检索结果-内蒙古大学图书馆

Evolutionary Optimization with a Simplified Helper Task for High-Dimensional Expensive Multiobjective Problems

ACM Transactions on Evolutionary Learning and Optimization 2024年第4期4卷 1-32页

作者： Wu, Xunfeng Lin, Qiuzhen Zhou, Junwei Liu, Songbai Coello Coello, Carlos A. Leung, Victor C. M. College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China Mexico City07300 Mexico Department of Electrical and Computer Engineering University of British Columbia VancouverBCV6T 1Z4 Canada

In recent years, surrogate-Assisted evolutionary algorithms (SAEAs) have been sufficiently studied for tackling computationally expensive multiobjective optimization problems (EMOPs), as they can quickly estimate the qualities of solutions by using surrogate models to substitute for expensive evaluations. However, most existing SAEAs only show promising performance for solving EMOPs with no more than 10 dimensions, and become less efficient for tackling EMOPs with higher dimensionality. Thus, this article proposes a new SAEA with a simplified helper task for tackling high-dimensional EMOPs. In each generation, one simplified task will be generated artificially by using random dimension reduction on the target task (i.e., the target EMOPs). Then, two surrogate models are trained for the helper task and the target task, respectively. Based on the trained surrogate models, evolutionary multitasking optimization is run to solve these two tasks so that the experiences of solving the helper task can be transferred to speed up the convergence of tackling the target task. Moreover, an effective model management strategy is designed to select new promising samples for training the surrogate models. When compared to five competitive SAEAs on four well-known benchmark suites, the experiments validate the advantages of the proposed algorithm on most test cases. © 2024 held by the owner/author(s).

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

Challenges of Using Pre-trained Models: The Practitioners' Perspective 31

Challenges of Using Pre-trained Models: The Practitioners' P...

引用

31st IEEE International Conference on software Analysis, Evolution and Reengineering, SANER 2024

作者： Tan, Xin Li, Taichuan Chen, Ruohe Liu, Fang Zhang, Li School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Economics and Management Beihang University Beijing China

ISBN: (纸本)9798350330663

The challenges associated with using pre-trained models (PTMs) have not been specifically investigated, which hampers their effective utilization. To address this knowledge gap, we collected and analyzed a dataset of 5,896 PTM-related questions on Stack Overflow. We first analyze the popularity and difficulty trends of PTM-related questions. We find that PTM-related questions are becoming more and more popular over time. However, it is noteworthy that PTM-related questions not only have a lower response rate but also exhibit a longer response time compared to many well-researched topics in software engineering. This observation emphasizes the significant difficulty and complexity associated with the practical application of PTMs. To delve into the specific challenges, we manually annotate 430 PTM-related questions, categorizing them into a hierarchical taxonomy of 42 codes (i.e., leaf nodes) and three categories. This taxonomy encompasses many PTM prominent challenges such as fine-tuning, output understanding, and prompt customization, which reflects the gaps between current techniques and practical needs. We discuss the implications of our study for PTM practitioners, vendors, and educators, and suggest possible directions and solutions for future research. © 2024 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Fair and Communication-Efficient Personalized Federated Learning 18th

Fair and Communication-Efficient Personalized Federated Lea...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Zheng, Yifu Zheng, Xu Wang, Tingqi Mu, Chong Zhakiyev, Nurkhat School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Science and Innovation Astana IT University Astana Kazakhstan

ISBN: (纸本)9783031714665

Personalized Federated Learning (pFL) is among the most popular tasks in distributed deep learning, which compensates for mutual knowledge and enables device-specific model personalization. However, the effectiveness of pFL is severely impeded by challenges on fairness and significant communication overhead, where devices holding essential samples have to devote extensive resources for model training. To address these issues, we introduce the Fair and Communication-Efficient Personalized Federated Learning (FCE-PFL) framework, which harmonizes performance and device fairness while maintaining communication costs. Based on the Dempster-Shafer Theory, FCE-PFL employs assistance and contribution metrics to quantify the auxiliary information a client receives and provides. Then FCE-PFL balances and adjusts the involvement of devices in each training iteration, so as to facilitate fair training by constraining the maximum resource consumption per device and reduce the overall communication overhead. Our framework has been proven to be superior to existing methods in accuracy through rigorous experiments on the CIFAR10 and CIFAR100 datasets, demonstrating its potential as a fair and efficient pFL solution. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Vehicle Surface Damage Analysis Model Based on YOLOv8

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第6期52卷 1921-1929页

作者： Tan, Xu Zhao, Ji School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

The rapid evolution of intelligent automotive systems has driven the urgent need for advanced damage assessment methodologies, revealing critical limitations in conventional visual inspection techniques. This study posits a multi-task learning architecture for vehicular surface damage quantification through synergistic integration of instance segmentation and monocular depth estimation. Three key technical innovations are incorporated: 1) A Heterogeneous Feature Single-Phase Booster (HFSPB) module utilizing RepViT layers to optimize backbone feature discriminability;2) A Channel-wise Cross Fusion Block facilitating adaptive multi-scale feature amalgamation with intrinsic noise attenuation;3) A depth estimation head implementing Depth Interval Attraction Refinement for geometrically consistent surface reconstruction. Benchmark evaluations revealed a threefold acceleration in inference speed relative to conventional approaches, coupled with robust metric performance (δ₁: 91.9%, δ₂: 99.4%, δ₃: 99.8%, REL=0.089, RMSE=0.312). This integrated framework establishes a computationally efficient paradigm for multimodal damage characterization, providing critical insights for autonomous vehicle maintenance systems. © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Fairness with adaptive weight in network attack detection 29

