检索结果-内蒙古大学图书馆

39th IEEE International Conference on data engineering, ICDE 2023

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Xi'an Jiaotong University Department of Computer Science and Technology China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Xi'an Jiaotong University Department of Distance Education China Beihang University School of Software China Beihang University Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9798350322279

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Resource Management in Blockchain-Enabled Federated Learning Network

IEEE Networking Letters

引用

IEEE Networking Letters 2022年第3期4卷 137-141页

作者： Hieu, Nguyen Quang Tran, The Anh Nguyen, Cong Luong Niyato, Dusit Kim, Dong In Elmroth, Erik University of Technology Sydney School of Electrical and Data Engineering SydneyNSW2007 Australia Nanyang Technological University School of Computer Science and Engineering Jurong West Singapore Phenikaa University Faculty of Computer Science Hanoi10000 Viet Nam Sungkyunkwan University Department of Electrical and Computer Engineering Seoul16419 Korea Republic of Umeå University Department of Computing Science Umeå901 87 Sweden

Blockchain-enabled Federated Learning (BFL) enables model updates to be stored in blockchain in a reliable manner. However, one problem is the increase of the training latency due to the mining process. Moreover, mobile devices have energy and CPU constraints. Therefore, the machine learning model owner (MLMO) needs to decide the data and energy that the mobile devices use for the training and determine the block generation rate to minimize the system latency and mining cost while achieving the target accuracy. Under the uncertainty of BFL, we propose to use deep reinforcement learning to find the optimal decisions for the MLMO. © 2019 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

Securely Fine-tuning Pre-trained Encoders Against Adversaria...

引用

IEEE Symposium on Security and Privacy

作者： Ziqi Zhou Minghui Li Wei Liu Shengshan Hu Yechao Zhang Wei Wan Lulu Xue Leo Yu Zhang Dezhong Yao Hai Jin 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 School of Software Engineering Huazhong University of Science and Technology 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

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the *** this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six d

关键词： Training Adaptation models Sensitivity Accuracy Self-supervised learning Genetics Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Network Adaptive Situation Awareness Method in Spatio-Temporal Dimension 1

引用

1st International Artificial Intelligence Conference, IAIC 2023

作者： Zhang, Hongbin Xu, Ying Liu, Bin Zhao, Dongmei Bai, Yikang School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang050000 China Hebei Key Laboratory of Network and Information Security Hebei Normal University Hebei Shijiazhuang050024 China School of Economics and Management Hebei University of Science and Technology Shijiazhuang050000 China Research Center of Big Data and Social Computing Hebei University of Science Shijiazhuang China

ISBN: (数字)9789819713325

ISBN: (纸本)9789819713318

In large-scale networks, the state space is exploding and changing dynamically. This leads to difficulties in collecting and analyzing situational awareness data, so we construct an adaptive situational awareness model in spatio-temporal dimensions. In the spatial dimension, vulnerabilities’s threats are assessed through attack graphs combined with Shapley values. At the same time, vulnerability threats are dynamically quantified by updating the status node reachability probability in real time. In the temporal dimension, a game model is established by analyzing vulnerability attack graph nodes to dynamically adjust the observation frequency of high-risk vulnerabilities, focusing on the safety status characteristics of high-risk assets. Experimental results show that our proposal integrates the security features of both space and time dimensions. This method can better focus on high-risk vulnerabilities and accurately reflect the dynamic changes in the network security situation, ensuring timeliness and accuracy in network security detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Advancements in Chatbot Technology: Enhancing User Experience through AI and NL

Advancements in Chatbot Technology: Enhancing User Experienc...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Arora, Yojna Singh, Ajeet Sharma, Abhay Aggarwal, Nitin Bansal, Nidhi Sharda University Department of Computer Science & Engineering Greater Noida India Moradabad Institute of Technology Department of Computer Science & Engineering Uttar Pradesh Moradabad India School of Computing and Intelligent System Manipal University Jaipur Department of IoT & IS Rajasthan Jaipur India Supervisor Oracle Development Database Admin Data Science PA United States Pune India

ISBN: (纸本)9798331517953

A chatbot is an AI-powered software or application designed to communicate with people. This technology can perform a variety of tasks, including providing instant responses and answers to users, delivering information, assisting with purchasing products, and enhancing customer service. In my paper, I present the fundamental principles and essential concepts of computing related to chatbots and its applications various sectors like Education, E commerce, Entertainment, Healthcare, Telecommunication, Customer Service etc. The paper also mentions detailed literature explain the contribution by various researchers in this fields. Architecture and step wise approach of creating a chatbot is presented lately. © 2024 IEEE.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Intelligent Network Optimisation for Beyond 5G Networks Considering Packet Drop Rate 25

