检索结果-内蒙古大学图书馆

Robust Regularization Design of Graph Neural Networks Against Adversarial Attacks Based on Lyapunov Theory

Chinese Journal of Electronics 2024年第3期33卷 732-741页

作者： Wenjie YAN Ziqi LI Yongjun QI School of Artificial Intelligence Hebei University of Technology School of Computer Science and Engineering of North China Institute of Aerospace Engineering

The robustness of graph neural networks（GNNs） is a critical research topic in deep *** researchers have designed regularization methods to enhance the robustness of neural networks,but there is a lack of theoretical analysis on the principle of *** order to tackle the weakness of current robustness designing methods,this paper gives new insights into how to guarantee the robustness of GNNs.A novel regularization strategy named Lya-Reg is designed to guarantee the robustness of GNNs by Lyapunov *** results give new insights into how regularization can mitigate the various adversarial effects on different graph *** experiments on various public datasets demonstrate that the proposed regularization method is more robust than the state-of-theart methods such as L1-norm,L2-norm,L2-norm,Pro-GNN,PA-GNN and GARNET against various types of graph adversarial attacks.

关键词： Deep learning Graph neural network Robustness Lyapunov Regularization

来源：评论

学校读者我要写书评

暂无评论

A Novel Predictive Model for Edge Computing Resource Scheduling Based on Deep Neural Network

引用

computer Modeling in engineering & sciences 2024年第4期139卷 259-277页

作者： Ming Gao Weiwei Cai Yizhang Jiang Wenjun Hu Jian Yao Pengjiang Qian School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214122China The Center for Intelligent Systems and Applications Research School of Artificial Intelligence and Computer ScienceJiangnan UniversityWuxi214122China School of Information Engineering Huzhou UniversityHuzhou313000China

Currently,applications accessing remote computing resources through cloud data centers is the main mode of operation,but this mode of operation greatly increases communication latency and reduces overall quality of service(QoS)and quality of experience(QoE).Edge computing technology extends cloud service functionality to the edge of the mobile network,closer to the task execution end,and can effectivelymitigate the communication latency ***,the massive and heterogeneous nature of servers in edge computing systems brings new challenges to task scheduling and resource management,and the booming development of artificial neural networks provides us withmore powerfulmethods to alleviate this ***,in this paper,we proposed a time series forecasting model incorporating Conv1D,LSTM and GRU for edge computing device resource scheduling,trained and tested the forecasting model using a small self-built dataset,and achieved competitive experimental results.

关键词： Edge computing resource scheduling predictive models

来源：评论

学校读者我要写书评

暂无评论

Robust video question answering via contrastive cross-modality representation learning

引用

science China(Information sciences) 2024年第10期67卷 211-226页

作者： Xun YANG Jianming ZENG Dan GUO Shanshan WANG Jianfeng DONG Meng WANG School of Information Science and Technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center School of Computer Science and Information Engineering Hefei University of Technology Institutes of Physical Science and Information Technology Anhui University School of Computer Science and Technology Zhejiang Gongshang University

Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts, recent studies revealed that current VideoQA models mostly tend to over-rely on the superficial correlations rooted in the dataset bias while overlooking the key video content, thus leading to unreliable results. Effectively understanding and modeling the temporal and semantic characteristics of a given video for robust VideoQA is crucial but, to our knowledge, has not been well investigated. To fill the research gap, we propose a robust VideoQA framework that can effectively model the cross-modality fusion and enforce the model to focus on the temporal and global content of videos when making a QA decision instead of exploiting the shortcuts in datasets. Specifically, we design a self-supervised contrastive learning objective to contrast the positive and negative pairs of multimodal input, where the fused representation of the original multimodal input is enforced to be closer to that of the intervened input based on video perturbation. We expect the fused representation to focus more on the global context of videos rather than some static keyframes. Moreover, we introduce an effective temporal order regularization to enforce the inherent sequential structure of videos for video representation. We also design a Kullback-Leibler divergence-based perturbation invariance regularization of the predicted answer distribution to improve the robustness of the model against temporal content perturbation of videos. Our method is model-agnostic and can be easily compatible with various VideoQA backbones. Extensive experimental results and analyses on several public datasets show the advantage of our method over the state-of-the-art methods in terms of both accuracy and robustness.

关键词： video question answering cross-modality fusion contrastive learning cross-media reasoning

来源：评论

学校读者我要写书评

暂无评论

Explaining the better generalization of label distribution learning for classification

引用

science China(Information sciences) 2025年第5期68卷 348-361页

作者： Jing WANG Xin GENG School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications(Southeast University) Ministry of Education

Label distribution learning(LDL) has shown advantages over traditional single-label learning(SLL) in many realworld applications, but its superiority has not been theoretically understood. In this paper, we attempt to explain why LDL generalizes better than SLL. Label distribution has rich supervision information such that an LDL method can still choose the sub-optimal label from label distribution even if it neglects the optimal one. In comparison, an SLL method has no information to choose from when it fails to predict the optimal label. The better generalization of LDL can be credited to the rich information of label distribution. We further establish the label distribution margin theory to prove this explanation; inspired by the theory,we put forward a novel LDL approach called LDL-LDML. In the experiments, the LDL baselines outperform the SLL ones, and LDL-LDML achieves competitive performance against existing LDL methods, which support our explanation and theories in this paper.

