检索结果-内蒙古大学图书馆

19th International Conference on advanced Data Mining and Applications, ADMA 2023

作者： Zhao, Haijun Xu, Ronghai Wang, Chang-Dong Jiang, Ying School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9783031466601

Click-Through Rate (CTR) prediction is a critical problem in recommendation systems since it involves enormous business interest. Most deep CTR model follows an Embedding & Feature Interaction paradigm. However, the feature interaction module cannot work well without a good embedding representation of features. Due to the long-tail phenomenon in real scenes, few samples are provided in the dataset for a large proportion of features. In this paper, we present ProtoMix, a model-agnostic framework for learnable data augmentation on few-shot features in CTR prediction. ProtoMix automatically extracts information from co-occurred features within the same instance to assign prototype embedding with vector quantization for few-shot features and further synthesize the embedding representation of the augmented virtual instance for training. Original embedding, feature interaction module, and the embedding generator are jointly trained on a well-designed objective in an end-to-end manner in ProtoMix. We experimentally validate the effectiveness and compatibility of ProtoMix by comparing it with baseline and other data augmentation methods on different deep CTR models and multiple real-world CTR benchmark datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

ALGCN: Accelerated Light Graph Convolution Network for Recommendation 28th

ALGCN: Accelerated Light Graph Convolution Network for Reco...

引用

28th International Conference on Database Systems for advanced Applications, DASFAA 2023

作者： Xu, Ronghai Zhao, Haijun Li, Zhi-Yuan Wang, Chang-Dong School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Beijing China

ISBN: (纸本)9783031306716

Recently, Graph Convolutional Network (GCN) has been widely applied in the field of collaborative filtering (CF) with tremendous success, since its message-passing mechanism can efficiently aggregate neighborhood information between users and items. However, most of the existing GCN-based CF models suffer from low convergence rates during training, mainly because they follow the design of standard GCN using a simple uniform average to aggregate the neighborhood information. We also find that the scale of embedding across different layers oscillates. We argue that these issues can be alleviated by our proposed graph convolution framework, namely Accelerated Light Graph Convolutional Network (ALGCN). ALGCN mainly contains two components: influence-aware graph convolution operation and augmentation-free in-batch contrastive loss on the unit sphere. Empirical evaluations on three large and public datasets demonstrate that the proposed method achieves remarkable training speedups over LightGCN and substantially outperforms the state-of-the-art GCN-based CF models. Our method also shows a great improvement in long-tail recommendation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Obtaining Electromagnetic Properties of Multi-Type Media in Realistic Environments:State-of-the-Art and Prospects

引用

China Communications 2025年第1期22卷 25-40页

作者： Guo Lantu Guan Ke Liu Ting He Danping Zhang Haixia Zhu Qiuming Lu Jun Zhang Minggao China Research Institute of Radiowave Propagation Qingdao 266107China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong UniversityBeijing 100044China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Control Science and Engineering Shandong UniversityJinan 250061China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Jinan 250061China College of Electronic and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China Jiaxing University Jiaxing 314001China

To meet the requirements of electromagnetic(EM)theory and applied physics,this study presents an overview of the state-of-the-art research on obtaining the EM properties of media and points out potential solutions that can break through the bottlenecks of current ***,based on the survey of three mainstream approaches for acquiring EM properties of media,we identify the difficulties when implementing them in realistic *** a focus on addressing these problems and challenges,we propose a novel paradigm for obtaining the EM properties of multi-type media in realistic ***,within this paradigm,we describe the implementation approach of the key technology,namely“multipath extraction using heterogeneous wave propagation data in multi-spectrum cases”.Finally,the latest measurement and simulation results show that the EM properties of multi-type media in realistic environments can be precisely and efficiently acquired by the methodology proposed in this study.

