LLM can be enhanced through knowledge *** methods that utilize knowledge graphs to enhance LLM have been explored in various tasks,they may have some limitations,such as the possibility of not being able to retrieve the required *** this paper,we introduce a novel framework for knowledge-based VQA titled“Prompting Large Language Models with Knowledge-Injection”(PLLMKI).We use vanilla VQA model to inspire the LLM and further enhance the LLM with knowledge *** earlier approaches,we adopt the LLM for knowledge enhancement instead of relying on knowledge ***,we leverage open LLMs,incurring no additional *** comparison to existing baselines,our approach exhibits the accuracy improvement of over 1.3 and 1.7 on two knowledge-based VQA datasets,namely OK-VQA and A-OKVQA,respectively.

关键词： visual question answering knowledge-based visual question answering large language model knowledge injection

来源：评论

学校读者我要写书评

暂无评论

DM-FedMF: A Recommendation Model of Federated Matrix Factorization with Detection Mechanism

引用

IEEE Transactions on network Science and engineering 2025年

作者： Zheng, Xiaoyao Jia, Xianmin Cheng, Xiongchao He, Wenxuan Sun, Liping Guo, Liangmin Yu, Qingying Luo, Yonglong Anhui Normal University Anhui Provincial Key Laboratory of Network and Information Security School of Computer and Information Wuhu China

Items are recommended to users by the federated recommendation system while protecting user privacy, but there is a risk of the performance of the global model being seriously affected by malicious clients through the tampering of local data and model parameters. In this paper, a federated matrix factorization recommendation model with a detection mechanism(DM-FedMF) is proposed. The experimental analysis concludes that there is a gradient difference in item preference parameters between malicious and benign clients. Accordingly, an objective function is designed to measure item preference differences as a means of identifying malicious clients on the server. Secondly, a malicious client reporting mechanism is proposed to count the reported frequency of all clients and set a threshold. Based on the number of honest clients, the list of attackers is updated. Finally, the malicious client is detected and eliminated based on the list of attackers. The other three defense algorithms are compared with two public datasets in this paper. The experimental results show that the detection mechanism can effectively defend against data poisoning attacks, category attacks, noise attacks, and sign flipping attacks, and the performance of the model's recommendations is better than that achieved by applying other defense methods. © 2025 IEEE. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Image Semantic Communication System Based on GAN and Relative Position-Encoding

引用

IEEE Communications Letters 2025年第6期29卷 1280-1284页

作者： Zhang, Ziqi Tan, Weijie Li, Chunguo Guizhou University College of Big Data and Information Engineering Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Ministry of Industry and Information Technology Laboratory of Cryptography Application Technology Innovation and Testing Verification Beijing100015 China Southeast University School of Information Science and Engineering Nanjing210096 China

In image semantic communication, the complex wireless channel environment leads to the loss of image details and performance degradation during transmission. To address this issue, we propose an image semantic communication system based on Generative Adversarial networks (GAN) and Relative Position-Encoding (RPE), named GAN-RpeSC. Specifically, in the system design, we introduce the GAN network at the output of the semantic communication framework to enhance the image restoration. We integrate the RPE module into the Visual Transformer (ViT) module, adding the RPE module to its Multihead Self Attention (MHSA), so that the model can better capture the spatial location information of the image. Experimental results show that the proposed GAN-RpeSC has significant advantages in improving image transmission quality, with a 0.3 dB improvement in peak signal-to-noise ratio (PSNR) compared to the ViT module alone. © 1997-2012 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

GLAC-GCN: Global and Local Topology-Aware Contrastive Graph Clustering network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1448-1459页

作者： Xu, Yuan-Kun Huang, Dong Wang, Chang-Dong Lai, Jian-Huang South China Agricultural University College of Mathematics and Informatics Guangzhou510642 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou510006 China

Though many deep attributed graph clustering approaches have been developed in recent years, most still suffer from two limitations. First, in the input space, they primarily rely on the original topology structure as the input (to some graph network), lacking the ability to jointly leverage local and global topology information to refine the graph. Second, in the learning process, they usually employ a single graph learning pipeline (with a single input graph), overlooking the opportunities in the joint optimization of multiple graph learning pipelines (with multiple topology structures). In view of this, this article presents a global and local topology-aware contrastive graph clustering network (GLAC-GCN) for attributed graph clustering. Specifically, the local topology structure, and global semantic information are simultaneously utilized to refine the graph. Then a paralleled graph convolutional network (GCN) learning mechanism is designed, where i) both the original graph and the globally and locally refined graph are treated as input graphs, and ii) two pipelines of GCNs are jointly and interactively utilized. Furthermore, a self-adaptive learning mechanism is devised to ensure consistency between multiple learning pipelines via the Kullback–Leibler (KL)-divergence. Meanwhile, the contrastive learning is enforced by minimizing the mismatch of the cluster distributions obtained from different GCN pipelines. Extensive experiments are conducted on seven real-world datasets. Notably, GLAC-GCN achieves the best ACC (or NMI) scores on all (or five) of the seven datasets, demonstrating its superiority over the state-of-the-art approaches. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Joint Entity and Relation Extraction Based on Prompt Learning and Multi-channel Heterogeneous Graph Enhancement 22

