检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Kouwenhoven, Tom Peeperkorn, Max Verhoef, Tessa Leiden Institute of Advanced Computer Science Leiden University Netherlands School of Computing University of Kent United Kingdom

ISBN: (纸本)9798891761964

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper, we investigate whether the same happens if artificial languages are optimised for implicit biases of Large Language Models (LLMs). To this end, we simulate a classical referential game in which LLMs learn and use artificial languages. Our results show that initially unstructured holistic languages are indeed shaped to have some structural properties that allow two LLM agents to communicate successfully. Similar to observations in human experiments, generational transmission increases the learnability of languages, but can at the same time result in non-humanlike degenerate vocabularies. Taken together, this work extends experimental findings, shows that LLMs can be used as tools in simulations of language evolution, and opens possibilities for future human-machine experiments in this field. © 2025 Association for Computational Linguistics.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Algorithms for online fault tolerance server consolidation

引用

Digital Communications and Networks 2025年第2期11卷 514-523页

作者： Li, Boyu Wu, Bin Shen, Meng Peng, Hao Li, Weisheng Zhang, Hong Gan, Jie Tian, Zhihong Xu, Guangquan College of Intelligence and Computing Tianjin University Tianjin300350 China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing100081 China School of Computer Science and Technology Zhejiang Normal University Jinhua321004 China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400054 China School of Astronautics Beihang University Beijing100191 China School of Computer Science University of Sydney SydneyNSW20528 Australia Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou511370 China

We study a novel replication mechanism to ensure service continuity against multiple simultaneous server failures. In this mechanism, each item represents a computing task and is replicated into ξ+1 servers for some integer ξ≥1, with workloads specified by the amount of required resources. If one or more servers fail, the affected workloads can be redirected to other servers that host replicas associated with the same item, such that the service is not interrupted by the failure of up to ξ servers. This requires that any feasible assignment algorithm must reserve some capacity in each server to accommodate the workload redirected from potential failed servers without overloading, and determining the optimal method for reserving capacity becomes a key issue. Unlike existing algorithms that assume that no two servers share replicas of more than one item, we first formulate capacity reservation for a general arbitrary scenario. Due to the combinatorial nature of this problem, finding the optimal solution is difficult. To this end, we propose a Generalized and Simple Calculating Reserved Capacity (GSCRC) algorithm, with a time complexity only related to the number of items packed in the server. In conjunction with GSCRC, we propose a robust replica packing algorithm with capacity optimization (RobustPack), which aims to minimize the number of servers hosting replicas and tolerate multiple server failures. Through theoretical analysis and experimental evaluations, we show that the RobustPack algorithm can achieve better performance. © 2024 Chongqing University of Posts and Telecommunications

关键词： Cloud computing Server consolidation Replica Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Containerized Data-Flow Processing for Scalable Real-Time Analytics on Edge Devices 25th

Containerized Data-Flow Processing for Scalable Real-Time A...

引用

25th International Conference on Parallel and Distributed computing, Applications and Technologies, PDCAT 2024

作者： HoseinyFarahabady, MohammadReza Y. Zomaya, Albert School of Computer Science Center for Distributed and High Performance Computing The University of Sydney SydneyNSW2006 Australia

ISBN: (纸本)9789819642069

The increasing demand for real-time data analysis in Internet of Things (IoT) ecosystems has created several challenges, particularly in environments where resources are limited, and minimizing data processing latency is critical. This paper investigates the use of Linux Containerization (LXC) as a lightweight, resource-efficient alternative to traditional virtual machine managers for accelerating data-flow processing applications. We propose an architecture that integrates Linux Containerization (LXC) with a Proportional-Integral-Derivative (PID) controller to dynamically manage I/O resource allocation, ensuring Quality of Service (QoS) for I/O-intensive data analytics workloads. The proposed PID controller continuously monitors system performance and dynamically adjusts I/O resource allocation to mitigate performance degradation. Through a series of experiments, we demonstrate that LXC-based solutions outperform traditional methods in managing I/O-intensive data analytics workloads in IoT and edge ecosystems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Latency- and Privacy-Aware Convolutional Neural Network Distributed Inference for Reliable Artificial Intelligence Systems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 365-377页

