检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Shaochen Wu, Zihao Zhao, Huaqin Shu, Peng Liu, Zhengliang Liao, Wenxiong Li, Sheng Sikora, Andrea Liu, Tianming Li, Xiang School of Computing University of Georgia United States School of Computer Science and Engineering South China University of Technology China School of Data Science University of Virginia United States Department of Clinical and Administrative Pharmacy University of Georgia College of Pharmacy United States Massachusetts General Hospital Harvard Medical School United States

In this study, we leverage LLM to enhance the semantic analysis and develop similarity metrics for texts, addressing the limitations of traditional unsupervised NLP metrics like ROUGE and BLEU. We develop a framework where LLMs such as GPT-4 are employed for zero-shot text identification and label generation for radiology reports, where the labels are then used as measurements for text similarity. By testing the proposed framework on the MIMIC data, we find that GPT-4 generated labels can significantly improve the semantic similarity assessment, with scores more closely aligned with clinical ground truth than traditional NLP metrics. Our work demonstrates the possibility of conducting semantic analysis of the text data using semi-quantitative reasoning results by the LLMs for highly specialized domains. While the framework is implemented for radiology report similarity analysis, its concept can be extended to other specialized domains as well. © 2024, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection

FedMoS: Taming Client Drift in Federated Learning with Doubl...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Xiong Wang Yuxin Chen Yuqing Li Xiaofei Liao Hai Jin Bo Li 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 Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients’ selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal ${{\mathcal{O}}}\left({{T^{ - 2/3}}}\right)$ convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-Click Exploits and Malware: An In-Depth Analysis and Case Studies

Zero-Click Exploits and Malware: An In-Depth Analysis and Ca...

引用

Security of Information and Networks (SIN), International Conference on

作者： Prabith GS S Abhishek Anjali T Radhika Ravindran Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Departmant of Computer Science (Data Science) State University of New York University at Buffalo USA

This research paper provides an in-depth study of zero click exploits and malware exploring their techniques, implications and real-world instances. Our primary objective is to offer a clear understanding of the constantly evolving realm of cyber threats, all the while highlighting the pressing need for robust security measures as a bulwark against these sophisticated attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A DQN-Based Approach for Online Service Placement in Mobile Edge computing 16th

A DQN-Based Approach for Online Service Placement in Mobile ...

引用

16th EAI International Conference on Collaborative computing: Networking, Applications, and Worksharing, CollaborateCom 2020

作者： Jie, Xiaogan Liu, Tong Gao, Honghao Cao, Chenhong Wang, Peng Tong, Weiqin School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Shanghai Engineering Research Center of Intelligent Computing System Shanghai China

ISBN: (纸本)9783030675394

Due to the development of 5G networks, computation intensive applications on mobile devices have emerged, such as augmented reality and video stream analysis. Mobile edge computing is put forward as a new computing paradigm, to meet the low-latency requirements of applications, by moving services from the cloud to the network edge like base stations. Due to the limited storage space and computing capacity of an edge server, service placement is an important issue, determining which services are deployed at edge to serve corresponding tasks. The problem becomes particularly complicated, with considering the stochastic arrivals of tasks, the additional latency incurred by service migration, and the time spent for waiting in queues for processing at edge. Benefiting from reinforcement learning, we propose a deep Q network based approach, by formulating service placement as a Markov decision process. Real-time service placement strategies are output, to minimize the total latency of arrived tasks in a long term. Extensive simulation results demonstrate that our approach works effectively. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Optical Wireless Communication System in Fog Weather Conditions

Performance Evaluation of Optical Wireless Communication Sys...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Kanagaraj Venusamy S. Kannadhasan E. Prakash Priyadarsini K Department of Mechatronics Engineering Rajalakshmi Engineering College Chennai India Department of Electronics and Communication Engineering Study World College of Engineering Coimbatore Chennai India Department of Data Science and Business Systems School of Computing SRM Institute of Science & Technology Kattankulathur Chennai India

Free space optical communication being an emerging technology, has Fog as a primary challenge on its way which makes fog modelling necessary to manage wireless networks. In this paper, an analytical study was made on the performance of five mathematical fog models employing the NRZ-OOK modulation scheme for transmission and a Si PIN photodiode as the photo receptor. This article focuses on numerous performance specifications including Signal to noise ratio [SNR], Bit error rate [BER] and channel capacity all against visibility under fog for propagations wavelengths of 850 nm and 1550 nm and simulations were carried out in MATLAB. The results indicate that the wavelength of 1550nm as more advantageous option over the others for FSO wireless links and an investigation on different models and their characteristics define their suitability for implementation.

关键词： PIN photodiodes Wireless networks Bit error rate Mathematical models Silicon Optical fiber communication Optical transmitters

来源：评论

学校读者我要写书评

暂无评论

Improving Software Defined Network Controllers in a Multi-Vendor Environment

SSRN

引用

SSRN 2023年

作者： Deneke, Bereketeab Berhanu Beyene, Asrat Mulatu Haile, Endalew Ayenew Department of Computer Science School of Graduate Studies St. Mary’s University Addis Ababa Ethiopia High Performance Computing & Big Data Analytics CoE Department of Electrical and Computer Engineering Addis Ababa Science and Technology University Addis Ababa Ethiopia Adama Science and Technology University School of Electrical Engineering and Computing Electrical Power and Control Engineering Adama Ethiopia

