首页 > 最新文献

ACM Computing Surveys最新文献

英文 中文
Modality deep-learning frameworks for fake news detection on social networks: a systematic literature review 用于社交网络假新闻检测的模态深度学习框架:系统性文献综述
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-23 DOI: 10.1145/3700748
Mohamed Mostafa, Ahmad S Almogren, Muhammad Al-Qurishi, Majed Alrubaian
Fake news on social networks is a challenging problem due to the rapid dissemination and volume of information, as well as the ease of creating and sharing content anonymously. Fake news stories are problematic not only for the credibility of online journalism, but also due to their detrimental real-world consequences. The primary research objective of this study is: What are the recent state-of-the-art modalities based on deep learning to detect fake news in social networks. This paper presents a systematic literature review of deep learning-based fake news detection models in social networks. The methodology followed a rigorous approach, including predefined criteria for study selection of deep learning modalities. This study focuses on the types of deep learning modalities; unimodal (refers to the use of a single model for analysis or modeling purposes) and multimodal models (refers to the integration of multiple models). The results of this review reveal the strengths and weaknesses of modalities approaches, as well as the limitations of low-resource languages datasets. Furthermore, it provides insights into future directions for deep learning models and different fact checking techniques. At the end of this study, we discuss the problem of fake news detection in the era of large language models in terms of advantages, drawbacks, and challenges.
社交网络上的假新闻是一个具有挑战性的问题,这是因为信息传播速度快、数量大,而且匿名创建和分享内容非常容易。假新闻不仅会影响网络新闻的可信度,还会对现实世界造成有害影响。本研究的主要研究目标是最近有哪些基于深度学习的先进模式来检测社交网络中的假新闻。本文对基于深度学习的社交网络假新闻检测模型进行了系统的文献综述。研究方法遵循严格的方法,包括预定义的深度学习模式研究选择标准。本研究侧重于深度学习模式的类型;单模态(指使用单一模型进行分析或建模)和多模态模型(指整合多个模型)。综述结果揭示了模式方法的优缺点,以及低资源语言数据集的局限性。此外,它还为深度学习模型和不同事实检查技术的未来发展方向提供了见解。在本研究的最后,我们从优势、缺点和挑战三个方面讨论了大型语言模型时代的假新闻检测问题。
{"title":"Modality deep-learning frameworks for fake news detection on social networks: a systematic literature review","authors":"Mohamed Mostafa, Ahmad S Almogren, Muhammad Al-Qurishi, Majed Alrubaian","doi":"10.1145/3700748","DOIUrl":"https://doi.org/10.1145/3700748","url":null,"abstract":"Fake news on social networks is a challenging problem due to the rapid dissemination and volume of information, as well as the ease of creating and sharing content anonymously. Fake news stories are problematic not only for the credibility of online journalism, but also due to their detrimental real-world consequences. The primary research objective of this study is: What are the recent state-of-the-art modalities based on deep learning to detect fake news in social networks. This paper presents a systematic literature review of deep learning-based fake news detection models in social networks. The methodology followed a rigorous approach, including predefined criteria for study selection of deep learning modalities. This study focuses on the types of deep learning modalities; unimodal (refers to the use of a single model for analysis or modeling purposes) and multimodal models (refers to the integration of multiple models). The results of this review reveal the strengths and weaknesses of modalities approaches, as well as the limitations of low-resource languages datasets. Furthermore, it provides insights into future directions for deep learning models and different fact checking techniques. At the end of this study, we discuss the problem of fake news detection in the era of large language models in terms of advantages, drawbacks, and challenges.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142488348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Single-Document Abstractive Text Summarization: A Systematic Literature Review 单文档摘要文本总结:系统性文献综述
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-18 DOI: 10.1145/3700639
Abishek Rao, Shivani Aithal, Sanjay Singh
ive text summarization is a task in natural language processing that automatically generates the summary from the source document in a human-written form with minimal loss of information. Research in text summarization has shifted towards abstractive text summarization due to its challenging aspects. This study provides a broad systematic literature review of abstractive text summarization on single-document summarization to gain insights into the challenges, widely used datasets, evaluation metrics, approaches, and methods. This study reviews research articles published between 2011 and 2023 from popular electronic databases. In total, 226 journal and conference publications were included in this review. The in-depth analysis of these papers helps researchers understand the challenges, widely used datasets, evaluation metrics, approaches, and methods. This paper identifies and discusses potential opportunities and directions, along with a generic conceptual framework and guidelines on abstractive summarization models and techniques for research in abstractive text summarization.
