检索结果-内蒙古大学图书馆

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Qinggang Wang Long Zheng Ao Hu Yu Huang Pengcheng Yao Chuangyi Gui Xiaofei Liao Hai Jin Jingling Xue 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 and Zhejiang Lab Hangzhou China 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 School of Computer Science and Engineering University of New South Wales Sydney NSW Australia

ISBN: (纸本)9781665462723

Hypergraph processing has emerged as a powerful approach for analyzing complex multilateral relationships among multiple entities. Past research on building hypergraph systems suggests that changing the scheduling order of bipartite edge tasks can improve the overlap-induced data locality in hypergraph processing. However, due to the complex intertwined connections between vertices and hyperedges, it is almost impossible to find a locality-optimal scheduling order. Thus, these task-centric hypergraph systems often suffer from substantial off-chip *** this paper, we first propose a novel data-centric Load-Trigger-Reduce (LTR) execution model to exploit fully the locality in hypergraph processing. Unlike a task-centric model that loads the required data along with a task, our LTR model invokes tasks as per the data used. Specifically, once the hypergraph data is loaded into the on-chip memory, all of its relevant computation tasks will be triggered simultaneously to output intermediate results, which are finally reduced to update the final results. Our LTR model enables all hypergraph data to be accessed once in each iteration. To fully exploit the LTR performance potential, we further architect an LTR-driven hypergraph accelerator, XuLin, which features with an adaptive data loading mechanism to minimize the loading cost via chunk merging at runtime. XuLin is also equipped with a priority-based differential data reduction scheme to reduce the impact of conflicting updates on performance. We have implemented XuLin both on a Xilinx Alveo U250 FPGA card and using a cycle-accurate simulator. The results show that XuLin outperforms the state-of-the-art hypergraph processing solutions Hygra and ChGraph by 20.47× and 8.77× on average, respectively.

关键词： hypergraph data-centric accelerator

来源：评论

学校读者我要写书评

暂无评论

Combining Self-Supervised Learning and Adversarial Training Based Domain Adaptation for Speaker Verification

Combining Self-Supervised Learning and Adversarial Training ...

引用

International Symposium on Chinese Spoken Language Processing

作者： Zhengyang Chen Shuai Wang Bing Han Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai Shenzhen Research Institute of Big Data Shenzhen Chinese University of Hong Kong Shenzhen

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Adapting an existing well-trained system to a new domain using only unlabeled data is a highly sought-after yet challenging task for speaker verification in real-world scenarios. In this paper, we study two different domain adaptation methods, the adversarial domain adaptation (ADA) and the self-supervised learning-based domain adaptation (SSDA). To facilitate the deployment of unsupervised adaptation methods in applications, we conduct a detailed analysis of the characteristics of both the ADA and SSDA adaptation strategies. Our findings indicate that the SSDA strategy's performance is highly influenced by the amount of target domain data, whereas the ADA strategy is relatively insensitive to data quantity. Furthermore, augmenting target domain data enhances SSDA system performance but diminishes ADA performance. To further enhance system performance, we explore the complementarity between ADA and SSDA. Our results demonstrate that ADA and SSDA complement each other. When both strategies are applied jointly, the best system achieves over 20.0% relative Equal Error Rate (EER) improvement on the Cnceleb evaluation set and over 35.0% relative average EER improvement on the SRE16 Cantonese and Tagalog evaluation set under domain mismatched conditions.

关键词： Training Error analysis System performance Self-supervised learning Speech processing

来源：评论

学校读者我要写书评

暂无评论

Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples

Beyond Textual Constraints: Learning Novel Diffusion Conditi...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuyang Yu Bangzhen Liu Chenxi Zheng Xuemiao Xu Shengfeng He Huaidong Zhang South China University of Technology State Key Laboratory of Subtropical Building Science Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Ministry of Education Key Laboratory of Big Data and Intelligent Robot Singapore Management University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In this paper, we delve into a novel aspect of learning novel diffusion conditions with datasets an order of magnitude smaller. The rationale behind our approach is the elimination of textual constraints during the few-shot learning process. To that end, we implement two optimization strategies. The first, prompt-free conditional learning, utilizes a prompt-free encoder derived from a pre-trained Stable Diffusion model. This strategy is designed to adapt new conditions to the diffusion process by minimizing the textual-visual cor-relation, thereby ensuring a more precise alignment between the generated content and the specified conditions. The second strategy entails condition-specific negative rectification, which addresses the inconsistencies typically brought about by Classifier-free guidance in few-shot training con-texts. Our extensive experiments across a variety of condition modalities demonstrate the effectiveness and efficiency of our framework, yielding results comparable to those obtained with datasets a thousand times larger. Our codes are available at https://***/Yuyan9Yu/BeyondTextConstraint.

