检索结果-内蒙古大学图书馆

GCSS:a global collaborative scheduling strategy for wide-area high-performance computing

Frontiers of computer science 2022年第5期16卷 1-15页

作者： Yao SONG Limin XIAO Liang WANG Guangjun QIN Bing WEI Baicheng YAN Chenhao ZHANG State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China Smart City College Beijing Union UniversityBeijing 100101China

Wide-area high-performance computing is widely used for large-scale parallel computing applications owing to its high computing and storage ***,the geographical distribution of computing and storage resources makes efficient task distribution and data placement more *** achieve a higher system performance,this study proposes a two-level global collaborative scheduling strategy for wide-area high-performance computing *** collaborative scheduling strategy integrates lightweight solution selection,redundant data placement and task stealing mechanisms,optimizing task distribution and data placement to achieve efficient computing in wide-area *** experimental results indicate that compared with the state-of-the-art collaborative scheduling algorithm HPS+,the proposed scheduling strategy reduces the makespan by 23.24%,improves computing and storage resource utilization by 8.28%and 21.73%respectively,and achieves similar global data migration costs.

关键词： high-performance computing scheduling strategy task scheduling data placement

来源：评论

学校读者我要写书评

暂无评论

Adaptive Token Selection and Fusion Network for Multimodal Sentiment Analysis 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Li, Xiang Lu, Ming Guo, Ziming Zhang, Xiaoming School of Cyber Science and Technology Beihang University Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China

ISBN: (数字)9783031533112

ISBN: (纸本)9783031533105

Multimodal sentiment analysis aims to predict human sentiment polarity with multiple modalities. Most existing methods focus on directly integrating original modal features into multimodal fusion, ignoring the redundancy and heterogeneity across modalities. In this paper, we propose a simple but efficient Adaptive Token Selection and Fusion Network (ATSFN) to mitigate the effect of redundancy and heterogeneity. ATSFN employs adaptive trainable tokens to extract unimodal informative tokens and perform dynamic multimodal token fusion. Specifically, we first integrate critical information from original features into adaptive selection tokens through token selection transformers. Sentiment features flow through these smaller sequences of tokens to capture important information while reducing redundancy. Next, we introduce a token fusion transformer to fuse multimodal features dynamically. It adaptively estimates the unique contribution of each modality to sentiment tendencies through learnable fusion tokens. Experiments on two benchmark datasets demonstrate that our proposed approach achieves competitive performance and significant improvements. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

New Intent Discovery with Attracting and Dispersing Prototype 30

New Intent Discovery with Attracting and Dispersing Prototyp...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Shun Yang, Jian Bai, Jiaqi Yan, Chaoran Li, Tongliang Yan, Zhao Li, Zhoujun State Key Lab of Software Development Environment Beihang University Beijing China School of Cyber Science and Technology Beihang University Beijing China Beijing Information Science and Technology University China Tencent Youtu Lab China

ISBN: (纸本)9782493814104

New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. The task is addressed as a feature-clustering problem and recent studies augment instance representation. However, existing methods fail to capture cluster-friendly representations, since they show less capability to effectively control and coordinate within-cluster and between-cluster distances. Tailored to the NID problem, we propose a Robust and Adaptive Prototypical learning (RAP) framework for globally distinct decision boundaries for both known and new intent categories. Specifically, a robust prototypical attracting learning (RPAL) method is designed to compel instances to gravitate toward their corresponding prototype, achieving greater within-cluster compactness. To attain larger between-cluster separation, another adaptive prototypical dispersing learning (APDL) method is devised to maximize the between-cluster distance from the prototype-to-prototype perspective. Experimental results evaluated on three challenging benchmarks (CLINC, BANKING, and StackOverflow) of our method with better cluster-friendly representation demonstrate that RAP brings in substantial improvements over the current state-of-the-art methods (even large language model) by a large margin (average +5.5% improvement). © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cost Aggregation in Iterative Depth Estimation for Efficient Multi-view Stereo 12th

Adaptive Cost Aggregation in Iterative Depth Estimation for...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Wang, Xiang Bai, Xiao Wang, Chen School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University Beijing China

ISBN: (纸本)9783031463075

The deep multi-view stereo (MVS) approaches generally construct 3D cost volumes to regularize and regress the depth map. These methods are limited with high-resolution outputs since the memory and time costs grow cubically as the volume resolution increases. In this paper, we presented an multi-stage iterative depth map estimation method for MVS. In our network, the cost volume is iteratively processed by lightweight 2D convolution based GRU modules, and the multi-stage coarse-to-fine structure is adopted to speed up the depth estimation process. To further improve the 3D reconstruction quality, we make improvements from two different perspectives of adaptive cost aggregation: a view-adaptive weighting module is proposed to account for the occlusion problem in cost volume fusion, and a spatial-adaptive deformable geometric feature encoding module is introduced to the cost volume feature encoding before feeding into GRUs for stronger modeling capability. Experiments on the DTU dataset demonstrated the effectiveness of the proposed network in accuracy with remarkable efficiency performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Active Perception for Grasp Detection via Neural Graspness Field 38

