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

Towards Capacity-Aware Broker Matching: From Recommendation to Assignment 39

Towards Capacity-Aware Broker Matching: From Recommendation ...

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Wei, Shuyue Tong, Yongxin Zhou, Zimu Liu, Qiaoyang Zhang, Lulu Zeng, Yuxiang Ye, Jieping Beihang University State Key Laboratory of Software Development Environment Beijing China City University of Hong Kong Hong Kong Ke Holdings Inc Beijing China

ISBN: (纸本)9798350322279

Online real estate platforms are gaining increasing popularity, where a central issue is to match brokers with clients for potential housing transactions. Mainstream platforms match brokers via top-k recommendation. Yet we observe through extensive data analysis that such top-k recommendation tends to overload the top brokers, which notably degrades their service quality. In this paper, we propose to avoid such overloading in broker matching via the paradigm shift from recommendation to assignment. To this end, we design learned assignment with contextual bandits (LACB), a data-driven capacity-aware assignment scheme for broker matching which estimates broker-specific workload capacity in an online fashion and assigns brokers to clients from a global perspective to maximize the overall service quality. Extensive evaluations on synthetic and real-world datasets from an industrial online real estate platform validate the efficiency and effectiveness of our solution. © 2023 IEEE.

关键词： Quality control

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

PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation 39

PriSTI: A Conditional Diffusion Framework for Spatiotemporal...

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Liu, Mingzhe Huang, Han Feng, Hao Sun, Leilei Du, Bowen Fu, Yanjie Beihang University State Key Laboratory of Software Development Environment Beijing100191 China University of Central Florida Department of Computer Science FL32816 United States

ISBN: (纸本)9798350322279

Spatiotemporal data mining plays an important role in air quality monitoring, crowd flow modeling, and climate forecasting. However, the originally collected spatiotemporal data in real-world scenarios is usually incomplete due to sensor failures or transmission loss. Spatiotemporal imputation aims to fill the missing values according to the observed values and the underlying spatiotemporal dependence of them. The previous dominant models impute missing values autoregressively and suffer from the problem of error accumulation. As emerging powerful generative models, the diffusion probabilistic models can be adopted to impute missing values conditioned by observations and avoid inferring missing values from inaccurate historical imputation. However, the construction and utilization of conditional information are inevitable challenges when applying diffusion models to spatiotemporal imputation. To address above issues, we propose a conditional diffusion framework for spatiotemporal imputation with enhanced prior modeling, named PriSTI. Our proposed framework provides a conditional feature extraction module first to extract the coarse yet effective spatiotemporal dependencies from conditional information as the global context prior. Then, a noise estimation module transforms random noise to realistic values, with the spatiotemporal attention weights calculated by the conditional feature, as well as the consideration of geographic relationships. PriSTI outperforms existing imputation methods in various missing patterns of different real-world spatiotemporal data, and effectively handles scenarios such as high missing rates and sensor failure. The implementation code is available at https://***/LMZZML/PriSTI. © 2023 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification

HILL: Hierarchy-aware Information Lossless Contrastive Learn...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Zhu, He Wu, Junran Liu, Ruomei Hou, Yue Yuan, Ze Li, Shangzhe Pan, Yicheng Xu, Ke State Key Lab of Software Development Environment Beihang University Beijing100191 China Zhongguancun Laboratory Beijing100094 China School of Statistics and Mathematics Central University of Finance and Economics Beijing100081 China

ISBN: (纸本)9798891761148

Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contrastive samples, which can potentially corrupt or distort the original information. In this paper, we tend to investigate the feasibility of a contrastive learning scheme in which the semantic and syntactic information inherent in the input sample is adequately reserved in the contrastive samples and fused during the learning process. Specifically, we propose an information lossless contrastive learning strategy for HTC, namely Hierarchy-aware Information Lossless contrastive Learning (HILL), which consists of a text encoder representing the input document, and a structure encoder directly generating the positive sample. The structure encoder takes the document embedding as input, extracts the essential syntactic information inherent in the label hierarchy with the principle of structural entropy minimization, and injects the syntactic information into the text representation via hierarchical representation learning. Experiments on three common datasets are conducted to verify the superiority of HILL. ©2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Degradation of metoprolol by UV/sulfite as an advanced oxidation or reduction process:The significant role of oxygen