Intelligent Network Optimisation for Beyond 5G Networks Cons...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： Mahmoud, Haitham Aneiba, Adel He, Ziming Tong, Fei Guo, Liucheng Asyhari, Taufiq Wang, Ziwei Gao, Zhen College Of Computing Birmingham City University Birmingham United Kingdom Samsung Cambridge Solution Centre System Lsi Samsung Electronics Cambridge United Kingdom London United Kingdom Monash University Data Science Department Tangerang Indonesia School Of Engineering Lancaster University Lancaster United Kingdom School Of Information And Electronics Beijing Institute Of Technology Beijing China

ISBN: (纸本)9798350340266

To meet the growing expectations for fast and dependable connectivity, Novel approaches such as reinforcement learning-based resource allocation and network slicing are essential to consider. Enhancing network intelligence through the use of deep reinforcement learning and machine learning may increase capacity, lower latency and congestion, improve energy efficiency, and open up new revenue opportunities and business models. However, the current body of research falls short in terms of thoroughly exploring network slicing datasets and taking packet drop likelihood into account when allocating resources. With reference to current benchmarks, this paper presents a network slicing strategy and illustrates its efficacy using seven machine learning algorithms (ANN, SVM, RF, DT, GNG, LDA, and RT). To prioritize packets that run the risk of being dropped, a priority algorithm is also developed. To improve network performance, a resource allocation technique is used that is based on the mathematical study of packet drop rate. Utilizing deep reinforcement learning and genetic algorithms, the distribution of tasks across Cloud and Edge resources is further improved according to network slice characteristics. In spite of high network traffic, this guarantees constant service availability. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: vivid multi-colored hair editing via latent diffusion 24

HairDiffusion: vivid multi-colored hair editing via latent d...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yu Zeng Yang Zhang Jiachen Liu Linlin Shen Kaijun Deng Weizhao He Jinbao Wang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University and Shenzhen Institute of Artificial Intelligence and Robotics for Society and National Engineering Laboratory for Big Data System Computing Technology Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University and Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond black-box advice: learning-augmented algorithms for MDPs with Q-value predictions 23

Beyond black-box advice: learning-augmented algorithms for M...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Tongxin Li Yiheng Lin Shaolei Ren Adam Wierman School of Data Science CUHK-SZ China Computing + Mathematical Sciences Caltech Electrical & Computer Engineering UC Riverside

We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice. Our work departs from the typical approach of treating advice as coming from black-box sources by instead considering a setting where additional information about how the advice is generated is available. We prove a first-of-its-kind consistency and robustness tradeoff given Q-value advice under a general MDP model that includes both continuous and discrete state/action spaces. Our results highlight that utilizing Q-value advice enables dynamic pursuit of the better of machine-learned advice and a robust baseline, thus result in near-optimal performance guarantees, which provably improves what can be obtained solely with black-box advice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unified Graph Augmentations for Generalized Contrastive Learning on Graphs 38

Unified Graph Augmentations for Generalized Contrastive Lear...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhuo, Jiaming Lu, Yintong Ning, Hui Fu, Kun Niu, Bingxin He, Dongxiao Wang, Chuan Guo, Yuanfang Wang, Zhen Cao, Xiaochun Yang, Liang Hebei Province Key Laboratory of Big Data Calculation School of Artificial Intelligence Hebei University of Technology Tianjin China College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science and Technology Beijing JiaoTong University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Cybersecurity Northwestern Polytechnical University Xi'an China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen China

In real-world scenarios, networks (graphs) and their tasks possess unique characteristics, requiring the development of a versatile graph augmentation (GA) to meet the varied demands of network analysis. Unfortunately, most Graph Contrastive Learning (GCL) frameworks are hampered by the specificity, complexity, and incompleteness of their GA techniques. Firstly, GAs designed for specific scenarios may compromise the universality of models if mishandled. Secondly, the process of identifying and generating optimal augmentations generally involves substantial computational overhead. Thirdly, the effectiveness of the GCL, even the learnable ones, is constrained by the finite selection of GAs available. To overcome the above limitations, this paper introduces a novel unified GA module dubbed UGA after reinterpreting the mechanism of GAs in GCLs from a message-passing perspective. Theoretically, this module is capable of unifying any explicit GAs, including node, edge, attribute, and subgraph augmentations. Based on the proposed UGA, a novel generalized GCL framework dubbed Graph cOntrastive UnifieD Augmentations (GOUDA) is proposed. It seamlessly integrates widely adopted contrastive losses and an introduced independence loss to fulfill the common requirements of consistency and diversity of augmentation across diverse scenarios. Evaluations across various datasets and tasks demonstrate the generality and efficiency of the proposed GOUDA over existing state-of-the-art GCLs. © 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

MISA: Unveiling the Vulnerabilities in Split Federated Learning

MISA: Unveiling the Vulnerabilities in Split Federated Learn...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

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

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of *** this paper, we present a novel poisoning attack known as $\color{Fuchsia} {{\text{MISA}}}$. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.

关键词：

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：