Joint Entity and Relation Extraction Based on Prompt Learnin...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Lv, Haiqing Han, Xiaohui Wang, Peipei Zuo, Wenbo Guo, Jing Xu, Lijuan Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China Quan Cheng Laboratory Jinan China Jinan China

ISBN: (纸本)9798331509712

Joint extraction of entity and relation is crucial in information extraction, aiming to extract all relation triples from unstructured text. However, current joint extraction methods face two main issues. Firstly, they rarely consider the semantic information of entity and relation labels, leading to models that fail to fully understand and utilize the rich semantics in these labels, thereby limiting their performance. Secondly, although table-filling methods are widely used, they focus only on the start or end positions and ignore deep interactions between tables, relying solely on word-level information. To address these issues, we propose the P-MHE framework based on prompt learning and multi-channel heterogeneous graph enhancement. First, we use prompt templates to construct semantic nodes for entity and relation type labels, initializing them along with words as nodes in a heterogeneous graph. We iteratively fuse these semantic nodes through a message-passing mechanism to obtain node representations suitable for entity and relation extraction tasks. Secondly, we design a multi-channel heterogeneous graph to model node relationships from different perspectives, enhancing feature interactions among different types of nodes. Finally, we aggregate the semantic node information of entity and relation type labels after iteration, constructing separate decoding tables for each entity and relation type to better adapt to their respective characteristics. We evaluated our model on four public datasets. Experimental results show that P-MHE outperforms existing models on multiple public datasets. Extensive additional experiments further validate the effectiveness of our model. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Tjong:A transformer‐based Mahjong AI via hierarchical decision‐making and fan backward

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 982-995页

作者： Xiali Li Bo Liu Zhi Wei Zhaoqi Wang Licheng Wu School of Information and Engineering Minzu University of ChinaBeijingChina Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE Minzu University of ChinaBeijingChina Department of Computer Science New Jersey Institute of TechnologyNewarkNew JerseyUSA

Mahjong,a complex game with hidden information and sparse rewards,poses significant *** Mahjong AIs require substantial hardware resources and extensive datasets to enhance AI *** authors propose a transformer‐based Mahjong AI(Tjong)via hierarchical decision‐*** utilising self‐attention mechanisms,Tjong effectively captures tile patterns and game dynamics,and it decouples the decision pro-cess into two distinct stages:action decision and tile *** design reduces de-cision complexity ***,a fan backward technique is proposed to address the sparse rewards by allocating reversed rewards for actions based on winning *** consists of 15M parameters and is trained using approximately 0.5 M data over 7 days of supervised learning on a single server with 2 *** action decision achieved an accuracy of 94.63%,while the claim decision attained 98.55%and the discard decision reached 81.51%.In a tournament format,Tjong outperformed AIs(CNN,MLP,RNN,ResNet,VIT),achieving scores up to 230%higher than its ***-more,after 3 days of reinforcement learning training,it ranked within the top 1%on the leaderboard on the Botzone platform.

关键词： decision making deep learning deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Asymptotics-Aware Multi-View Subspace Clustering

引用

IEEE Transactions on Multimedia 2025年 27卷 3650-3663页

作者： Xu, Yesong Chen, Shuo Li, Jun Yang, Jian Anhui Polytechnic University School of Computer and Information Wuhu241000 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Nanjing University of Science and Technology PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

Recently, multi-view subspace clustering has attracted extensive attention due to the rapid increase of multi-view data in many real-world applications. The main goal of this task is to learn a common representation of multiple subspaces from the given multi-view data, and most existing methods usually directly merge multiple groups of features by the single-step integration. However, there may exist large disparities among different views of the data, and thus the conventional single-step practice can hardly obtain a generally consistent feature representation for the multi-view data. To overcome this challenge, we present a novel approach dubbed "Asymptotics-Aware Multi-view Subspace Clustering (A2 MSC)"to pursue a consistent feature representation in a multi-step way, which iteratively conducts the data recovery to gradually reduce the differences between pairwise views. Specifically, we construct an asymptotic learning rule to update the feature representation, and the iteration result converges to a consistent feature vector for characterizing each instance of the original multi-view data. After that, we utilize such a new feature representation to learn a clustering-oriented similarity matrix via minimizing a self-expressive objective, and we also design the corresponding optimization algorithm to solve it with convergence guarantees. Theoretically, we prove that the learned asymptotic representation effectively integrates multiple views, thereby ensuring the effective handling of multi-view data. Empirically, extensive experimental results demonstrate the superiority of our proposed A2 MSC over the state-of-the-art multi-view subspace clustering approaches. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Time-Varying Workload Scheduling With Priority and Resource Awareness

