检索结果-内蒙古大学图书馆

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Liu, Haifeng Zheng, Long Huang, Yu Huang, Haoyan Liao, Xiaofei Hai, Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China

ISBN: (纸本)9798400706011

The memory-intensive embedding layer in recommendation model continues to be the performance bottleneck. While prior works have attempted to improve the embedding layer performance by exploiting the data locality to cache the frequently accessed embedding vectors and their partial sums. However, these solutions rely on the static cache, which is inapplicable in the embedding training scenario where the embedding vectors are updated frequently. To this end, this paper proposes ReFree, a redundancy-free near-memory processing (NMP) solution for recommendation model training. Specifically, ReFree identifies the reusable data in realtime for both embedding layer forward and backward stages and leverages a lightweight NMP architecture to enable redundancy-free near-memory acceleration of the entire embedding training process. Evaluation results on real-world datasets show that ReFree outperforms the state-of-the-art solutions by 10.9× and reduces 5.3× energy consumption on average. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

An insider user authentication method based on improved temporal convolutional network

引用

High-Confidence computing 2023年第4期3卷 87-95页

作者： Xiaoling Tao Yuelin Yu Lianyou Fu Jianxiang Liu Yunhao Zhang Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic TechnologyGuilin 541004China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic TechnologyGuilin 541004China

With the rapid development of information technology,information system security and insider threat detection have become important topics for organizational *** the current network environment,user behavioral bio-data presents the characteristics of nonlinearity and temporal *** of the existing research on authentication based on user behavioral biometrics adopts the method of manual feature *** do not adequately capture the nonlinear and time-sequential dependencies of behavioral bio-data,and also do not adequately reflect the personalized usage characteristics of users,leading to bottlenecks in the performance of the authentication *** order to solve the above problems,this paper proposes a Temporal Convolutional Network method based on an Efficient Channel Attention mechanism(ECA-TCN)to extract user mouse dynamics features and constructs an one-class Support Vector Machine(OCSVM)for each user for *** results show that compared with four existing deep learning algorithms,the method retains more adequate key information and improves the classification performance of the neural *** the final authentication,the Area Under the Curve(AUC)can reach 96%.

关键词： Insider users Mouse dynamics Feature extraction Temporal convolutional network Efficient channel attention mechanism Authentication

来源：评论

学校读者我要写书评

暂无评论

IF-Font: Ideographic Description Sequence-Following Font Generation 38

IF-Font: Ideographic Description Sequence-Following Font Gen...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Xinping Ke, Xiao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font. © 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

Towards High-Performance Graph Processing: From a Hardware/Software Co-Design Perspective

引用

Journal of Computer Science & Technology 2024年第2期39卷 245-266页

作者：廖小飞赵文举金海姚鹏程黄禹王庆刚赵进郑龙张宇邵志远 National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China

Graph processing has been widely used in many scenarios,from scientific computing to artificial *** processing exhibits irregular computational parallelism and random memory accesses,unlike traditional ***,running graph processing workloads on conventional architectures(e.g.,CPUs and GPUs)often shows a significantly low compute-memory ratio with few performance benefits,which can be,in many cases,even slower than a specialized single-thread graph *** domain-specific hardware designs are essential for graph processing,it is still challenging to transform the hardware capability to performance boost without coupled software *** article presents a graph processing ecosystem from hardware to *** start by introducing a series of hardware accelerators as the foundation of this ***,the codesigned parallel graph systems and their distributed techniques are presented to support graph ***,we introduce our efforts on novel graph applications and hardware *** results show that various graph applications can be efficiently accelerated in this graph processing ecosystem.

关键词： graph processing hardware accelerator software system high performance ecosystem

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Robust Android Malware Familial Classification

引用

IEEE Transactions on Dependable and Secure computing 2022年 1-14页

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China University of Texas at Dallas Dallas USA 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 Wuhan China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning 5

Task Separation and Knowledge Sharing for Class Incremental ...

引用

5th International Conference on Intelligent computing and Human-Computer Interaction, ICHCI 2024

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 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

Research on Blockchain-based Decentralized Federated Learning

Research on Blockchain-based Decentralized Federated Learnin...

引用

2023 International Conference on Computer Applications Technology, CCAT 2023

作者： Han, Boyuan Liang, Zhihong Qin, Mingming Jiang, Rongxin Dai, Wei Southwest Forestry University School of Big Data and Intelligent Engineering Kunming China Southwest Forestry University Big Data and Cloud Computing Center Kunming China Yunnan Pu'er Technical School Yunnan Pu'er Technical School Kunming China