文本摘要是自然语言处理中的一项任务,它能以人工编写的形式自动生成源文件的摘要,并将信息损失降到最低。由于抽象文本摘要的挑战性,文本摘要的研究已经转向抽象文本摘要。本研究对抽象文本摘要的单篇文档摘要进行了广泛系统的文献综述,以深入了解其面临的挑战、广泛使用的数据集、评估指标、方法和手段。本研究综述了 2011 年至 2023 年间在流行电子数据库中发表的研究文章。共有 226 篇期刊和会议出版物被纳入本综述。对这些论文的深入分析有助于研究人员了解所面临的挑战、广泛使用的数据集、评估指标、方法和途径。本文确定并讨论了抽象文本摘要研究的潜在机遇和方向,以及关于抽象摘要模型和技术的通用概念框架和指南。
{"title":"Single-Document Abstractive Text Summarization: A Systematic Literature Review","authors":"Abishek Rao, Shivani Aithal, Sanjay Singh","doi":"10.1145/3700639","DOIUrl":"https://doi.org/10.1145/3700639","url":null,"abstract":"ive text summarization is a task in natural language processing that automatically generates the summary from the source document in a human-written form with minimal loss of information. Research in text summarization has shifted towards abstractive text summarization due to its challenging aspects. This study provides a broad systematic literature review of abstractive text summarization on single-document summarization to gain insights into the challenges, widely used datasets, evaluation metrics, approaches, and methods. This study reviews research articles published between 2011 and 2023 from popular electronic databases. In total, 226 journal and conference publications were included in this review. The in-depth analysis of these papers helps researchers understand the challenges, widely used datasets, evaluation metrics, approaches, and methods. This paper identifies and discusses potential opportunities and directions, along with a generic conceptual framework and guidelines on abstractive summarization models and techniques for research in abstractive text summarization.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142449294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Systematic Mapping Study on Quantum and Quantum-inspired Algorithms in Operations Research 运筹学中的量子算法和量子启发算法系统映射研究
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-18 DOI: 10.1145/3700874
Cláudio Gomes, João Paulo Fernandes, Gabriel Falcao, Soummya Kar, Sridhar Tayur
Quantum and quantum-inspired algorithms have not yet been systematically classified in the context of potential Operations Research (OR) applications. Our systematic mapping is designed for quick consultation and shows which algorithms have been significantly explored in the context of OR, as well as which algorithms have been vaguely addressed in the same context. The study provides rapid access to OR professionals, both practitioners and researchers, who are interested in applying and/or further developing these algorithms in their respective contexts. We prepared a replicable protocol as a backbone of this systematic mapping study, specifying research questions, establishing effective search and selection methods, defining quality metrics for assessment, and guiding the analysis of the selected studies. A total of more than 2 000 studies were found, of which 149 were analyzed in detail. Readers can have an interactive hands-on experience with the collected data on an open-source repository with a website. An international standard was used as part of our classification, enabling professionals and researchers from across the world to readily identify which algorithms have been applied in any industry sector. Our effort also culminated in a rich set of takeaways that can help the reader identify potential paths for future work.