Active Perception for Grasp Detection via Neural Graspness F...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ma, Haoxiang Shi, Modi Gao, Boyang Huang, Di State Key Laboratory of Complex and Critical Software Environment School of Computer Science and Engineering Beihang University Beijing China Geometry Robotics

This paper tackles the challenge of active perception for robotic grasp detection in cluttered environments. Incomplete 3D geometry information can negatively affect the performance of learning-based grasp detection methods, and scanning the scene from multiple views introduces significant time costs. To achieve reliable grasping performance with efficient camera movement, we propose an active grasp detection framework based on the Neural Graspness Field (NGF), which models the scene incrementally and facilitates next-best-view planning. Constructed in real-time as the camera moves, the NGF effectively models the grasp distribution in 3D space by rendering graspness predictions from each view. For next-best-view planning, we aim to reduce the uncertainty of the NGF through a graspness inconsistency-guided policy, selecting views based on discrepancies between NGF outputs and a pre-trained graspness network. Additionally, we present a neural graspness sampling method that decodes graspness values from the NGF to improve grasp pose detection results. Extensive experiments on the GraspNet-1Billion benchmark demonstrate significant performance improvements compared to previous works. Real-world experiments show that our method achieves a superior trade-off between grasping performance and time costs. Code is available at https://***/mahaoxiang822/ActiveNGF. © 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

Some New Methods to Generate Short Addition Chains

IACR Transactions on Cryptographic Hardware and Embedded Sys...

引用

IACR Transactions on Cryptographic Hardware and Embedded Systems 2023年第2期2023卷 270-285页

作者： Ding, Yuanchao Guo, Hua Guan, Yewei Song, Hutao Zhang, Xiyong Liu, Jianwei School of Cyber Science and Technology Beihang University Beijing China State Key Laboratory of Cryptology P.O. Box Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Beijing Institute of Satellite Information Engineering Beijing China

Modular exponentiation and scalar multiplication are important operations in most public-key cryptosystems, and their efficient computation is essential to cryptosystems. The shortest addition chain is one of the most important mathematical concepts to realize the optimization of computation. However, finding a shortest addition chain of length r is generally regarded as an NP-hard problem, whose time complexity is comparable to O(r!). This paper proposes some novel methods to generate short addition chains. We firstly present a Simplified Power-tree method by deeply deleting the power-tree whose time complexity is reduced to O(r2). In this paper, a Cross Window method and its variant are introduced by improving the Window method. The Cross Window method uses the cross correlation to deal with the windows and its pre-computation is optimized by a new Addition Sequence Algorithm. The theoretical analysis is conducted to show the correctness and effectiveness. Meanwhile, our experiments show that the new methods can obtain shorter addition chains compared to the existing methods. The Cross Window method with the Addition Sequence algorithm can attain 44.74% and 9.51% reduction of the addition chain length, in the best case, compared to the Binary method and the Window method respectively. © 2023, Ruhr-university of Bochum. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A study on the impact of pre-trained model on Just-In-Time defect prediction 23

A study on the impact of pre-trained model on Just-In-Time d...

引用

23rd IEEE International Conference on software Quality, Reliability, and Security, QRS 2023

作者： Guo, Yuxiang Gao, Xiaopeng Zhang, Zhenyu Chan, W.K. Jiang, Bo Beihang University State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China City University of Hong Kong Department of Computer Science Hong Kong

ISBN: (纸本)9798350319583

Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In this study, we build six models: RoBERTaJIT, CodeBERTJIT, BARTJIT, PLBARTJIT, GPT2JIT, and CodeGPTJIT, each with a distinct pre-trained model as its backbone. We systematically explore the differences and connections between these models. Specifically, we investigate the performance of the models when using Commit code and Commit message as inputs, as well as the relationship between training efficiency and model distribution among these six models. Additionally, we conduct an ablation experiment to explore the sensitivity of each model to inputs. Furthermore, we investigate how the models perform in zero-shot and few-shot scenarios. Our findings indicate that each model based on different backbones shows improvements, and when the backbone's pre-training model is similar, the training resources that need to be consumed are closer. We also observe that Commit code plays a significant role in defect detection, and different pre-trained models demonstrate better defect detection ability with a balanced dataset under few-shot scenarios. These results provide new insights for optimizing JIT defect prediction tasks using pre-trained models and highlight the factors that require more attention when constructing such models. Additionally, CodeGPTJIT and GPT2JIT achieved better performance than DeepJIT and CC2Vec on the two datasets respectively under 2000 training samples. These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