关键词： Training Computer vision Adaptation models Codes Text to image Diffusion processes Diffusion models

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

arXiv

引用

arXiv 2024年

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado SpringsCO United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China 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 Cluster and Grid Computing Lab China JinYinHu Laboratory Wuhan China

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter-Procedural Vulnerability dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulnerability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Multi-Temporal Relationship Inference in Urban Areas

arXiv

引用

arXiv 2023年

作者： Li, Shuangli Zhou, Jingbo Liu, Ji Xu, Tong Chen, Enhong Xiong, Hui School of Computer Science and Technology University of Science and Technology of China Baidu Research China Business Intelligence Lab Baidu Research China Big Data Lab Baidu Research China School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Finding multiple temporal relationships among locations can benefit a bunch of urban applications, such as dynamic offline advertising and smart public transport planning. While some efforts have been made on finding static relationships among locations, little attention is focused on studying time-aware location relationships. Indeed, abundant location-based human activities are time-varying and the availability of these data enables a new paradigm for understanding the dynamic relationships in a period among connective locations. To this end, we propose to study a new problem, namely multi-Temporal relationship inference among locations (Trial for short), where the major challenge is how to integrate dynamic and geographical influence under the relationship sparsity constraint. Specifically, we propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet) with two collaborative components: spatially evolving graph convolution module (SEConv) and spatially evolving self-supervised learning strategy (SE-SSL). SEConv performs the intra-time aggregation and inter-time propagation to capture the multifaceted spatially evolving contexts from the view of location message passing. In addition, SE-SSL designs time-aware self-supervised learning tasks in a global-local manner with additional evolving constraint to enhance the location representation © 2023, CC BY.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Implicit Supervision-Assisted Graph Collaborative Filtering for Third-Party Library Recommendation

引用

IEEE Transactions on Services Computing 2025年第3期18卷 1459-1471页

作者： Lianrong Chen Mingdong Tang Naidan Mei Fenfang Xie Guo Zhong Qiang He School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China Unicom (Guangdong) Industry Internet Company Guangzhou China 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 Department of Computing Technologies Swinburne University of Technology Melbourne VIC Australia

Third-party libraries (TPLs) play a crucial role in software development. Utilizing TPL recommender systems can aid software developers in promptly finding useful TPLs. A number of TPL recommendation approaches have been proposed and among them graph neural network (GNN)-based recommendation is attracting the most attention. However, GNN-based approaches generate node representations through multiple convolutional aggregations, which is prone to introducing noise, resulting in the over-smoothing issue. In addition, due to the high sparsity of labelled data, node representations may be biased in real-world scenarios. To address these issues, this paper presents a TPL recommendation method named Implicit Supervision-assisted Graph Collaborative Filtering (ISGCF). Specifically, it takes the App-TPL interaction relationships as input and employs a popularity-debiased method to generate denoised App and TPL graphs. This reduces the noise introduced during graph convolution and alleviates the over-smoothing issue. It also employs a novel implicitly-supervised loss function to exploit the labelled data to learn enhanced node representations. Extensive experiments on a large-scale real-world dataset demonstrate that ISGCF achieves a significant performance advantage over other state-of-the-art TPL recommendation methods in Recall, NDCG and MAP. The experiments also validate the superiority of ISGCF in mitigating the over-smoothing problem.