量子和量子启发算法在运筹学(OR)的潜在应用中尚未得到系统分类。我们的系统图谱是为快速咨询而设计的,它显示了哪些算法在运筹学背景下得到了大量探索,以及哪些算法在运筹学背景下得到了模糊处理。这项研究为有兴趣在各自领域应用和/或进一步开发这些算法的手术室专业人员(包括从业人员和研究人员)提供了快速通道。我们编写了一份可复制的协议,作为这项系统图谱研究的基础,明确了研究问题,建立了有效的搜索和选择方法,定义了评估质量指标,并指导了对所选研究的分析。共找到 2000 多项研究,对其中 149 项进行了详细分析。读者可以通过网站上的开放源码资源库对收集到的数据进行交互式实践体验。我们在分类过程中采用了国际标准,使世界各地的专业人士和研究人员能够轻松识别哪些算法已应用于任何行业领域。我们的努力还产生了一系列丰富的启示,可以帮助读者确定未来工作的潜在路径。
{"title":"A Systematic Mapping Study on Quantum and Quantum-inspired Algorithms in Operations Research","authors":"Cláudio Gomes, João Paulo Fernandes, Gabriel Falcao, Soummya Kar, Sridhar Tayur","doi":"10.1145/3700874","DOIUrl":"https://doi.org/10.1145/3700874","url":null,"abstract":"Quantum and quantum-inspired algorithms have not yet been systematically classified in the context of potential Operations Research (OR) applications. Our systematic mapping is designed for quick consultation and shows which algorithms have been significantly explored in the context of OR, as well as which algorithms have been vaguely addressed in the same context. The study provides rapid access to OR professionals, both practitioners and researchers, who are interested in applying and/or further developing these algorithms in their respective contexts. We prepared a replicable protocol as a backbone of this systematic mapping study, specifying research questions, establishing effective search and selection methods, defining quality metrics for assessment, and guiding the analysis of the selected studies. A total of more than 2 000 studies were found, of which 149 were analyzed in detail. Readers can have an interactive hands-on experience with the collected data on an open-source repository with a website. An international standard was used as part of our classification, enabling professionals and researchers from across the world to readily identify which algorithms have been applied in any industry sector. Our effort also culminated in a rich set of takeaways that can help the reader identify potential paths for future work.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142449253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Security and Reliability of Internet of Underwater Things: Architecture, Challenges, and Opportunities 水下物联网的安全性和可靠性:架构、挑战和机遇
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-17 DOI: 10.1145/3700640
Bin Jiang, Jiacheng Feng, Xuerong Cui, Jian Wang, Yongxin Liu, Houbing Song
The Internet of Underwater Things (IoUT) pertains to a system that utilizes technology of Internet of Things (IoT) for data collection, communication, and control in the underwater environment. The monitoring and management of various parameters in the underwater domain are gathered through the deployment of underwater sensors, communication devices, and controllers. It is crucial in emerging ocean engineering. However, due to the instability of the underwater environment and the particularity of the underwater communication transmission medium, it is vulnerable to security threats, which may damage the system or cause data errors. In this survey, we will discuss the challenges, solutions and future directions of IoUT from security and reliability respectively. In order to ensure the normal operation of IoUT, we analyze the underwater security problems and solutions of the IoUT. Then, we discuss the reliability issue and improved strategies of IoUT system in detail. Finally, we come up with our views about the theories, challenges and future prospects of IoUT security after the comparative analysis.
水下物联网(IoUT)是指在水下环境中利用物联网(IoT)技术进行数据收集、通信和控制的系统。通过部署水下传感器、通信设备和控制器,对水下领域的各种参数进行监测和管理。这对新兴的海洋工程至关重要。然而,由于水下环境的不稳定性和水下通信传输介质的特殊性,它很容易受到安全威胁,从而破坏系统或导致数据错误。本研究将分别从安全性和可靠性两方面探讨 IoUT 所面临的挑战、解决方案和未来发展方向。为了确保 IoUT 的正常运行,我们分析了 IoUT 的水下安全问题和解决方案。然后,我们详细讨论了 IoUT 系统的可靠性问题和改进策略。最后,通过对比分析,我们对物联网UT 安全性的理论、挑战和未来前景提出了自己的看法。
{"title":"Security and Reliability of Internet of Underwater Things: Architecture, Challenges, and Opportunities","authors":"Bin Jiang, Jiacheng Feng, Xuerong Cui, Jian Wang, Yongxin Liu, Houbing Song","doi":"10.1145/3700640","DOIUrl":"https://doi.org/10.1145/3700640","url":null,"abstract":"The Internet of Underwater Things (IoUT) pertains to a system that utilizes technology of Internet of Things (IoT) for data collection, communication, and control in the underwater environment. The monitoring and management of various parameters in the underwater domain are gathered through the deployment of underwater sensors, communication devices, and controllers. It is crucial in emerging ocean engineering. However, due to the instability of the underwater environment and the particularity of the underwater communication transmission medium, it is vulnerable to security threats, which may damage the system or cause data errors. In this survey, we will discuss the challenges, solutions and future directions of IoUT from security and reliability respectively. In order to ensure the normal operation of IoUT, we analyze the underwater security problems and solutions of the IoUT. Then, we discuss the reliability issue and improved strategies of IoUT system in detail. Finally, we come up with our views about the theories, challenges and future prospects of IoUT security after the comparative analysis.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142448773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Cold Start Latency in Serverless Computing: A Systematic Review, Taxonomy, and Future Directions 无服务器计算中的冷启动延迟:系统回顾、分类和未来方向