关键词： label distribution learning classification generalization label distribution margin label ambiguity neural network

来源：评论

学校读者我要写书评

暂无评论

Secure container Orchestration: A framework for detecting and mitigating Orchestrator - level vulnerabilities

引用

Multimedia Tools and Applications 2025年第17期84卷 18351-18371页

作者： Mahavaishnavi, V. Saminathan, R. Prithviraj, R. Department of Artificial Intelligence and Data Science Panimalar Engineering College Tamil Nadu Chennai600123 India Department of Computer Science and Engineering Annamalai University Chidambaram India Department of Computer Science and Engineering Annamalai University Chidambaram India

This paper presents Secure Orchestration, a novel framework meticulously planned to uphold rigorous security measures over the profound security concerns that lie within the container orchestration platforms, especially in Kubernetes. The widespread adoption of containerized environments has raised concerns about the vulnerabilities at the level of the orchestrator. Secure Orchestration delivers a comprehensive approach by leveraging cutting-edge methods to detect and prevent the exposure of vulnerabilities from orchestrator misconfigurations, privilege escalation exploits that can thwart the orchestration security layer, and unauthorized access attempts targeting the orchestration system itself. In addition, it is further strengthened by deploying an Intrusion Detection and Prevention System (IDPS), which is responsible for actively monitoring the orchestration infrastructure. The IDPS utilizes sophisticated algorithms and mechanisms for detecting anomalies to continuously assess the orchestration environment for indications of intrusion, vulnerabilities, and anomalous activities. By using this proactive approach, the framework is able to rapidly identify potential threats and respond through countermeasures in a timely manner, thus greatly reducing the risks associated with orchestrator level vulnerabilities. Conducting a set of real-world experiments that closely simulate a variety of threat scenarios is imperative for empirically validating the efficiency of this framework. The obtained empirical results yield insightful revelations on the efficacy of the framework in accurately identifying and mitigating vulnerabilities, thereby ensuring the privacy and integrity of container orchestration systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Improving Crop Recommendations with Augmented Reality and Sensor Data Analysis 2

Improving Crop Recommendations with Augmented Reality and Se...

引用

2nd International Conference of Intelligent Methods, Systems and Applications, IMSA 2024

作者： Ghanem, Sahar I. Zaalouk, Moustafa Elbanna, Asmaa Pharos University in Alexandria Computer Science and Artificial Intelligence Faculty Artificial Intelligence Department Egypt

ISBN: (纸本)9798350362633

The decision about the selection of crops for agricultural production is closely related to many different aspects, such as the features of the soil and the surrounding environment. Using state-of-the-art sensor technology, these factors are measured with extreme caution, some significant metrics include soil pH, moisture level, and the surrounding temperature. These sensor-driven collected information are analyzed by expertly deploying robust machine learning algorithms, which leads to an accurate estimation of the best crop categories for the climatic circumstances. In this agricultural paradigm, augmented reality perceived as a game-changing tool that offers a fully immersive display of the sensor data, providing farmers an extensive awareness of the crop environment. In addition to automating the crop selection process, this smart combination of sensor technologies, machine learning with overall accuracy of 97%, and augmented reality offers farmers the insights they need to make appropriate choices and ensures sustainable agricultural practices. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

T5-LDSum: Leveraging T5 Transformer in Hybrid Abstractive-Extractive Long Document Summarization 6

T5-LDSum: Leveraging T5 Transformer in Hybrid Abstractive-Ex...

引用

6th IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2024

作者： Magdy, Mostafa Abdelbaky, Abdelrahman M. Mohamed, Ensaf Hussein Helwan University Master of Computer Science Faculty of Computers and Artificial Intelligence Egypt Helwan University Bachelor of Computer Science Faculty of Computers and Artificial Intelligence Egypt Nile University Computer Science School of Information Technology and Computer Science Giza Egypt Helwan University Faculty of Computers and Artificial Intelligence Computer Science Department Egypt

ISBN: (纸本)9798350378511

In the era of digital information overload, the ability to summarize books efficiently emerges as an invaluable skill. Book summarization condenses extensive texts into digestible, concise summaries, enabling readers to grasp the essence of a book without committing to reading it in its entirety. In scholarly research, various techniques for text summarization are employed, including extractive summarization, abstractive summarization, and hybrid approaches. This paper presents a novel hybrid method that leverages the strengths of both extractive and abstractive techniques, with a particular focus on the T5 text-to-text transformer model. Our methodology begins with a BERT-based extractive model paired with the LexRank algorithm to generate preliminary summaries. These summaries are subsequently refined using the T5 transformer model, known for its powerful text generation capabilities. We conducted two empirical studies using Oscar Wilde's 'The Picture of Dorian Gray,' specifically focusing on Chapter 13. Our experiments analyzed the efficacy of summaries derived from the top 20% and top 60% of sentences ranked by the extractive model. The findings indicate a consistent pattern: summaries based on the 60% sentence extraction significantly outperform those from the 20% extraction across all assessed metrics-Rouge, precision, recall, F1 scores, and human evaluations. The integration of the T5 transformer model in the refinement process is highlighted as a key component in achieving high-quality, coherent summaries. © 2024 IEEE.

