检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhenwei Shao Zhou Yu Meng Wang Jun Yu Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China School of Computer Science and Information Engineering Hefei University of Technology China

Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have sought to use a large language model (i.e., GPT-3 [3]) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of GPT-3 as the provided input information is insufficient. In this paper, we present Prophet-a conceptually simple framework designed to $prompt$ GPT-3 with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are encoded into the prompts to enable GPT-3 to better comprehend the task thus enhancing its capacity. Prophet significantly outperforms all existing state-of-the-art methods on two challenging knowledge-based VQA datasets, OK-VQA and A-OKVQA, delivering 61.1% and 55.7% accuracies on their testing sets, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Synchronous Parallel Method with Parameters Communication Prediction for Distributed Machine Learning 19th

A Synchronous Parallel Method with Parameters Communication...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yanguo Xue, Meiting Xu, Peiran Shi, Yukun Zeng, Kaisheng Zhang, Jilin Yue, Lupeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China National University of Defense Technology Changsha China School of Cyberspace HangZhou Dianzi University Hangzhou China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783031545306

With the development of machine learning technology in various fields, such as medical care, smart manufacturing, etc., the data has exploded. It is a challenge to train a deep learning model for different application domains with large-scale data and limited resources of a single device. The distributed machine-learning technology, which uses a parameter server and multiple clients to train a model collaboratively, is an excellent method to solve this problem. However, it needs much communication between different devices with limited communication resources. The stale synchronous parallel method is a mainstream communication method to solve this problem, but it always leads to high synchronization delay and low computing efficiency as the inappropriate delay threshold value set by the user based on experience. This paper proposes a synchronous parallel method with parameters communication prediction for distributed machine learning. It predicts the optimal timing for synchronization, which can solve the problem of long synchronization waiting time caused by the inappropriate threshold settings in the stale synchronous parallel method. Moreover, it allows fast nodes to continue local training while performing global synchronization, which can improve the resource utilization of work nodes. Experimental results show that compared with the delayed synchronous parallel method, the training time and quality, and resource usage of our method are both significantly improved. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Interest Representation Network for Click-Through Rate Prediction

Evolutionary Interest Representation Network for Click-Throu...

引用

IEEE International Conference on Web Services (ICWS)

作者： Renjie Zhou Zhenming Jin Jian Wan Jilin Zhang Xingyu Guo Qiang Liu Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education ITMO Joint Institute Hangzhou Dianzi University Hangzhou China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou China Dept. of Computer and Information Technology Zhejiang Police College Hangzhou China

The rapid development of the Internet has revo-lutionized our lives, providing us with an array of convenient services. However, this revolution has also led to the problem of data overload. Personalized recommendation services have been widely recognized as an effective solution to this problem by both the industrial and academic communities. Accurate prediction of click-through rate (CTR) is a critical task in personalized recommendation systems since it can improve the user’s shopping experience, ultimately increasing revenue for the platform. To achieve accurate CTR prediction, it is crucial to capture user interests. While several methods for interest modeling exist, challenges related to user interest evolution and user behavior noise need further attention. This paper proposes a novel CTR prediction model named the Evolutionary Interest Representation Network (EIRN), which learns the evolving interest representation of users from their behaviors, profiles, and environmental attributes. In the model, we introduce an advertisement correlation graph decomposition layer and a noise filter layer to enhance and purify the user behavior representation. An interest extraction layer is designed to capture sequential correlations and common characteristics between user behaviors, representing their interests. Additionally, as user interests evolve over time and their importance changes, an attention-based interest evolution layer is designed to track the evolution of user interests. Our proposed method is validated using four public datasets and an industrial dataset, showing its superiority over existing CTR prediction methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DyCREM: Dynamic Credit Risk Management Using Edge-Based Blockchain

DyCREM: Dynamic Credit Risk Management Using Edge-Based Bloc...

引用

IEEE/ACM Symposium on Edge Computing (SEC)

作者： Youhuizi Li Weisong Shi Mohit Kumar Jun Chen Key Laboratory of Complex Systems Modeling and Simulation Hangzhou Dianzi University Hangzhou China Department of Computer Science Wayne State University Detroit USA Chain Oriental LLC Beijing China

ISBN: (纸本)9781538694466;9781538694459

Banks play an important role in the financial market, and their profit mainly comes from loan service. Traditional risk management approaches, as the key part in the loan services, still have several issues including low data credibility, unreliable checking and alert delay. We propose a novel dynamic credit risk management system which leverages edge-based blockchain technology to improve the performance and provide a fair loan environment. Besides, we discuss the potential challenges that the system may face, such as data standards, security on edge and scalability.