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-17 DOI: 10.1145/3700875
Muhammed GOLEC, GUNEET KAUR WALIA, MOHIT KUMAR, FELIX CUADRADO, Sukhpal Singh Gill, STEVE UHLIG
Recently, academics and the corporate sector have paid attention to serverless computing, which enables dynamic scalability and an economic model. In serverless computing, users only pay for the time they actually use resources, enabling zero scaling to optimise cost and resource utilisation. However, this approach also introduces the serverless cold start problem. Researchers have developed various solutions to address the cold start problem, yet it remains an unresolved research area. In this article, we propose a systematic literature review on clod start latency in serverless computing. Furthermore, we create a detailed taxonomy of approaches to cold start latency, which we use to investigate existing techniques for reducing the cold start time and frequency. We have classified the current studies on cold start latency into several categories such as caching and application-level optimisation-based solutions, as well as Artificial Intelligence (AI)/Machine Learning (ML)-based solutions. Moreover, we have analyzed the impact of cold start latency on quality of service, explored current cold start latency mitigation methods, datasets, and implementation platforms, and classified them into categories based on their common characteristics and features. Finally, we outline the open challenges and highlight the possible future directions.
最近,学术界和企业界都开始关注无服务器计算,因为它可以实现动态可扩展性和经济模式。在无服务器计算中,用户只需为实际使用资源的时间付费,从而实现零扩展,优化成本和资源利用率。然而,这种方法也带来了无服务器冷启动问题。研究人员已经开发了各种解决方案来解决冷启动问题,但它仍然是一个尚未解决的研究领域。在本文中,我们对无服务器计算中的冷启动延迟进行了系统的文献综述。此外,我们还为解决冷启动延迟问题的方法创建了一个详细的分类法,并以此来研究现有的减少冷启动时间和频率的技术。我们将当前有关冷启动延迟的研究分为几类,如基于缓存和应用级优化的解决方案,以及基于人工智能(AI)/机器学习(ML)的解决方案。此外,我们还分析了冷启动延迟对服务质量的影响,探索了当前的冷启动延迟缓解方法、数据集和实施平台,并根据它们的共同特点和特征将其分类。最后,我们概述了有待解决的挑战,并强调了未来可能的发展方向。
{"title":"Cold Start Latency in Serverless Computing: A Systematic Review, Taxonomy, and Future Directions","authors":"Muhammed GOLEC, GUNEET KAUR WALIA, MOHIT KUMAR, FELIX CUADRADO, Sukhpal Singh Gill, STEVE UHLIG","doi":"10.1145/3700875","DOIUrl":"https://doi.org/10.1145/3700875","url":null,"abstract":"Recently, academics and the corporate sector have paid attention to serverless computing, which enables dynamic scalability and an economic model. In serverless computing, users only pay for the time they actually use resources, enabling zero scaling to optimise cost and resource utilisation. However, this approach also introduces the serverless cold start problem. Researchers have developed various solutions to address the cold start problem, yet it remains an unresolved research area. In this article, we propose a systematic literature review on clod start latency in serverless computing. Furthermore, we create a detailed taxonomy of approaches to cold start latency, which we use to investigate existing techniques for reducing the cold start time and frequency. We have classified the current studies on cold start latency into several categories such as caching and application-level optimisation-based solutions, as well as Artificial Intelligence (AI)/Machine Learning (ML)-based solutions. Moreover, we have analyzed the impact of cold start latency on quality of service, explored current cold start latency mitigation methods, datasets, and implementation platforms, and classified them into categories based on their common characteristics and features. Finally, we outline the open challenges and highlight the possible future directions.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142448775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Survey on Advanced Persistent Threat Detection: A Unified Framework, Challenges, and Countermeasures 高级持续性威胁检测调查:统一框架、挑战与对策
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-16 DOI: 10.1145/3700749
Bo Zhang, Yansong Gao, Boyu Kuang, Changlong Yu, Anmin Fu, Willy Susilo
In recent years, frequent Advanced Persistent Threat (APT) attacks have caused disastrous damage to critical facilities, leading to severe information leakages, economic losses, and even social disruptions. Via sophisticated, long-term, and stealthy network intrusions, APT attacks are often beyond the capabilities of traditional intrusion detection methods. Existing methods employ various techniques to enhance APT detection at different stages, but this makes it difficult to fairly and objectively evaluate the capability, value, and orthogonality of available techniques. Overly focusing on hardening specific APT detection stages cannot address some essential challenges from a global perspective, which would result in severe consequences. To holistically tackle this problem and explore effective solutions, we abstract a unified framework that covers the complete process of APT attack detection, with standardized summaries of state-of-the-art solutions and analysis of feasible techniques. Further, we provide an in-depth discussion of the challenges and countermeasures faced by each component of the detection framework. In addition, we comparatively analyze public datasets and outline the capability criteria to provide a reference for standardized evaluations. Finally, we discuss insights into potential areas for future research.