Software Defined Networking (SDN) is an emerging networking paradigm with the potential to foster innovation through programmable networks. SDNs are characterized by the separation of control and data planes where, in a logically centralized controller, it’s possible to make routing decisions on behalf of forwarding elements. For this, there are different protocols used like Open Flow, Forward and Control Element Separation (FORCES), Path Computation Element Protocol (PCEP), Network Configuration Protocol (NETCONF), and Interface to Routing System (IRS). Border Gateway Protocol (BGP) is one such protocol that can enable the network programmability promised by SDNs. The controllers used in BGP as control plane protocol leverages RESTCONF (RFC 8040) as management plane protocol to interact with physical routers, switches, and network service firewalls. Therefore, the aim of this work is to improve the performance of SDN controllers using BGP enabling a multi-vendor environment without requiring infrastructure upgrade showcasing how interoperability can be achieved. The proposed system is implemented using OpenDaylight controllers. The performance of the prototype is evaluated using Latency, Throughput, CPU consumption, and TTL (Time to Live). Based on the simulation results it is observed that the SDN controllers that use BGP show improvements in terms of Latency and Throughput. © 2023, The Authors. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Scribble-supervised semantic segmentation with prototype-based feature augmentation 24

Scribble-supervised semantic segmentation with prototype-bas...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Guiyang Chan Pengcheng Zhang Hai Dong Shunhui Ji Bainian Chen Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China and College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://***/TranquilChan/PFA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unifying Synergies between Self-supervised Learning and Dynamic Computation

arXiv

引用

arXiv 2023年

作者： Krishna, Tarun Rai, Ayush K. Drimbarean, Alexandru Arazo, Eric Albert, Paul Smeaton, Alan F. McGuinness, Kevin O’Connor, Noel E. Insight Centre for Data Analytics Dublin City University Dublin Ireland School of Computing Dublin City University Dublin Ireland School of Electronic Engineering Dublin City University Dublin Ireland Xperi Corporation Galway Ireland

Computationally expensive training strategies make self-supervised learning (SSL) impractical for resource-constrained industrial settings. Techniques like knowledge distillation (KD), dynamic computation (DC), and pruning are often used to obtain a lightweight model, which usually involves multiple epochs of fine-tuning (or distilling steps) of a large pre-trained model, making it more computationally challenging. In this work we present a novel perspective on the interplay between the SSL and DC paradigms. In particular, we show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in an SSL setting without any additional fine-tuning or pruning steps. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off and therefore yields a generic and multi-purpose architecture for application-specific industrial settings. Extensive experiments on several image classification benchmarks including CIFAR-10/100, STL-10 and ImageNet-100, demonstrate that the proposed training strategy provides a dense and corresponding gated sub-network that achieves on-par performance compared with the vanilla self-supervised setting, but at a significant reduction in computation in terms of FLOPs, under a range of target budgets (td). © 2023, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Strategy Bus Deviation-Driven Layer Assignment Algorithm

Multi-Strategy Bus Deviation-Driven Layer Assignment Algorit...

引用

Electronics Design Automation (ISEDA), International Symposium of

作者： Yantao Yu Zepeng Li Jiarui Chen Xing Huang Genggeng Liu Ning Xu College of Computer and Data Science Fuzhou University Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China School of Computer Science Northwestern Polytechnical University Xian China School of Information Engineering Wuhan University of Technology Wuhan China

ISBN: (数字)9798350352030

ISBN: (纸本)9798350352047

In modern very large-scale integration (VLSI) design, the solution quality of the bus routing is a crucial factor that determines the timing and power of circuit, and finally affects the performance and yield of chips. Taking bus deviation as the main optimization objective, an effective multi-strategy bus deviation-driven layer assignment algorithm is proposed to solve the timing-matching problem of bus routing. First, a net priority determination method that integrates multiple features is presented to determine the layer assignment order, thus obtaining a routing sequence which can weigh the wirelength and bus deviation well. Second, an effective single net layer assignment algorithm is proposed to assign each net based on dynamic programming, thus reducing the number of vias. Third, a layer shifting strategy based on the bus lookup table is designed to effectively balance total wirelength and bus deviation by sacrificing a certain number of vias. Experimental results, compared to existing work, show that the proposed algorithm can achieve significant optimization on the bus deviation and total wirelength, and finally obtain the best results in terms of the bus deviation, which is the most important optimization objective for bus routing.

关键词： Design automation Heuristic algorithms Very large scale integration Routing Timing Pins Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction

arXiv

引用

arXiv 2025年

作者： Liu, Wenxuan Li, Zixuan Bai, Long Zuo, Yuxin Xu, Daozhu Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Geo-Information Engineering Shaanxi Xi’an China

Developing a general-purpose extraction system that can extract events with massive types is a long-standing target in Event Extraction (EE). In doing so, the challenge comes from two aspects: 1) The absence of an efficient and effective annotation method. 2) The absence of a powerful extraction method can handle massive types. For the first challenge, we propose a collaborative annotation method based on Large Language Models (LLMs). Through collaboration among multiple LLMs, it first refines annotations of trigger words from distant supervision and then carries out argument annotation. Next, a voting phase consolidates the annotation preferences across different LLMs. Finally, we create the EEMT dataset, the largest EE dataset to date, featuring over 200,000 samples, 3,465 event types, and 6,297 role types. For the second challenge, we propose an LLM-based Partitioning EE method called LLM-PEE. To overcome the limited context length of LLMs, LLM-PEE first recalls candidate event types and then splits them into multiple partitions for LLMs to extract events. The results in the supervised setting show that LLM-PEE outperforms the state-of-the-art methods by 5.4% in event detection and 6.1% in argument extraction. In the zero-shot setting, LLM-PEE achieves up to 12.9% improvement compared to mainstream LLMs, demonstrating its strong generalization capabilities. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

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：