引用

Journal of environmental Sciences 2023年第6期128卷 107-116页

作者： Ying Cao Juan Li Yanxin Zhao Yumeng Zhao Wei Qiu Suyan Pang Jin Jiang Advanced Interdisciplinary Institute of Environment and Ecology Beijing Normal University at ZhuhaiZhuhai 519087China State Key Laboratory of Urban Water Resource and Environment School of EnvironmentHarbin Institute of TechnologyHarbin 150090China Key Laboratory of Songliao Aquatic Environment Ministry of EducationSchool of Municipal and Environmental EngineeringJilin Jianzhu UniversityChangchun 130118China Key Laboratory for City Cluster Environmental Safety and Green Development of the Ministry of Education Institute of Environmental and Ecological EngineeringGuangdong University of TechnologyGuangzhou 510006China Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou) Guangzhou 511458China

The degradation of metoprolol(MTP)by the UV/sulfite with oxygen as an advanced reduction process(ARP)and that without oxygen as an advanced oxidation process(AOP)was comparatively studied *** degradation of MTP by both processes followed the first-order rate law with comparable reaction rate constants of 1.50×10^(-3)sec^(−1)and 1.20×10^(-3)sec^(−1),*** experiments demonstrated that both e^(−)_(aq)and H·played a crucial role in MTP degradation by the UV/sulfite as an ARP,while SO_(4)^(·−)was the dominant oxidant in the UV/sulfite *** degradation kinetics of MTP by the UV/sulfite as an ARP and AOP shared a similar pH dependence with a minimum rate obtained around pH *** results could be well explained by the pH impacts on the MTP speciation and sulfite *** six transformation products(TPs)were identified from MTP degradation by the UV/sulfite ARP,and two additional ones were detected in the UV/sulfite *** benzene ring and ether groups of MTP were proposed as the major reactive sites for both processes based on molecular orbital calculations by density functional theory(DFT).The similar degradation products of MTP by the UV/sulfite process as an ARP and AOP indicated that e^(−)_(aq)/H·and SO_(4)^(·−)might share similar reaction mechanisms,primarily including hydroxylation,dealkylation,and H *** toxicity of MTP solution treated by the UV/sulfite AOP was calculated to be higher than that in the ARP by the Ecological Struc-ture Activity Relationships(ECOSAR)software,due to the accumulation of TPs with higher toxicity.

关键词： UV/sulfite Advanced reduction process(ARP) Advanced oxidation process(AOP) Metoprolol Degradation products Toxicity

来源：评论

学校读者我要写书评

暂无评论

Exploiting Hierarchical Symmetry in Multi-Agent Reinforcement Learning 27

Exploiting Hierarchical Symmetry in Multi-Agent Reinforcemen...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Tian, Yongkai Yu, Xin Qi, Yirong Wang, Li Feng, Pu Wu, Wenjun Shi, Rongye Luo, Jie State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing China Institute of Artificial Intelligence Beihang University Beijing China

ISBN: (纸本)9781643685489

Achieving high sample efficiency is a critical research area in reinforcement learning. This becomes extremely difficult in multi-agent reinforcement learning (MARL), as the capacity of the joint state and action space grows exponentially with the number of agents. The reliance of MARL solely on exploration and trial- and-error, without incorporating prior knowledge, exacerbates the issue of low sample efficiency. Currently, introducing symmetry into MARL is an effective approach to address this issue. Yet the concept of hierarchical symmetry, which maintains symmetry across different levels of a multi-agent system (MAS), has not been explored in existing methods. This paper focuses on multi-agent cooperative tasks and proposes a method incorporating hierarchical symmetry, termed the Hierarchical Equivariant Policy Network (HEPN) which is O(n)equivariant. Specifically, HEPN utilizes clustering to perform hierarchical information extraction in MAS, and employs graph neural networks to model agent interactions. We conducted extensive experiments across various multi-agent tasks. The results indicate that our method achieves faster convergence speeds and higher convergence rewards compared to baseline algorithms. Additionally, we have deployed our algorithm in a physical multi-robot system, confirming its effectiveness in real-world environments. Supplementary materials are available at https://***/HEPN/. © 2024 The Authors.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ServeNet-GPT-Fusion: A Fusion Language Model For Web Services Classification 21

ServeNet-GPT-Fusion: A Fusion Language Model For Web Service...