近年来,频繁发生的高级持续性威胁(APT)攻击对关键设施造成了灾难性破坏,导致严重的信息泄露、经济损失甚至社会混乱。通过复杂、长期和隐蔽的网络入侵,APT 攻击往往超出了传统入侵检测方法的能力范围。现有方法在不同阶段采用各种技术来加强 APT 检测,但这很难公正客观地评估现有技术的能力、价值和正交性。过度关注特定 APT 检测阶段的加固,无法从全局角度应对一些基本挑战,这将导致严重后果。为了从整体上解决这一问题并探索有效的解决方案,我们抽象出了一个统一的框架,涵盖了 APT 攻击检测的整个过程,并对最先进的解决方案进行了标准化总结,对可行的技术进行了分析。此外,我们还深入讨论了检测框架各组成部分所面临的挑战和对策。此外,我们还对公共数据集进行了比较分析,并概述了能力标准,为标准化评估提供参考。最后,我们讨论了对未来研究潜在领域的见解。
{"title":"A Survey on Advanced Persistent Threat Detection: A Unified Framework, Challenges, and Countermeasures","authors":"Bo Zhang, Yansong Gao, Boyu Kuang, Changlong Yu, Anmin Fu, Willy Susilo","doi":"10.1145/3700749","DOIUrl":"https://doi.org/10.1145/3700749","url":null,"abstract":"In recent years, frequent Advanced Persistent Threat (APT) attacks have caused disastrous damage to critical facilities, leading to severe information leakages, economic losses, and even social disruptions. Via sophisticated, long-term, and stealthy network intrusions, APT attacks are often beyond the capabilities of traditional intrusion detection methods. Existing methods employ various techniques to enhance APT detection at different stages, but this makes it difficult to fairly and objectively evaluate the capability, value, and orthogonality of available techniques. Overly focusing on hardening specific APT detection stages cannot address some essential challenges from a global perspective, which would result in severe consequences. To holistically tackle this problem and explore effective solutions, we abstract a unified framework that covers the complete process of APT attack detection, with standardized summaries of state-of-the-art solutions and analysis of feasible techniques. Further, we provide an in-depth discussion of the challenges and countermeasures faced by each component of the detection framework. In addition, we comparatively analyze public datasets and outline the capability criteria to provide a reference for standardized evaluations. Finally, we discuss insights into potential areas for future research.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142444402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions 深度聚类综合调查:分类、挑战和未来方向
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-16 DOI: 10.1145/3689036
Sheng Zhou, Hongjia Xu, Zhuonan Zheng, Jiawei Chen, Zhao Li, Jiajun Bu, Jia Wu, Xin Wang, Wenwu Zhu, Martin Ester
Clustering is a fundamental machine learning task which aims at assigning instances into groups so that similar samples belong to the same cluster while dissimilar samples belong to different clusters. Shallow clustering methods usually assume that data are collected and expressed as feature vectors within which clustering is performed. However, clustering high-dimensional data, such as images, texts, videos, and graphs, poses significant challenges for clustering tasks, such as indiscriminate representation and intricate relationships among instances. Over the past decades, deep learning has achieved remarkable success in effective representation learning and modeling complex relationships. Motivated by these advancements, Deep Clustering seeks to improve clustering outcomes through deep learning techniques, garnering considerable interest from both academia and industry. Despite many contributions to this vibrant area of research, the lack of systematic analysis and a comprehensive taxonomy has hindered progress in this field. In this survey, we first explore how deep learning can be integrated into deep clustering and identify two fundamental components: the representation learning module and the clustering module. Then we summarize and analyze the representative design of these two modules. Furthermore, we introduce a novel taxonomy of deep clustering based on how these two modules interact, specifically through multistage, generative, iterative, and simultaneous approaches. In addition, we present well-known benchmark datasets, evaluation metrics, and open-source tools to clearly demonstrate different experimental approaches. Finally, we examine the practical applications of deep clustering and propose challenging areas for future research.