作者： Hu, Yuhao Xu, Xiaolong Qi, Lianyong Zhou, Xiaokang Xia, Xiaoyu Nanjing University of Information Science and Technology School of Software Nanjing210044 China College of computer science and technology Qingdao266850 China Shiga University Faculty of Data Science Hikone522-8522 Japan RMIT University School of Computing Technologies MelbourneVIC3000 Australia

Reliable artificial intelligence (AI) systems not only propose a challenge on providing intelligent services with high quality for customers but also require customers' privacy to be protected as much as possible during process of the services. Given the ultrahigh computing load brought by deep-learning-based intelligent services to edge devices and the ultralong distance between edge and cloud, low-latency requirement of intelligent services is hard to meet in single edge computing or cloud computing. Edge-cloud collaborative inference of deep neural networks (DNNs) is considered a feasible solution to the problem. However, former work has not reduced the inference latency to the greatest extent and has not considered privacy protection in distributed systems. To solve the problem, we first establish a novel queue mechanism. Then, the convolution layer split decisions are made based on deep reinforcement learning (DRL) to realize the parallel inference of convolutional neural networks (CNNs) for inference latency reduction. Next, for each CNN, the partition decision is made based on brute force algorithm to further reduce inference latency and protect customers' privacy. Finally, simulation results show that our method performs better than the existing other methods. © 2020 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Integrating Edge Intelligence with Blockchain-Driven Secured IoT Healthcare Optimization Model

引用

computers, Materials & Continua 2025年第5期83卷 1973-1986页

作者： Khulud Salem Alshudukhi Mamoona Humayun Ghadah Naif Alwakid Department of Computer Science College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Department of Computing School of Arts Humanities and Social SciencesUniversity of RoehamptonLondonSW155PHUK

The Internet ofThings(IoT)and edge computing have substantially contributed to the development and growth of smart *** handled time-constrained services and mobile devices to capture the observing environment for surveillance *** systems are composed of wireless cameras,digital devices,and tiny sensors to facilitate the operations of crucial healthcare ***,many interactive applications have been proposed,including integrating intelligent systems to handle data processing and enable dynamic communication functionalities for crucial IoT ***,most solutions lack optimizing relayingmethods and impose excessive overheads for maintaining devices’***,data integrity and trust are another vital consideration for nextgeneration *** research proposed a load-balanced trusted surveillance routing model with collaborative decisions at network edges to enhance energymanagement and resource *** leverages graph-based optimization to enable reliable analysis of decision-making ***,mobile devices integratewith the proposed model to sustain trusted routes with lightweight privacy-preserving and *** proposed model analyzed its performance results in a simulation-based environment and illustrated an exceptional improvement in packet loss ratio,energy consumption,detection anomaly,and blockchain overhead than related solutions.

关键词： Smart cities load balancing blockchain health systems edge computing

来源：评论

学校读者我要写书评

暂无评论

A Secured Internet of Drone Model with Distributed Protocols 4

A Secured Internet of Drone Model with Distributed Protocols

引用

4th International Conference on Evolutionary computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Janani, V.S. Mukhopadhyay, Adwitiya Department of Computer Science Amrita School of Computing Mysuru Campus Amrita Vishwa Vidyapeetham Mysuru570026 India

With the increasing demand in drone technology, Internet-of-drones (IoD) has attracted researchers to contribute multiple benefits for various military and civilian applications. Providing security in a distributed IoD environment is highly challenging due to its inherent open characteristics in radio channels. Nevertheless. communication through such insecure transmission paths in unattended drone applications make it highly vulnerable to privacy and security issues. The proposed work focuses on providing a secured communication path between ground stations and Unmanned Aerial vehicles UAVs (drones) by mitigating inherent vulnerabilities. A hash based cryptographic algorithm is presented through different phases for the registration and key agreement of IoD nodes. A simulation environment is set up using OMNeT++ with a decentralised IoD paradigm to evaluate the proposed protocol. The performance analysis hence proved that the presented protocol provides an efficient secure transmission path for real time UAV applications. © 2025 The Authors. Published by Elsevier B.V.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

MetaHG: Enhancing HGNN Systems Leveraging Advanced Metapath Graph Abstraction 25

MetaHG: Enhancing HGNN Systems Leveraging Advanced Metapath ...