关键词： abstractive summarization Book summarization evaluation metrics extractive summarization hybrid summarization

来源：评论

学校读者我要写书评

暂无评论

A Variational Inference-Based LSTM-enhanced Deep Neural Model for Sequential Recommendations

引用

IEEE Access 2025年 13卷 95945-95962页

作者： Ngaffo, Armielle Noulapeu Kamgang, Ines Raissa Djouela Maka, Ebenezer Maka Malong, Yannick University of Douala Laboratory of Computer Science Data Science and Artificial Intelligence National Higher Polytechnic School of Douala Douala8580 Cameroon Department of computer engineering University of Buea Faculty of Engineering and Technology Cameroon

Long Short-Term Memory (LSTM) networks are particularly useful in recommender systems since user preferences change over time. Unlike traditional recommender models which assume static user-item interactions, LSTM models capture sequential dependencies and temporal dynamics, making them ideal for personalized, session-based, and sequential recommendation tasks. However, traditional LSTM-based recommender systems do not model uncertainty since they perform deterministic predictions. Moreover, those recommender models exhibit poor generalization on small datasets, and poor-handle cold-start and data sparsity problems. To overcome those limitations, this paper presents an LSTM-based recommender model that leverages an improved deep matrix factorization to accurately address the data sparsity problem. In addition, an enhanced variational inference coupled to the Evidence Lower Bound Optimization is applied on LSTM unit layers to perform uncertainty-aware predictions. Thereafter, latent vectors obtained from LSTM networks are effectively involved in the sequential recommendation process. Experiments have been conducted on several real-world datasets to evaluate our proposal and the results show the proposed model presents significant performances compared to state-of-the-art models. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantic-aware entity alignment for low resource language knowledge graph

引用

Frontiers of computer science 2024年第4期18卷 97-106页

作者： Junfei TANG Ran SONG Yuxin HUANG Shengxiang GAO Zhengtao YU Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500China

Entity alignment(EA)is an important technique aiming to find the same real entity between two different source knowledge graphs(KGs).Current methods typically learn the embedding of entities for EA from the structure of KGs for *** EA models are designed for rich-resource languages,requiring sufficient resources such as a parallel corpus and pre-trained language ***,low-resource language KGs have received less attention,and current models demonstrate poor performance on those low-resource ***,researchers have fused relation information and attributes for entity representations to enhance the entity alignment performance,but the relation semantics are often *** address these issues,we propose a novel Semantic-aware Graph Neural Network(SGNN)for entity ***,we generate pseudo sentences according to the relation triples and produce representations using pre-trained ***,our approach explores semantic information from the connected relations by a graph neural *** model captures expanded feature information from *** results using three low-resource languages demonstrate that our proposed SGNN approach out performs better than state-of-the-art alignment methods on three proposed datasets and three public datasets.

关键词： graph neural network knowledge graph entity alignment low-resource language

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Trainer-Based Deep Q-Network for Dynamic Flexible Job Shop Scheduling

引用

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

作者： Liu, Yun Zhang, Fangfang Sun, Yanan Zhang, Mengjie College of Computer Science Sichuan University Chengdu PR China Center for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

Dynamic flexible job shop scheduling (DFJSS) aims to achieve the optimal efficiency for production planning in the face of dynamic events. In practice, deep Q-network (DQN) algorithms have been intensively studied for solving various DFJSS problems. However, these algorithms often cause moving targets for the given job-shop state. This will inevitably lead to unstable training and severe deterioration of the performance. In this paper, we propose a training algorithm based on genetic algorithm to efficiently and effectively address this critical issue. Specifically, a state feature extraction method is first developed, which can effectively represent different job shop scenarios. Furthermore, a genetic encoding strategy is designed, which can reduce the encoding length to enhance search ability. In addition, an evaluation strategy is proposed to calculate a fixed target for each job-shop state, which can avoid the parameter update of target networks. With the designs, the DQNs could be stably trained, thus their performance is greatly improved. Extensive experiments demonstrate that the proposed algorithm outperforms the state-of-the-art peer competitors in terms of both effectiveness and generalizability to multiple scheduling scenarios with different scales. In addition, the ablation study also reveals that the proposed algorithm can outperform the DQN algorithms with different updating frequencies of target networks. IEEE

关键词： Job shop scheduling

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：