聚类是一项基本的机器学习任务,其目的是将实例分配到不同的组中,使相似的样本属于同一个组,而不相似的样本属于不同的组。浅层聚类方法通常假定数据已收集并表示为特征向量,并在特征向量内进行聚类。然而,图像、文本、视频和图形等高维数据的聚类对聚类任务提出了巨大挑战,例如无差别表示和实例之间错综复杂的关系。过去几十年来,深度学习在有效表示学习和复杂关系建模方面取得了显著成就。在这些进步的推动下,深度聚类试图通过深度学习技术改善聚类结果,这引起了学术界和工业界的极大兴趣。尽管对这一充满活力的研究领域做出了很多贡献,但缺乏系统分析和全面的分类方法阻碍了这一领域的进展。在本调查中,我们首先探讨了如何将深度学习集成到深度聚类中,并确定了两个基本组成部分:表征学习模块和聚类模块。然后,我们总结并分析了这两个模块的代表性设计。此外,我们还根据这两个模块的交互方式,特别是通过多级、生成、迭代和同步方法,介绍了一种新颖的深度聚类分类法。此外,我们还介绍了著名的基准数据集、评估指标和开源工具,以清楚地展示不同的实验方法。最后,我们探讨了深度聚类的实际应用,并提出了未来研究的挑战领域。
{"title":"A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions","authors":"Sheng Zhou, Hongjia Xu, Zhuonan Zheng, Jiawei Chen, Zhao Li, Jiajun Bu, Jia Wu, Xin Wang, Wenwu Zhu, Martin Ester","doi":"10.1145/3689036","DOIUrl":"https://doi.org/10.1145/3689036","url":null,"abstract":"Clustering is a fundamental machine learning task which aims at assigning instances into groups so that similar samples belong to the same cluster while dissimilar samples belong to different clusters. Shallow clustering methods usually assume that data are collected and expressed as feature vectors within which clustering is performed. However, clustering high-dimensional data, such as images, texts, videos, and graphs, poses significant challenges for clustering tasks, such as indiscriminate representation and intricate relationships among instances. Over the past decades, deep learning has achieved remarkable success in effective representation learning and modeling complex relationships. Motivated by these advancements, Deep Clustering seeks to improve clustering outcomes through deep learning techniques, garnering considerable interest from both academia and industry. Despite many contributions to this vibrant area of research, the lack of systematic analysis and a comprehensive taxonomy has hindered progress in this field. In this survey, we first explore how deep learning can be integrated into deep clustering and identify two fundamental components: the representation learning module and the clustering module. Then we summarize and analyze the representative design of these two modules. Furthermore, we introduce a novel taxonomy of deep clustering based on how these two modules interact, specifically through multistage, generative, iterative, and simultaneous approaches. In addition, we present well-known benchmark datasets, evaluation metrics, and open-source tools to clearly demonstrate different experimental approaches. Finally, we examine the practical applications of deep clustering and propose challenging areas for future research.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142444403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Green IN Artificial Intelligence from a Software perspective: State-of-the-Art and Green Decalogue 从软件角度看绿色 IN 人工智能:最新技术与绿色十诫
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-15 DOI: 10.1145/3698111
María Gutiérrez, Mª Angeles Moraga, Félix Garcia, Coral Calero
This work presents a structured view of the state-of-the-art research on Artificial Intelligence (AI), from the point of view of efficiency and reduction of the energy consumption of AI Software. We analysed the current research on energy consumption of AI algorithms and its improvements, which gave us a starting literature corpus of 2688 papers that we identified as Green AI with a software perspective. We structure this corpus into Green IN AI and Green BY AI, which led us to discover that only 36 of them could be considered Green IN AI. After some quick insights about Green BY AI, we then introduce our main contribution: a systematic mapping of Green IN AI. We provide an in-depth analysis of the AI models that observed during the mapping, and what solutions have been proposed for improving their energy efficiency. We also analyse the energy evaluation methodologies employed in Green IN AI, discovering that most papers opt for a software-based energy estimation approach and a 27% of all papers not documenting their methodology. We finish by synthetising our insights from the mapping into a Decalogue of Good Practices for Green AI.