引用

IEEE Transactions on network and Service Management 2025年第3期22卷 2838-2852页

作者： Liu, Qifeng Fan, Qilin Zhang, Xu Li, Xiuhua Wang, Kai Xiong, Qingyu Chongqing University School of Big Data and Software Engineering Chongqing400044 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing400044 China Nanjing University School of Electronic Science and Engineering Nanjing210023 China Haihe Laboratory of Information Technology Application Innovation Tianjin300072 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China Shandong Key Laboratory of Industrial Network Security Weihai264209 China

With the proliferation of cloud services and the continuous growth in enterprises' demand for dynamic multi-dimensional resources, the implementation of effective strategy for time-varying workload scheduling has become increasingly significant. In this paper, we propose a deep reinforcement learning (DRL)-based method for time-varying workload scheduling, aiming to allocate resources efficiently across servers in the cluster. Specifically, we integrate a classifier and queue scorer to construct a priority queue that exploits temporal resource utilization patterns across different workload classes. Then, we design parallel graph attention layers to capture the dimensional features and temporal dynamics of cloud server cluster. Moreover, we propose a DRL algorithm to generate scheduling strategies that can adapt to dynamic environments. Validation on real-world traces from Google cluster demonstrates that our method outperforms existing approaches in key metrics of cloud server cluster management. © 2004-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

A Pseudonym Exchange-Based Traceable Location Privacy Protection Scheme for IoV

A Pseudonym Exchange-Based Traceable Location Privacy Protec...

引用

2023 International Conference on networking and network Applications, NaNA 2023

作者： Ma, Weigang Yu, Yaping Wang, Yichuan Liu, Xiaoxue Wang, Zhoukai School of Computer Science and Engineering Xi'an University of Technology Xi'an China Shaanxi Key Laboratory for Network Computing and Security Technology China

ISBN: (纸本)9798350327380

Internet of Vehicles (IoV) is a network built by communicating entities such as vehicles and roadside infrastructure, etc. The entities can communicate with each other, sharing data and providing services. However, the openness and interoperability (location services) of IoV makes the communication entity vulnerable to attacks. when the vehicle requests location services, it will expose its own location information, which will cause serious personal safety problems. To address the location privacy leakage problem in the IoV, this paper proposes a pseudonym exchange-based traceable location privacy protection scheme for IoV. Our scheme not only provides location privacy protection, but has the following properties: First, the whole pseudonym exchange process does not require trusted third-party participation;Second, each vehicle performs a series of hash operations on several dynamic anonyms and obtains a corresponding fixed-length hash value as the corresponding account in order to cut off the connection between the real identity, which is different in each run. If a vehicle is compromised and utilized to launch attack, the trusted center (CA) can also recover his/her real identity;Last, the experimental results show that the pseudonym exchange process and pseudonym update process cost less time compared to relevant literature. Hence, these features make our scheme very suitable for computation-limited mobile devices compared with other related existing schemes. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Tensor Factorization for Accurate Anomaly Detection in Dynamic networks

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年第3期10卷 439-450页

作者： Li, Xiaocan Wen, Jigang Xie, Kun Xie, Gaogang Liang, Wei Hunan University College of Computer Science Electronics Engineering Changsha410012 China Ministry of Education Key Laboratory of Supercomputing Artificial Intelligence Fusion Computing Changsha410012 China School of Computer Science Engineering Hunan University of Science Technology Xiangtan411199 China Chinese Academy of Sciences Computer Network Information Center Beijing411199 China

Accurately detecting traffic anomalies becomes increasingly crucial in network management. Algorithms that model the traffic data as a matrix suffers from low detection accuracy, while the work using the tensor model often assumes the tensor is regular without considering that network nodes may dynamically join in or leave, which will fail in a practical network with the change of node set as a result of mobility and churn behaviors. We propose a novel Tensor Recovery scheme in a Dynamic network (TRDN) with traffic data modeled as a practical irregular tensor for accurate anomaly detection. To take advantage of correlations among small tensors, each formed with a short time duration to capture more hidden information in the data for higher detection accuracy, we propose several novel techniques: 1) a new joint tensor factorization model to capture the characteristic shared by the common nodes of small tensors, 2) a tensor partition algorithm to identify the data that can be applied to train the shared parameters efficiently, and 3) a bar-based algorithm that partitions nodes into the minimum number of no-overlapping subsets to form the shared tensor model. Extensive experiments on two Internet traffic data sets, Abilene and GÈANT, demonstrate the effectiveness of the proposed TRDN. © 2016 IEEE.

关键词： Data accuracy

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：