IoTAEG: Automatic Exploit Generation of IoT Devices 4

IoTAEG: Automatic Exploit Generation of IoT Devices

引用

2023 4th International Conference on computer Engineering and Intelligent Control, ICCEIC 2023

作者： Wang, Yu Li, Zhoujun Zhang, Yipeng Zhai, You Beihang University State Key Lab of Software Development Environment Beijing China North China University of Technology School of Information Science and Technology Beijing China

ISBN: (纸本)9798350308877

Automatic exploit generation (AEG) refers to the process of automatically finding the path in the program that can trigger vulnerabilities and generate exploits. Generally speaking, the process of finding vulnerabilities needs to apply fuzzing and symbolic execution techniques. Existing AEG generally targets executables for regular Linux and Windows platforms, but no AEG for vulnerable Internet of Things (IoT) devices. In response to this situation, we propose the exploit generation system IoTAEG, which automatically detects stack overflow vulnerabilities in the firmware of IoT devices, and automatically generates and exploits the generation system based on the stack overflow vulnerabilities. IoTAEG uses the mature fuzzing software AFL++ to detect vulnerabilities in IoT devices, uses the crashed input found by AFL++ to construct a symbolic state through symbolic execution, dynamically analyzes the constructed symbolic state, and detects whether there are exploitable vulnerabilities. If the above vulnerabilities exist, different exploit generation strategies will be adopted for different protection mechanisms, and some protection mechanisms such as Address space layout randomization (ASLR) and Non-eXecute (NX) will be bypassed. For some difficult-to-exploit cases, IoTAEG uses advanced stack overflow exploitation methods to generate exploits. Experiments show that IoTAEG can complete 20 MIPS/ARM binary files and 8 IoT devices' firmware vulnerability detection and exploit generation. IoTAEG is the first publicly available vulnerability mining and exploit generation system for IoT devices. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Aster: Encoding Data Augmentation Relations into Seed Test Suites for Robustness Assessment and Fuzzing of Data-Augmented Deep Learning Models 23

Aster: Encoding Data Augmentation Relations into Seed Test S...

引用

23rd IEEE International Conference on software Quality, Reliability, and Security, QRS 2023

作者： Wang, Haipeng Wei, Zhengyuan Zhou, Qilin Jiang, Bo Chan, W.K. City University of Hong Kong Hong Kong Beihang University State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing China

ISBN: (纸本)9798350319583

Data-augmented deep learning models are widely used in real-world applications. However, many state-of the-art loss-based or coverage-based fuzzing techniques fail to produce fuzzing samples for them from many seeds. This paper proposes Aster, a novel technique to address this problem to enhance their fuzzing effectiveness for deep learning models trained with multi-sample data augmentation methods. Aster formulates a novel reachability-based strategy to encode the insights of every seed's direct and indirect data augmentation relation instances into the replacement seed of that seed systematically. Our experiment shows that Aster is highly effective. On average, loss-based and coverage-based fuzzing techniques can generate 166% and 110% more fuzzing samples and reduce 31% and 22% unsuccessful seeds, respectively, after adopting the replacement seeds generated by Aster to replace their original seeds. Their improved models also become up to 55% and 40% on average more robust against FGSM and PGD attacks in the experiment. © 2023 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Light field super-resolution using complementary-view feature attention

引用

Computational Visual Media 2023年第4期9卷 843-858页

作者： Wei Zhang Wei Ke Da Yang Hao Sheng Zhang Xiong Faculty of Applied Sciences Macao Polytechnic UniversityMacao SAR 999078China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191Chinaand Beihang Hangzhou Innovation Institute YuhangXixi Octagon CityYuhang DistrictHangzhou 310023China

Light field(LF)cameras record multiple perspectives by a sparse sampling of real scenes,and these perspectives provide complementary *** information is beneficial to LF super-resolution(LFSR).Compared with traditional single-image super-resolution,LF can exploit parallax structure and perspective correlation among different LF ***,the performance of existing methods are limited as they fail to deeply explore the complementary information across LF *** this paper,we propose a novel network,called the light field complementary-view feature attention network(LF-CFANet),to improve LFSR by dynamically learning the complementary information in LF ***,we design a residual complementary-view spatial and channel attention module(RCSCAM)to effectively interact with complementary information between complementary ***,RCSCAM captures the relationships between different channels,and it is able to generate informative features for reconstructing LF images while ignoring redundant ***,a maximum-difference information supplementary branch(MDISB)is used to supplement information from the maximum-difference angular positions based on the geometric structure of LF *** branch also can guide the process of *** results on both synthetic and real-world datasets demonstrate the superiority of our *** proposed LF-CFANet has a more advanced reconstruction performance that displays faithful details with higher SR accuracy than state-of-the-art methods.

关键词： light field(LF) super-resolution(SR) attention

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：