关键词： electromagnetic properties of media multi-type media parameter inversion ray tracing realistic environment

来源：评论

学校读者我要写书评

暂无评论

引用

4th International Conference on Computer Information Science and Artificial Intelligence, CISAI 2021

作者： Zhu, DI Pang, Jianmin Zhou, Xin Han, Wenjie Zhengzhou University Zhengzhou450002 China Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450002 China

ISBN: (纸本)9781665406925

As the mainstream of smart contract research, most Ethereum smart contracts do not open their source code, and the bytecode of smart contracts has attracted the attention of researchers. Based on the similarity measurement of smart contract bytecode, a series of tasks such as vulnerability mining, contract upgrading and malicious contract detection can be carried out. This paper proposes a method to measure the similarity of smart contract bytecode. Firstly, the key opcode combination of smart contract is summarized. When traversing the CFG(control flow graph) constructed by decompilation of smart contract bytecode, the opcodes in the basic block are pattern matched, and the features between the basic blocks are extracted according to the in-out degree, so as to enhance the similarity measurement effect of contract semantics in vector space. The experimental results show that the proposed method is greatly improved compared with the baseline. © 2021 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Pixel+ and Pixel++: compact and efficient forward-secure multi-signatures for PoS blockchain consensus 24

Pixel+ and Pixel++: compact and efficient forward-secure mul...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Jianghong Wei Guohua Tian Ding Wang Fuchun Guo Willy Susilo Xiaofeng Chen State Key Laboratory of Integrated Service Networks (ISN) Xidian University and State Key Laboratory of Mathematical Engineering and Advanced Computing State Key Laboratory of Integrated Service Networks (ISN) Xidian University College of Cyber Science Nankai University School of Computing and Information Technology University of Wollongong

ISBN: (纸本)9781939133441

Multi-signature schemes have attracted considerable attention in recent years due to their popular applications in PoS blockchains. However, the use of general multi-signature schemes poses a critical threat to the security of PoS blockchains once signing keys get corrupted. That is, after an adversary obtains enough signing keys, it can break the immutable nature of PoS blockchains by forking the chain and modifying the history from some point in the past. Forward-secure multi-signature (FS-MS) schemes can overcome this issue by periodically updating signing keys. The only FS-MS construction currently available is Drijvers et al's Pixel, which builds on pairing groups and only achieves forward security at the time period *** this work, we present new FS-MS constructions that either are free from pairing or capture forward security at the individual message level (i.e., fine-grained forward security). Our first construction Pixel+ works for a maximum number of time periods T. Pixel+ signatures consist of only one group element, and can be verified using two exponentiations. It is the first FS-MS from RSA assumption, and has 3.5x and 22.8x faster signing and verification than Pixel, respectively. Our second FS-MS construction Pixel++ is a pairing-based one. It immediately revokes the signing key's capacity of re-signing the message after creating a signature on this message, rather than at the end of the current time period. Thus, it provides more practical forward security than Pixel. On the other hand, Pixel++ is almost as efficient as Pixel in terms of signing and verification. Both Pixel+ and Pixel++ allow for non-interactive aggregation of signatures from independent signers and are proven to be secure in the random oracle model. In addition, they also support the aggregation of public keys, significantly reducing the storage overhead on PoS *** demonstrate how to integrate Pixel+ and Pixel++ into PoS blockchains. As a proof-of-concept, we provid

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pruned-F1DCN: A lightweight network model for traffic classification 22

Pruned-F1DCN: A lightweight network model for traffic classi...

引用

Proceedings of the 2022 International Conference on Cyber Security

作者： Ruo nan Wang Jin long Fei Rong kai Zhang State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering University Zhengzhou China China

ISBN: (纸本)9798400700132

With the continuous development of deep learning, deep neural networks are gradually applied to traffic classification problems. However, the large network structure and parameter number of deep neural networks hinder the application on edge computing devices. Reducing network scale helps relieve computational pressure, this paper proposes a lightweight traffic classification model to provide reliable accuracy and reduce the consumption of computing resources. In this work, we design an F1DCN network, which takes full advantage of the convolution layer parameters and the convolution kernel field of view. The lightweight approach effectively improves the classification performance and saves massive parameters. The model pruning method is applied to find the optimal structure of the network. Experiments on two public datasets show that the proposed model reduce more than 80 % parameters and 45 % FLOPS compared with traditional traffic classification methods, and maintaining more than 95 % classification accuracy.