引用

21st International Bhurban Conference on Applied Sciences and Technology, IBCAST 2024

作者： Liu, Sizuo Yang, Yilong Khan, Muhammad Ali Tian, Zhen Chen, Ping Shang, Jingwei School of Software Beihang University Beijing China Beihang University School of Software State Key Laboratory of Complex and Critical Environment Beijing China Software Quality Engineering Research Center CEPREI Guangzhou China

ISBN: (纸本)9798331516680

Automatic service classification plays an important role in service discovery, selection, and composition. Recently, machine learning has been widely used in service classification. Even though promising results are obtained, previous methods in a small-scale dataset has reached its limit. In this paper, we propose a method that integrates with existing large language models to further enhance the prediction accuracy across 50 service categories. To demonstrate the efficiency of our approach, we conducted experiments on predicting classification accuracy across 50 service categories using three ChatGPT models. The results indicated that each of the three ChatGPT's are prominent at predicting different service categories compared to existing results. By further integrating existing outcomes with these three models through a weighted voting method, we achieved a further improvement in accuracy. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

VGGAN: Visual Grounding GAN Using Panoptic Transformers

VGGAN: Visual Grounding GAN Using Panoptic Transformers

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Fengnan Quan Bo Lang State Key Laboratory of Software Development Environment Beihang University Beijing China State Key Laboratory of Software Development Environment Zhongguancun Laboratory Beihang University Beijing China

Visual Grounding is an important part of image annotation generation. The existing methods usually use data alignment based on the similarity calculation of visual text features in location inference and multi-modal fusion, which will lose visual and text information to some extent, and is more likely to make the model overfit the data of specific scenes. To solve this problem, we propose a Visual Grounding Generative Adversarial Network (VGGAN) for visual text fusion using the panoptic transformer. We use the generative adversarial network to generate the prediction, judge the accuracy, and design the visual text transformer according to the panoptic theory. The model can retain the feature information, realize the full interactions between features, thereby better supporting the feature fusion of visual and text. Experimental results on the COCO dataset of complex daily scenes verify the effectiveness of our model, and our model achieves the highest prediction accuracy compared with the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative responses of two maize genotypes with contrasting drought tolerance to biochar application

引用

Biochar 2024年第1期6卷 1173-1187页

作者： Renjie Ruan Hans Lambers Yaosheng Wang State Key Laboratory of Efficient Utilization of Agricultural Water Resources Key Laboratory of Dryland AgricultureMinistry of Agriculture and Rural Affairs of ChinaInstitute of Environment and Sustainable Development in AgricultureChinese Academy of Agricultural SciencesBeijing 100081China. School of Biological Sciences The University of Western AustraliaPerthWA 6009Australia.

The impact of biochar application on plant performance under drought stress necessitates a comprehensive understanding of biochar-soil interaction,root growth,and plant physiological ***,pot experiments were conducted to assess the effects of biochar on plant responses to drought stress at the seedling *** contrasting maize genotypes(drought-sensitive KN5585 vs.-tolerant Mo17)were subjected to biochar application under drought stress *** results indicated that biochar application decreased soil exchangeable Na+and Ca^(2+)contents while increased soil exchangeable K^(+)content(2.7-fold)and electrical conductivity(4.0-fold),resulting in an elevated leaf sap K^(+)concentration in both maize *** elevated K^(+)concentration with biochar application increased root apoplastic pH in the drought-sensitive KN5585,but not in the drought-tolerant Mo17,which stimulated the activation of H^(+)-ATPase and H^(+)efflux in KN5585 *** alkalinization of the drought-sensitive KN5585 resulting from biochar application further inhibited root growth by 30.7%,contributing to an improvement in water potential,a reduction in levels of O_(2)^(-),H_(2)O_(2),T-AOC,SOD,and POD,as well as the down-regulation of genes associated with drought resistance in KN5585 *** contrast,biochar application increased leaf sap osmolality and provided osmotic protection for the drought-tolerant Mo17,which was associated with trehalose accumulation in Mo17 *** application improved sucrose utilization and circadian rhythm of Mo17 roots,and increased fresh weight under drought *** study suggests that biochar application has the potential to enhance plant drought tolerance,which is achieved through the inhibition of root growth in sensitive plants and the enhancement of osmotic protection in tolerant plants,respectively.

关键词： Biochar application Drought stress Apoplastic pH Root growth Physiological traits

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：