本作品从人工智能软件的能效和降低能耗的角度,对人工智能(AI)的最新研究成果进行了结构化的分析。我们分析了当前有关人工智能算法能耗及其改进的研究,由此建立了一个包含 2688 篇论文的文献语料库,并将其确定为从软件角度出发的绿色人工智能。我们将该语料库分为 "绿色人工智能"(Green IN AI)和 "绿色人工智能"(Green BY AI),结果发现其中只有 36 篇可被视为 "绿色人工智能"(Green IN AI)。在对 "Green BY AI "进行了一些简单了解之后,我们介绍了我们的主要贡献:对 "Green IN AI "进行系统映射。我们深入分析了映射过程中观察到的人工智能模型,以及为提高其能效而提出的解决方案。我们还分析了 "绿色 IN "人工智能中采用的能源评估方法,发现大多数论文选择了基于软件的能源估算方法,27%的论文没有记录其方法。最后,我们将从图谱中获得的见解综合为《绿色人工智能良好实践十诫》(Decalogue of Good Practices for Green AI)。
{"title":"Green IN Artificial Intelligence from a Software perspective: State-of-the-Art and Green Decalogue","authors":"María Gutiérrez, Mª Angeles Moraga, Félix Garcia, Coral Calero","doi":"10.1145/3698111","DOIUrl":"https://doi.org/10.1145/3698111","url":null,"abstract":"This work presents a structured view of the state-of-the-art research on Artificial Intelligence (AI), from the point of view of efficiency and reduction of the energy consumption of AI Software. We analysed the current research on energy consumption of AI algorithms and its improvements, which gave us a starting literature corpus of 2688 papers that we identified as Green AI with a software perspective. We structure this corpus into Green IN AI and Green BY AI, which led us to discover that only 36 of them could be considered Green IN AI. After some quick insights about Green BY AI, we then introduce our main contribution: a systematic mapping of Green IN AI. We provide an in-depth analysis of the AI models that observed during the mapping, and what solutions have been proposed for improving their energy efficiency. We also analyse the energy evaluation methodologies employed in Green IN AI, discovering that most papers opt for a software-based energy estimation approach and a 27% of all papers not documenting their methodology. We finish by synthetising our insights from the mapping into a Decalogue of Good Practices for Green AI.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Learning-based Artificial Intelligence Artwork: Methodology Taxonomy and Quality Evaluation 基于学习的人工智能作品:方法分类和质量评估
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-15 DOI: 10.1145/3698105
Qian Wang, Hong-NingH Dai, Jinghua Yang, Cai Guo, Peter Childs, Maaike Kleinsmann, Yike Guo, Pan Wang
With the development of the theory and technology of computer science, machine or computer painting is increasingly being explored in the creation of art. Machine-made works are referred to as artificial intelligence (AI) artworks. Early methods of AI artwork generation have been classified as non-photorealistic rendering (NPR) and, latterly, neural-style transfer methods have also been investigated. As technology advances, the variety of machine-generated artworks and the methods used to create them have proliferated. However, there is no unified and comprehensive system to classify and evaluate these works. To date, no work has generalised methods of creating AI artwork including learning-based methods for painting or drawing. Moreover, the taxonomy, evaluation and development of AI artwork methods face many challenges. This paper is motivated by these considerations. We first investigate current learning-based methods for making AI artworks and classify the methods according to art styles. Furthermore, we propose a consistent evaluation system for AI artworks and conduct a user study to evaluate the proposed system on different AI artworks. This evaluation system uses six criteria: beauty, color, texture, content detail, line and style. The user study demonstrates that the six-dimensional evaluation index is effective for different types of AI artworks.