关键词： Risk management Edge computing Data models Computational modeling Real-time systems Analytical models

来源：评论

学校读者我要写书评

暂无评论

FedECCR: Federated Learning Method with Encoding Comparison and Classification Rectification 19th

FedECCR: Federated Learning Method with Encoding Comparison...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yan Zheng, Hui Wang, Xin Zhang, Beibei Zhou, Mingyao Zhang, Jilin Ren, YongJian School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Zhejiang Lab Hangzhou311100 China Hangzhou Huawei Communication Technology Co. Ltd. Hangzhou310052 China

ISBN: (纸本)9783031545306

Federated learning is a distributed training method that integrates multi-party data information using privacy-preserving technologies through dispersed client data sets to jointly construct a global model under the coordination of a central server. However, in practical applications, there is a high degree of data distribution skewness among clients, which causes the optimization direction of the client models to diverge, resulting in model bias and reducing the accuracy of the global model. Existing methods require the calculation and transmission of much information to correct the optimization direction of the client models, or only roughly limit the deviation of the client models end-to-end, ignoring targeted processing of the internal structure of the model, resulting in unclear improvement effects. To address these problems, we propose a federated optimization algorithm FedECCR based on encoding contrast and classification correction. This algorithm divides the model into an encoder and a classifier. It utilizes prototype contrastive training of the model encoder and unbiased classification correction of the classifier. This approach notably improves the accuracy of the global model while maintaining low communication costs. We conducted experiments on multiple data sets to evaluate the validity of our method, and the quantified results showed that FedECCR can improve the global model classification accuracy by approximately 1% to 6% compared to FedAvg, FedProx, and MOON. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Priority-Based Optimization of I/O Isolation for Hybrid Deployed Services 15th

Priority-Based Optimization of I/O Isolation for Hybrid Depl...

引用

15th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2019

作者： Zhang, Jiancheng Li, Youhuizi Zhou, Li Ren, Zujie Wan, Jian Wang, Yuan Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou Dianzi University Hangzhou China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Zhejiang Lab Hangzhou China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou China Key Enterprise Research Institute of NetEase Big Data of Zhejiang Province Netease Hangzhou Network Co.Ltd Hangzhou China

ISBN: (纸本)9783030301453

With the increasing of software complexity and user demands, collaborative service is becoming more and more popular. Each service focuses on its own specialty, their cooperation can support complicated task with high efficiency. To improve the resources utilization, virtualization technology like container is used and it enables multiple services running in the same physical machine. However, since the host physical machine is shared by several services, the resource competition is inevitable. Isolation is an effective solution, but the weak isolation mechanisms of container cannot handle such complicated scenarios. In the worst situation, the performance of services cannot meet the requirements and the system may crash. In order to solve this problem, we propose a priority-based optimization mechanism for I/O isolation after analyzing the characteristics of typical service workloads. Based on the real-time performance data, priority is automatically assigned to each service and corresponding optimization methods are applied. We evaluate the optimization effects of the priority-based mechanism in both static and dynamic workload cases, besides, the influence of different priority order is also analyzed. The experimental results show that our approach can indeed improve the system performance and guarantee the requirements of all the running services are satisfied. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

DeepDir: a deep learning approach for API directive detection

引用

Science China(Information Sciences) 2021年第9期64卷 238-240页

作者： Jingxuan ZHANG He JIANG Shuai LU Ge LI Xin CHEN College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics State Key Laboratory for Novel Software Technology Nanjing University Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education School of Software Dalian University of Technology School of Electronic Engineering and Computer Science Peking University School of Computer Science and Technology Hangzhou Dianzi University

Dear editor,Software developers tend to reuse existing libraries to facilitate their development process and implement certain functionalities by invoking application programming interfaces(APIs) [1]. However, it remains a challenging task for developers to correctly use APIs [2], so they often consult API learning resources [3, 4]. As one of the most important API learning resources,

关键词： Information systems and Communication Service

来源：评论

学校读者我要写书评

暂无评论

Robust Performance of Secure Transmission in Multi-Antenna Untrusted Relay Networks 5

Robust Performance of Secure Transmission in Multi-Antenna U...