Fairness with adaptive weight in network attack detection

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Wen, Xuezhi Wang, Nan Sun, Yuanlin Xu, Fan Zhang, Dalin Zhao, Xibin Beijing Jiaotong University School of Software Engineering Beijing China University of Science and Technology of China School of Computer Science and Technology Anhui China Tsinghua University School of Software Engineering Beijing China

ISBN: (纸本)9798350330717

Network attacks aim to exploit vulnerabilities inherent in network protocols, which is widely used in many real-world applications. In the process of network anomaly detection, most methods train the model by minimizing the average empirical risk of all samples. However, due to the uneven distribution of samples from different protocols, detection models tend to be biased against minority protocols groups. To address this issue, we propose an adaptive weight assignment method for network attack detection, which emphasizes more on error-prone samples in prediction and enhances adequate representation of minority groups for fairness. We conduct experiments on two widely used datasets, KDD and NSLKDD. According to the results, our method achieves better performance than state-of-the-art methods for classification and regression tasks, and is robust to label noise in the test dataset. © 2023 IEEE.

关键词： Adaptive weight Attack detection Fairness

来源：评论

学校读者我要写书评

暂无评论

HTDcr:a job execution framework for high-throughput computing on supercomputers

引用

science China(Information sciences) 2024年第1期67卷 69-85页

作者： Jiazhi JIANG Dan HUANG Hu CHEN Yutong LU Xiangke LIAO School of Computer Science and Engineering Sun Yat-sen University School of Software Engineering South China University of Technology

High-throughput computing(HTC) is a computing paradigm that aims to accomplish jobs by easily breaking them into smaller,independent ***,it requires a large amount of computing power for a long *** existing HTC frameworks are job-oriented without support for coscheduling with hardware architecture and task-level ***,most of the frameworks reach a limited scale,and their usability needs further ***,we present HTDcr,a job execution framework for the HTC on *** study aims to improve the throughput,task dispatching,and usability of the *** detail,the throughput optimizations include a sophisticated designed task management system,a hierarchical scheduler,and the co-optimization of the task-scheduling strategy with the application and hardware *** optimizations for usability include a programable execution workflow,mechanisms for more robust and reliable service qualities,and a fine-grained resource allocation system for the colocation of multiple *** to our evaluations,HTDcr can achieve outstanding scalability and high throughput on large-scale clusters for the HTC *** evaluate HTDcr with several microbenchmarks and real-world applications on Tianhe-2 and Sunway TaihuLight to demonstrate its effects on existing design *** instance,the task scheduling for two real-world applications integrated with the application and hardware characteristics achieves 1.7× and 1.9× speedups over the basic task-scheduling strategy.

关键词： high-throughput computing supercomputer task scheduling middleware password guessing

来源：评论

学校读者我要写书评

暂无评论

Faster AMEDA-A Hybrid Mesoscale Eddy Detection Algorithm

引用

computer Modeling in engineering & sciences 2024年第11期141卷 1827-1846页

作者： Xinchang Zhang Xiaokang Pan Rongjie Zhu Runda Guan Zhongfeng Qiu Biao Song Organization Department Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Teacher Education Nanjing University of Information Science and TechnologyNanjing210044China School of Electronics&Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China School of Software Nanjing University of Information Science and TechnologyNanjing210044China

Identification of ocean eddies from a large amount of ocean data provided by satellite measurements and numerical simulations is crucial,while the academia has invented many traditional physical methods with accurate detection capability,but their detection computational efficiency is *** recent years,with the increasing application of deep learning in ocean feature detection,many deep learning-based eddy detection models have been developed for more effective eddy detection from ocean *** it is difficult for them to precisely fit some physical features implicit in traditional methods,leading to inaccurate identification of ocean *** this study,to address the low efficiency of traditional physical methods and the low detection accuracy of deep learning models,we propose a solution that combines the target detection model Faster Region with CNN feature(Faster R-CNN)with the traditional dynamic algorithm Angular Momentum Eddy Detection and Tracking Algorithm(AMEDA).We use Faster R-CNN to detect and generate bounding boxes for eddies,allowing AMEDA to detect the eddy center within these bounding boxes,thus reducing the complexity of center *** demonstrate the detection efficiency and accuracy of this model,this paper compares the experimental results with AMEDA and the deep learning-based eddy detection method *** results show that the eddy detection results of this paper are more accurate than eddyNet and have higher execution efficiency than AMEDA.