引用

20th European Conference on computer Systems, EuroSys 2025, co-located 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2025

作者： He, Haiheng Liu, Haifeng Zheng, Long Huang, Yu Shen, Xinyang Huang, Wenkan Cao, Chuaihu Liao, Xiaofei Jin, Hai Xue, Jingling 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 Computer Science and Engineering University of New South Wales Australia

ISBN: (纸本)9798400711961

Heterogeneous Graph Neural Networks (HGNNs) are pivotal for extracting semantic and structural information from heterogeneous graphs. Traditional HGNN implementations often grapple with the challenges of excessive metapath instances, requiring substantial storage or incurring high instance-matching overhead. These methods typically suffer from redundant instance encoding and costly semantic graph construction. Addressing these issues, we introduce an advanced Metapath Graph (MG) abstraction that encapsulates the structural information of all metapath instances within a compact representation. This approach significantly reduces storage demands, eliminates redundant instance encodings, and foregoes the need for constructing semantic graphs, thereby facilitating rapid HGNN inference. Our software-based system, MetaHG, leverages layerwise encoding and aggregation to avoid redundancies without the necessity of semantic graphs. It incorporates a fast, lightweight partitioning method to efficiently manage large graphs. Distinctively, MetaHG seamlessly integrates with both dynamic HGNNs and homogeneous GNNs, unlike conventional systems. Comparative evaluations demonstrate that MetaHG surpasses the state-of-the-art BFS- and DFS-based HGNN systems, MAGNN and the software implementation of MetaNMP, by 42.5× and 4.53×, respectively, on average. © 2025 Copyright held by the owner/author(s).

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Causal Analysis and Risk Assessment for Batch Crowdsourcing

引用

IEEE Transactions on Mobile computing 2025年第6期24卷 5312-5323页

作者： Chao, Ke Wang, Shengling Shi, Hongwei Huang, Jianhui Cheng, Xiuzhen Beijing Normal University School of Artificial Intelligence Beijing100875 China Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China Shandong University School of Computer Science and Technology Shandong250100 China

The way of task posting serves as the main pillar in achieving an efficient crowdsourcing market. Pioneer solutions on task posting can be categorized as retail task posting and batch task posting. Unlike retail task posting, which simply matches the most suitable worker to tasks, batch task posting considers the collaborations not only between workers and tasks but also among tasks, which brings high efficiency, low costs, and satisfactory task completion rates. However, the state of the arts on batch task posting leverage specific attributes to combine tasks as bundles for posting, leading to limited scalability. Hence, we propose a causal analysis framework for batch crowdsourcing to achieve an attribute-independent batch crowdsourcing solution that disentangles multi-factors to uncover the posting merits of tasks bundled at optimal prices, based on which an approximately optimal algorithm is further introduced to form reasonable bundles for posting. Since batch crowdsourcing may incur losses due to short-term profit fluctuation, a risk assessment method is proposed to encourage the requestor to act properly for loss mitigations. Our work explores the causal analysis and risk assessment in batch crowdsourcing for the first time, with the following highlights: 1) generality. It proposes a composite metric for gauging task bundles which avoids the issue of attribute dependence in the state of the arts, resulting in better universality;2) synergy. By collaboratively considering the "value"and "relative position"of variables, our work derives results reflecting causal relationships rather than naive correlations;3) precision. We not only elucidate the probability of risk in batch crowdsourcing but also delineate the rate function governing its probability decay. This allows a requestor to know when and how fast to halt batch task posting. © 2025 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