ISBN: (纸本)9798350301540

The integration of blockchain and federated learning exhibits a highly synergistic relationship. Blockchain, with its assurance of trustworthiness in computational processes and data, combined with federated learning's ability to make data available yet invisible, mutually complement each other and have shown initial advancements across various domains. Consequently, research and analysis of blockchain-based federated learning technology have garnered considerable *** blockchain enhances the federated learning process, it also poses a number of problems, such as increased communication overhead and lack of computational *** article aims to provide a comprehensive examination of the subject. Firstly, it introduces the fundamental concept of federated learning technology, along with privacy protection techniques and the existing threat landscape. Secondly, it analyzes the core principles of blockchain-based federated learning technology, delving into current research status, progress, and outlining the various research directions involved. Furthermore, it conducts an in-depth analysis and summarization of the integration between federated learning and blockchain technology, identifying numerous challenges that need to be addressed within the relevant domains. Finally, it recognizes and analyzes the future development of this combination, emphasizing the need to overcome existing *** summary, this article highlights the amalgamation of federated learning and blockchain technology. It identifies and analyzes the many challenges that require resolution within the pertinent fields, while also offering insights into the future development of this integration. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Informed Spectral Normalized Gaussian Processes for Trajectory Prediction 27

Informed Spectral Normalized Gaussian Processes for Trajecto...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Schlauch, Christian Wirth, Christian Klein, Nadja Continental Automotive Technologies GmbH AI Lab Berlin Germany Humboldt-Universität zu Berlin Germany Karlsruhe Institute of Technology Scientific Computing Center Methods for Big Data Germany

ISBN: (纸本)9781643685489

Prior parameter distributions provide an elegant way to represent prior expert knowledge for informed learning. Previous work has shown that using such informative priors to regularize probabilistic deep learning (DL) models increases their performance and data efficiency. However, commonly used sampling-based approximations for probabilistic DL models can be computationally expensive, requiring multiple forward passes and longer training times. Promising alternatives are compute efficient last layer kernel approximations like spectral normalized Gaussian processes (SNGPs). We propose a novel regularization-based continual learning method for SNGPs, which enables the use of informative priors that represent prior knowledge learned from previous tasks. Our proposal builds upon well-established methods and requires no rehearsal memory or parameter expansion. We apply our informed SNGP model to the trajectory prediction problem in autonomous driving by integrating prior drivability knowledge. On two public datasets, we investigate its performance under diminishing training data and across locations, and thereby demonstrate an increase in data efficiency and robustness to location-transfers over non-informed and informed baselines. © 2024 The Authors.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

FedRKG: A Privacy-Preserving Federated Recommendation Framework via Knowledge Graph Enhancement 18th

FedRKG: A Privacy-Preserving Federated Recommendation Framew...

引用

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

作者： Yao, Dezhong Liu, Tongtong Cao, Qi Jin, Hai 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 Wuhan430074 China School of Computing Science University of Glasgow Glasgow United Kingdom

ISBN: (纸本)9789819998951

Federated Learning (FL) has emerged as a promising approach for preserving data privacy in recommendation systems by training models locally. Recently, Graph Neural Networks (GNN) have gained popularity in recommendation tasks due to their ability to capture high-order interactions between users and items. However, privacy concerns prevent the global sharing of the entire user-item graph. To address this limitation, some methods create pseudo-interacted items or users in the graph to compensate for missing information for each client. Unfortunately, these methods introduce random noise and raise privacy concerns. In this paper, we propose FedRKG, a novel federated recommendation system, where a global knowledge graph (KG) is constructed and maintained on the server using publicly available item information, enabling higher-order user-item interactions. On the client side, a relation-aware GNN model leverages diverse KG relationships. To protect local interaction items and obscure gradients, we employ pseudo-labeling and Local Differential Privacy (LDP). Extensive experiments conducted on three real-world datasets demonstrate the competitive performance of our approach compared to centralized algorithms while ensuring privacy preservation. Moreover, FedRKG achieves an average accuracy improvement of 4% compared to existing federated learning baselines. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of Factors Influencing Driver Lane-Changing Intentions Based on a Naturalistic Trajectory data Set on Highways 24

Analysis of Factors Influencing Driver Lane-Changing Intenti...

引用

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Wang, Guangchen Lu, Guangquan Wang, Jinghua Liu, Miaomiao School of Transportation Science and Engineering Beihang Univ. Beijing China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang Univ. Beijing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

Accurately analyzing and predicting driver lane-changing intentions is of paramount importance, as it significantly enhances the safety of self-driving vehicles in their decision-making processes, holding great promise for the future of intelligent transportation systems. This study extracts fundamental lane-changing characteristic parameters from the Next Generation Simulation (NGSIM) trajectory data set and employs Structural Equation Modeling (SEM) to construct a model that elucidates the factors influencing drivers’ lane-changing intentions. Furthermore, it provides insight into how lane-changing intentions are influenced by lane-changing behavior and explores the intricate connection between intention and associated risks. The results emphasize the substantial negative impact of the longitudinal speed difference between the self-vehicle and the preceding vehicle on lane-changing intentions. Additionally, the consideration of lane-changing risk plays a pivotal role in drivers’ decisions to engage in lane-changing behavior. These findings have significant implications for a deeper comprehension of lane-changing intentions, guiding lane-changing decisions, and enhancing overall traffic safety. © ASCE.

关键词： Autonomous vehicles

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：