引用

5th IEEE International Conference on Computer and Communications, ICCC 2019

作者： Chen, Dechuan Hu, Jianwei Wang, Lei Dong, Ran Yang, Weiwei Cai, Yueming Army Engineering University of PLA Nanjing210007 China Wu Han Zhong Yuan Electronics Group Co. Ltd. Wuhan430205 China Wu Han Zhong Yuan Communication Co. Ltd. Wuhan430205 China National Key Laboratory Fo R Complex Systems Simulation Beijing100101 China

ISBN: (纸本)9781728147437

In this work, we investigate the secrecy performance in multi-antenna untrusted relay networks, where destination-aided jamming is incorporated to help reduce the amount of confidential information leaked to an untrusted relay. We conduct a robust secrecy performance analysis for the worst-case scenario, where the antenna selection technique is performed at the untrusted relay for data reception and retransmission, and the selected antenna is the one with the highest probability of interrupting the confidential information. In addition, maximal ratio transmission is used at the source and destination for sending information and jamming signals. Under this transmission scheme, we derive the novel exact and asymptotic closed-form expressions for the secrecy outage probability (SOP) to evaluate the secrecy performance with arbitrary number of antennas. Numerical and simulation results indicate that there exists an optimal number of transmit antennas at the source to achieve the tradeoff between reliability and security. © 2019 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Strength of the North African monsoon in the Last Interglacial and under future warming

引用

Atmospheric and Oceanic Science Letters 2023年第3期16卷 20-26页

作者： Jiazhi He Weiyi Sun Jing Wang Bin Wang Jian Liu Key Laboratory for Virtual Geographic Environment Ministry of EducationState Key Laboratory Cultivation Base of Geographical Environment Evolution of Jiangsu ProvinceJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and ApplicationSchool of Geography ScienceNanjing Normal UniversityNanjingChina Department of Atmospheric Sciences and AtmosphereOcean Research Center University of Hawaii at ManoaHonoluluHIUA Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Mathematical ScienceNanjing Normal UniversityNanjingChina Open Studioforthe Simulationof Ocean-Climate-Isotope Qingdao National Laboratoryfor Marine Science and TechnologyQingdaoChina

与人为强迫引起的全球变暖相比,末次间冰期是轨道强迫引起的过去80万年来最暖的一个间冰期,但鲜有人研究末次间冰期中北非季风的响应.因此,本文基于CMIP6多模式模拟结果对比研究了末次间冰期和SSP5-8.5情景下北非季风的响应,发现末次间... 详细信息

与人为强迫引起的全球变暖相比,末次间冰期是轨道强迫引起的过去80万年来最暖的一个间冰期,但鲜有人研究末次间冰期中北非季风的响应.因此,本文基于CMIP6多模式模拟结果对比研究了末次间冰期和SSP5-8.5情景下北非季风的响应,发现末次间冰期下北非季风平均降水及其降水变率均远大于SSP5-8.5情景下的结果.轨道强迫导致的北大西洋暖于南大西洋增加了北非季风环流和平均降水,同时,南北大西洋海温梯度变化通过增强热带北大西洋的海气相互作用增大了海温梯度和撒哈拉低压的变率,从而增强了北非季风降水变率.

关键词：北非季风降水变率末次间冰期全球变暖

来源：评论

学校读者我要写书评

暂无评论

PID Control for Aeroengine Based on Sparrow Search Algorithm

PID Control for Aeroengine Based on Sparrow Search Algorithm

引用

Chinese Automation Congress (CAC)

作者： Liang Xu Hao Wang Ying Liu Wei Xue Ningning Li Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China National Key Laboratory for Complex Systems Simulation Beijing China Beijing Aerospace Propulsion Institute Beijing China

ISBN: (纸本)9781665426480

To address the problem of aeroengine PID parameter optimization and tuning, this work employs the excellent performance of the sparrow search algorithm (SSA) with high convergence accuracy and fast convergence speed to propose a self-tuning PID control method (SSA-PID) for aeroengine parameters. Considering that the oil supply output by the actuator may have a substantial overshoot, the proposed technique adds a penalty mechanism for the overshoot at the output, designs and improves the fitness function weighted by performance indicators, and effectively avoids the possible excessive overshoot and sharp oil supply phenomenon of the engine oil supply. The SSA-PID simulates and verifies the mathematical models of the turbofan engine’ s steady-state operating points on the ground and at high altitudes. The results show that the SSA-PID control method has better parameter tuning and optimization effects, a faster speed step response, and generates a fuel supply that does not have a targe overshoot, thereby proving its effectiveness and feasibility.

关键词： PI control Oils Search problems Mathematical models Steady-state PD control Fuels

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：