DAEA: Enhancing Entity Alignment in Real-World Knowledge Graphs Through Multi-Source Domain Adaptation 31

DAEA: Enhancing Entity Alignment in Real-World Knowledge Gra...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Linyan Zhou, Shiqiao Cheng, Jingwei Zhang, Fu Wan, Jizheng Wang, Shou Lee, Mark School of Computer Science and Engineering Northeastern University China School of Computer Science University of Birmingham United Kingdom Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Entity Alignment (EA) is a critical task in Knowledge Graph (KG) integration, aimed at identifying and matching equivalent entities that represent the same real-world objects. While EA methods based on knowledge representation learning have shown strong performance on synthetic benchmark datasets such as DBP15K, their effectiveness significantly decline in real-world scenarios which often involve data that is highly heterogeneous, incomplete, and domain-specific, as seen in datasets like DOREMUS and AGROLD. Addressing this challenge, we propose DAEA, a novel EA approach with Domain Adaptation that leverages the data characteristics of synthetic benchmarks for improved performance in real-world datasets. DAEA introduces a multi-source KGs selection mechanism and a specialized domain adaptive entity alignment loss function to bridge the gap between real-world data and optimal benchmark data, mitigating the challenges posed by aligning entities across highly heterogeneous KGs. Experimental results demonstrate that DAEA outperforms state-of-the-art models on real-world datasets, achieving a 29.94% improvement in Hits@1 on DOREMUS and a 5.64% improvement on AGROLD. Code is available at https://***/yangxiaoxiaoly/DAEA. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Superiority of Unsupervised Learning on GPU Cryptojacking Detection: Practice on Magnetic Side Channel-based Mechanism

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4874-4889页

作者： Cao, Hangcheng Xu, Guowen He, Ziyang Shi, Shaoqing Xu, Shengmin Wu, Cong Ning, Jianting Hunan University College of Computer Science and Electronic Engineering China City University of Hong Kong Department of Computer Science Hong Kong University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China Zhengzhou University School of Cyber Science and Engineering Zhengzhou China Zhengzhou University International College Zhengzhou China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fuzhou China Nanyang Technological University College of Computing and Data Science Singapore Wuhan University School of Cyber Science and Engineering Wuhan China City University of Macau Faculty of Data Science China

Ample profits of GPU cryptojacking attract hackers to recklessly invade victims’ devices, for completing specific cryptocurrency mining tasks. Such malicious invasion undoubtedly obstructs normal device usage and wastes computation resources. To resist the threat of GPU cryptojacking, existing works aim to timely detect and clear away it, by distinguishing the dissimilitude between it and legitimate applications. However, these detection mechanisms inappropriately rely on two conflict cornerstones, manifested in leveraging mutable samples of illegitimate cryptojacking to design supervision-based detection models requiring samples with stable patterns. This limitation compromises the practicability of existing detection mechanisms in the face of mutable cryptojacking samples. To fill the gap, we explore the superiority of unsupervised learning in handling this issue and further propose an unsupervised manner-enabled detection mechanism named MagInspector, only using legitimate applications’ magnetic signatures from GPU side channels for model construction. MagInspector innovates in training an unsupervised autoencoder network by an adversarial mode that well learns the stable signature patterns of legitimate applications, while incompatible with mutable cryptojacking ones. In the process of model training, we elaborately extract mutual energy cumulation distribution features to represent legitimate applications to overcome the impact of their inter-type differences. Meanwhile, a locality sensitive hashing-driven outlier removal algorithm is designed to enhance MagInspector’s robustness to the noise samples. Finally, extensive experiments are conducted on GPUs covering four generations of common NVIDIA architectures and two generations of AMD architectures;the results show that applying MagInspector to mutable cryptojacking signature detection achieves a significant average accuracy improvement of 25.5% and 17.8%, respectively. © 2005-2012 IEEE.

关键词： Unsupervised learning

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：