随着计算机科学理论和技术的发展,机器绘画或计算机绘画在艺术创作中的探索日益增多。机器制作的作品被称为人工智能(AI)艺术品。早期的人工智能艺术品生成方法被归类为非逼真渲染(NPR),后来也研究了神经式传输方法。随着技术的进步,机器生成艺术品的种类和创作方法也在激增。然而,目前还没有一个统一而全面的系统来对这些作品进行分类和评估。迄今为止,还没有任何作品将人工智能艺术作品的创作方法(包括基于学习的绘画或素描方法)普遍化。此外,人工智能艺术作品的分类、评估和开发方法也面临诸多挑战。本文正是基于这些考虑而撰写的。我们首先调查了当前基于学习的人工智能艺术作品制作方法,并根据艺术风格对这些方法进行了分类。此外,我们还为人工智能艺术作品提出了一个一致的评估系统,并开展了一项用户研究,在不同的人工智能艺术作品上对所提出的系统进行评估。该评估系统采用六项标准:美感、色彩、质感、内容细节、线条和风格。用户研究表明,六维评价指标对不同类型的人工智能艺术作品都很有效。
{"title":"Learning-based Artificial Intelligence Artwork: Methodology Taxonomy and Quality Evaluation","authors":"Qian Wang, Hong-NingH Dai, Jinghua Yang, Cai Guo, Peter Childs, Maaike Kleinsmann, Yike Guo, Pan Wang","doi":"10.1145/3698105","DOIUrl":"https://doi.org/10.1145/3698105","url":null,"abstract":"With the development of the theory and technology of computer science, machine or computer painting is increasingly being explored in the creation of art. Machine-made works are referred to as artificial intelligence (AI) artworks. Early methods of AI artwork generation have been classified as non-photorealistic rendering (NPR) and, latterly, neural-style transfer methods have also been investigated. As technology advances, the variety of machine-generated artworks and the methods used to create them have proliferated. However, there is no unified and comprehensive system to classify and evaluate these works. To date, no work has generalised methods of creating AI artwork including learning-based methods for painting or drawing. Moreover, the taxonomy, evaluation and development of AI artwork methods face many challenges. This paper is motivated by these considerations. We first investigate current learning-based methods for making AI artworks and classify the methods according to art styles. Furthermore, we propose a consistent evaluation system for AI artworks and conduct a user study to evaluate the proposed system on different AI artworks. This evaluation system uses six criteria: beauty, color, texture, content detail, line and style. The user study demonstrates that the six-dimensional evaluation index is effective for different types of AI artworks.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities 多模态错误信息检测:方法、挑战和机遇
IF 16.6 1区 计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS Pub Date : 2024-10-15 DOI: 10.1145/3697349
Sara Abdali, Sina Shaham, Bhaskar Krishnamachari
As social media platforms evolve from text-based forums into multi-modal environments, the nature of misinformation in social media is also transforming accordingly. Taking advantage of the fact that visual modalities such as images and videos are more favorable and attractive to users, and textual content is sometimes skimmed carelessly, misinformation spreaders have recently targeted contextual connections between the modalities, e.g., text and image. Hence, many researchers have developed automatic techniques for detecting possible cross-modal discordance in web-based content. We analyze, categorize, and identify existing approaches in addition to the challenges and shortcomings they face in order to unearth new research opportunities in the field of multi-modal misinformation detection.
随着社交媒体平台从基于文本的论坛演变为多模式环境,社交媒体中的虚假信息的性质也在发生相应的变化。图像和视频等视觉模式对用户更有利、更有吸引力,而文字内容有时会被粗心地略过,利用这一事实,误导信息传播者最近开始瞄准模式之间的上下文联系,如文字和图像。因此,许多研究人员开发了自动技术来检测网络内容中可能存在的跨模态不一致。我们对现有方法及其面临的挑战和不足进行了分析、分类和识别,以便在多模态错误信息检测领域发掘新的研究机会。
{"title":"Multi-modal Misinformation Detection: Approaches, Challenges and Opportunities","authors":"Sara Abdali, Sina Shaham, Bhaskar Krishnamachari","doi":"10.1145/3697349","DOIUrl":"https://doi.org/10.1145/3697349","url":null,"abstract":"As social media platforms evolve from text-based forums into multi-modal environments, the nature of misinformation in social media is also transforming accordingly. Taking advantage of the fact that visual modalities such as images and videos are more favorable and attractive to users, and textual content is sometimes skimmed carelessly, misinformation spreaders have recently targeted contextual connections between the modalities, e.g., text and image. Hence, many researchers have developed automatic techniques for detecting possible cross-modal discordance in web-based content. We analyze, categorize, and identify existing approaches in addition to the challenges and shortcomings they face in order to unearth new research opportunities in the field of multi-modal misinformation detection.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":null,"pages":null},"PeriodicalIF":16.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142440699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
ACM Computing Surveys
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1