关键词： Mesoscale eddy detection object detection contour detection remote sensing

来源：评论

学校读者我要写书评

暂无评论

Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection 29

Few-shot Message-Enhanced Contrastive Learning for Graph Ano...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Xu, Fan Wang, Nan Wen, Xuezhi Gao, Meiqi Guo, Chaoqun Zhao, Xibin University of Science and Technology of China School of Computer Science and Technology Anhui China Beijing Jiaotong University School of Software Engineering Beijing China Tsinghua University School of Software Engineering Beijing China

ISBN: (纸本)9798350330717

Graph anomaly detection plays a crucial role in identifying exceptional instances in graph data that deviate significantly from the majority. It has gained substantial attention in various domains of information security, including network intrusion, financial fraud, and malicious comments, et al. Existing methods are primarily developed in an unsupervised manner due to the challenge in obtaining labeled data. For lack of guidance from prior knowledge in unsupervised manner, the identified anomalies may prove to be data noise or individual data instances. In real-world scenarios, a limited batch of labeled anomalies can be captured, making it crucial to investigate the few-shot problem in graph anomaly detection. Taking advantage of this potential, we propose a novel few-shot Graph Anomaly Detection model called FMGAD (Few-shot Message-Enhanced Contrastive-based Graph Anomaly Detector). FMGAD leverages a self-supervised contrastive learning strategy within and across views to capture intrinsic and transferable structural representations. Furthermore, we propose the Deep-GNN message-enhanced reconstruction module, which extensively exploits the few-shot label information and enables long-range propagation to disseminate supervision signals to deeper unlabeled nodes. This module in turn assists in the training of self-supervised contrastive learning. Comprehensive experimental results on six real-world datasets demonstrate that FMGAD can achieve better performance than other state-of-the-art methods, regardless of artificially injected anomalies or domain-organic anomalies. © 2023 IEEE.

关键词： Deep-GNN few-shot graph anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-Graph Contrastive Network for Incomplete Multi-View Clustering

引用

IEEE Transactions on Multimedia 2025年 27卷 2747-2759页

作者： Xue, Zhe Li, Yawen Guan, Zhongchao Li, Wenling Liang, Meiyu Zhou, Hai Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing100876 China Beijing University of Posts and Telecommunications School of Economics and Management Beijing100876 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China

Food categorization is pivotal in numerous aspects of everyday life, assisting in the selection of food, managing diets, and addressing essential survival requirements. By leveraging the complementary information of various views, multi-view learning usually achieves superior performance compared to the single-view learning methods. However, characterized by the unrestrained openness of internet platforms and potential inconsistencies in food data collection processes, multi-view features often suffer from data loss, resulting in incomplete multi-view food data. Conventional multi-view clustering methods often falter in effectively capitalizing on the diverse correlations contained in food data, and exhibit limitations in dealing with the noise and irregularities pervading different views. Addressing these challenges, this paper presents the Robust Multi-Graph Contrastive network (RMGC) for multi-view food clustering. RMGC artfully combines multi-view representation learning with multi-graph contrastive regularization, creating a cohesive framework to manage incomplete multi-view data. By developing a multi-view encoding network, RMGC seamlessly blends various views into a cohesive representation, astutely assessing the significance of each view. More importantly, the proposed robust multi-graph contrastive regularization enhances the precision of the learned representation and successfully counteracts the noise and unreliability in multi-view data. The experiments conducted across several multi-view datasets manifest the effectiveness of RMGC, showing its superiority over existing methods. Our method not only making an advancement in food categorization but also contributes to the broader field of multi-view learning, offering innovative solutions for handling incomplete and noisy multi-view data. © 1999-2012 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Aspect Interest Neighbor-Augmented Network for Next-Basket Recommendation 48

Multi-Aspect Interest Neighbor-Augmented Network for Next-Ba...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Deng, Zhiying Li, Jianjun Guo, Zhiqiang Li, Guohui Huazhong University of Science and Technology School of Computer Science and Technology China Huazhong University of Science and Technology School of Software Engineering China

ISBN: (纸本)9781728163277

Next-basket recommendation (NBR) is a type of recommendation task that focuses on mining user interests based on the sequential basket records in which users purchase multiple items at a time. Limited by the sparsity brought by short-term user interaction behavior, existing NBR methods typically fail to mine fine-grained and complete representation of user interests, resulting in unsatisfactory recommendation performance. To address this issue, we propose a novel Multi-aspect Interest Neighbor-augmented Network (MINN) to capture fine-grained and complete representation of user interest for the next basket prediction. Specifically, we first design a multi-aspect interest encoder to learn representations of users and items in the multi-aspect interest space. Semantic neighbors are then selected for user to enhance the user's representation of interest through a semantic neighbor augmentation mechanism. Finally, the user's representation of interest and his/her repeated purchase behavior are jointly considered to implement the next basket prediction. Extensive experimental studies on two benchmark datasets demonstrate that MINN outperforms several representative NBR methods and achieves new state-of-the-art results. © 2023 IEEE.

关键词： multi-aspect interest learning neighbor augmentation next-basket recommendation Recommender systems

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：