关键词： Vectors Noise Training Collaborative filtering Recommender systems Libraries Predictive models Graph neural networks Electronic mail Convolution

来源：评论

学校读者我要写书评

暂无评论

Diabetes Mellitus Type 2 data Sharing System Based on Blockchain and Attribute-Encryption

Diabetes Mellitus Type 2 Data Sharing System Based on Blockc...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Weiqi Dai Zhenhui Lu Xia Xie Duoqiang Wang Hai Jin 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 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 School of Computer Science and Technology Hainan University Haikou China

Medical data sharing can improve the quality of medical care and promote progress in the field of public health. However, medical data has high confidentiality and complexity. Taking the clinical diagnosis and treatment data of Diabetes Mellitus Type 2 (T2DM) in medical treatment as an example, T2DM data often has the phenomenon of "multi-disease coexistence" and is insecure and inaccurate in the process of sharing. Based on Blockchain and Attribute- Encryption (ABE), we propose a T2DM data sharing system to solve the above problems. An Attribute-Encryption algorithm T2DM-CP-ABE is proposed to solve the problem of excessive sharing granularity. T2DM-CP-ABE, combined with the medical data contribution module, takes the contribution factor as an important consideration, to stimulate the power of T2DM data sharing and promote the development of national diabetes prevention. Based on the Blockchain, a medical data attribute authorization model is proposed, which provides a credible solution for multiple hospitals to realize medical data attribute authorization, and realizes the clinical diagnosis and treatment data sharing of T2DM among doctors. Based on Blockchain and ABE technology, a data sharing system for T2DM has been implemented on the Fabric platform. The result shows that the average time for the system to complete a single sharing is less than 1 second.

关键词： Authorization Hospitals Fabrics Blockchains Diabetes Encryption Security

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

On the Effectiveness of Function-Level Vulnerability Detecto...

引用

International Conference on Software Engineering (ICSE)

作者： Zhen Li Ning Wang Deqing Zou Yating Li Ruqian Zhang Shouhuai Xu Chao Zhang Hai Jin 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 Cluster and Grid Computing Lab School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jin YinHu Laboratory Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado Springs Colorado USA Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers; and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities.

关键词： Deep learning Detectors Open source software Software engineering

来源：评论

学校读者我要写书评

暂无评论

Effective and Efficient big OLAP data Cube Compression in Mobile Cloud Environments: The IQTS Algorithm

Effective and Efficient Big OLAP Data Cube Compression in Mo...

引用

IEEE International Conference on big data

作者： Alfredo Cuzzocrea Mojtaba Hajian iDEA Lab University of Calabria Rende Italy Dept. of Computer Science University of Paris City Paris France Big Data Management and Analytics at University of Paris City Paris France

This paper introduces the Indexed Quad-Tree Summary (IQTS) algorithm, along with its concepts, models, and “philosophy”. IQTS allows us to compress multidimensional OLAP views derived from big OLAP data cubes that populate Mobile Clouds. In addition to this, IQTS effectively and efficiently supports approximate query answering over compressed multidimensional OLAP views. These functionalities turn to be enabling functionalities for big data applications in a wide collection of modern scenarios, such as healthcare analytics. In light of these considerations, this paper provides motivations, anatomy and procedures of IQTS, enriched by several case studies that contribute to pinpoint the benefits coming from our proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FaaSTube: Optimizing GPU-oriented data Transfer for Serverless Computing

arXiv

引用

arXiv 2024年

作者： Wu, Hao Deng, Junxiao Yu, Minchen Yu, Yue Liu, Yaochen Fan, Hao Wu, Song Wang, Wei 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 China Hong Kong University of Science and Technology Hong Kong The Chinese University of Hong Kong Shenzhen China

Serverless computing has gained significant traction for machine learning inference applications, which are often deployed as serverless workflows consisting of multiple CPU and GPU functions with data dependency. However, existing data-passing solutions for serverless computing primarily reply on host memory for fast data transfer, mandating substantial data movement and resulting in salient I/O overhead. In this paper, we present FaaSTube, a GPU-efficient data passing system for serverless inference. FaaSTube manages intermediate data within a GPU memory pool to facilitate direct data exchange between GPU functions. It enables fine-grained bandwidth sharing over PCIe and NVLink, minimizing data-passing latency for both host-to-GPU and GPU-to-GPU while providing performance isolation between functions. Additionally, FaaSTube implements an elastic GPU memory pool that dynamically scales to accommodate varying data-passing demands. Evaluations on real-world applications show that FaaSTube reduces end-to-end latency by up to 90% and achieves up to 12x higher throughput compared to the state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： Computer graphics equipment

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：