关键词： Convolutional neural network Lightweight Model pruning Traffic classification

来源：评论

学校读者我要写书评

暂无评论

Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection

arXiv

引用

arXiv 2024年

作者： Song, Chengyu Ma, Linru Zheng, Jianming Liao, Jinzhi Kuang, Hongyu Yang, Lin Systems Engineering Institute Academy of Military Sciences Beijing China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi China National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha China

Log-based insider threat detection (ITD) detects malicious user activities by auditing log entries. Recently, Large Language Models (LLMs) with strong common sense knowledge are emerging in the domain of ITD. Nevertheless, diverse activity types and overlong log files pose a significant challenge for LLMs to directly discern malicious ones within myriads of normal activities. Furthermore, the faithfulness hallucination issue from LLMs aggravates its application difficulty in ITD, as the generated conclusion may not align with user commands and activity context. In response to these challenges, we introduce Audit-LLM, a multi-agent log-based insider threat detection framework comprising three collaborative agents: (i) the Decomposer agent, breaking down the complex ITD task into manageable sub-tasks using Chain-of-Thought (COT) reasoning;(ii) the Tool Builder agent, creating reusable tools for sub-tasks to overcome context length limitations in LLMs;and (iii) the Executor agent, generating the final detection conclusion by invoking constructed tools. To enhance conclusion accuracy, we propose a pair-wise Evidence-based Multi-agent Debate (EMAD) mechanism, where two independent Executors iteratively refine their conclusions through reasoning exchange to reach a consensus. Comprehensive experiments conducted on three publicly available ITD datasets—CERT r4.2, CERT r5.2, and PicoDomain—demonstrate the superiority of our method over existing baselines and show that the proposed EMAD significantly improves the faithfulness of explanations generated by LLMs. 1 2 Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Disentangling Ensemble Models on Adversarial Generalization in Image Classification

Disentangling Ensemble Models on Adversarial Generalization ...

引用

International Conference on Electronic engineering and Informatics (EEI)

作者： Chenwei Li Mengyuan Pan Bo Yang Hengwei Zhang State Key Laboratory of Mathematical Engineering and Advanced Computing Henan Key Laboratory of Information Security Zhengzhou China Guizhou University School of Chemistry and Chemical Engineering Guiyang China

Convolutional neural networks are widely used in computer vision and image processing. However, when the original input is added with manually imperceptible perturbations, these deep network models mostly tend to output incorrect predictions. The vulnerability of these models poses great threat to intelligent applications, and these manually imperceptible perturbations are called adversarial examples. Current baseline methods have achieved considerable white-box attack success rate, but black-box rate remains to be improved. To boost the adversarial generalization, ensemble models method is introduced to the process of generating adversarial examples. This paper proposes multiple ensemble strategies with baseline attack methods based on existing ensemble strategy used by former methods. Experiment on ImageNet dataset empirically verifies the optimal ensemble strategy on boosting adversarial generalization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Binary Function Name Prediction Method Based on Variable Alignment and Translation Model 23

A Binary Function Name Prediction Method Based on Variable A...

引用

Proceedings of the 2023 4th International Conference on Machine Learning and Computer Application

作者： Bing Xia Jiabin Yin Yunxiang Ge Ruinan Yang Key Laboratory of Mathematical Engineering and Advanced Computing ZhongYuan University of Technology China Henan Key Laboratory on Public Opinion Intelligent Analysis ZhongYuan University of Technology China ZhongYuan University of Technology China

ISBN: (纸本)9798400709449

Binary function naming is a code analysis task that generates functional descriptions of functions, and its results can be applied in the fields of malicious code analysis, vulnerability causation analysis, and algorithm governance. Aiming at the shortcomings of the pseudocode abstract syntax tree being difficult to extract and the binary function naming scheme having low accuracy rate, a binary function naming prediction model A2N based on variable alignment and sequence translation model is proposed. First, A2N extracts the function variable features of binary files from debugging information and performs variable alignment with the pseudocode obtained from decompiling; then, it obtains the hierarchical structure of the binary functions and designs the node extraction rules to generate an abstract syntax tree AST for each function; then, extract the paths between the leaf nodes of the AST and serialize the tree structure to represent it; finally, with the help of the neural network translation model, establish a mapping between the AST and the binary function names to realize the prediction function. The experimental results show that compared with Dire, Nero and XFL models, the F1 value of A2N is improved by 84%, 44% and 14% on file-level isolation experiments respectively, and the F1 value reaches 80.94% on function-level isolation experiments.

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：