WIREs Data Mining and Knowledge Discovery最新文献_第5页

A Survey on GNN-Based Link Prediction: Techniques, Applications, and Challenges 基于gnn的链路预测研究：技术、应用与挑战

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-05-03 DOI: 10.1002/widm.70093

Chengcheng Sun, Yajie Song, Cheng Zhai, Jiayun Tian, Jia Yang, Xiaobin Rui, Jian Zhang, Zhixiao Wang, Philip S. Yu

{"title":"A Survey on GNN-Based Link Prediction: Techniques, Applications, and Challenges","authors":"Chengcheng Sun, Yajie Song, Cheng Zhai, Jiayun Tian, Jia Yang, Xiaobin Rui, Jian Zhang, Zhixiao Wang, Philip S. Yu","doi":"10.1002/widm.70093","DOIUrl":"https://doi.org/10.1002/widm.70093","url":null,"abstract":"Graph neural networks (GNNs) have emerged as the leading paradigm for link prediction, enabling the inference of missing connections and the anticipation of potential future links. However, existing reviews lack systematic exploration specifically targeting underlying GNN architectures and diverse graph structures. To address this critical gap, this paper provides a comprehensive review of GNN-based link prediction from a novel and dedicated GNN perspective. We propose an innovative taxonomy that categorizes recent advancements based on techniques and applications. From a technique perspective, we focus on key GNN encoder architectures, including graph convolutional networks (GCN)-based, graph autoencoders (GAE)-based, graph attention networks (GAT)-based, and GFormer-based methods, discussing their strengths and limitations. From an application perspective, we highlight prominent use cases of link prediction in knowledge graphs and recommendation systems, demonstrating their real-world impact. In addition, we examine the current challenges and discuss promising future directions.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"175 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148290375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Skeleton-Based Hand Gesture Recognition: Backgrounds, Datasets, Methods, Applications, Future Trends, and Challenges 基于骨骼的手势识别：背景，数据集，方法，应用，未来趋势和挑战

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-30 DOI: 10.1002/widm.70092

Junhui Li, Linfang Wang, Sike Ni, Mohammed A. A. Al-qaness

{"title":"Skeleton-Based Hand Gesture Recognition: Backgrounds, Datasets, Methods, Applications, Future Trends, and Challenges","authors":"Junhui Li, Linfang Wang, Sike Ni, Mohammed A. A. Al-qaness","doi":"10.1002/widm.70092","DOIUrl":"https://doi.org/10.1002/widm.70092","url":null,"abstract":"Skeleton-based hand gesture recognition (SGR) has emerged as a prominent research area in computer vision (CV) due to the unique advantages of skeletal data. Although gesture recognition (GR) has traditionally relied on video streams and RGB image data, skeleton-based approaches remain underexplored. Despite advances in deep learning techniques, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), graph convolutional networks (GCNs), attention mechanisms, and multimodal fusion, a systematic and comprehensive review of these methods within the context of SGR is lacking. This paper addresses this gap by first underscoring the significance of GR and the pivotal role of skeletal data in its analysis. We then present the data acquisition techniques for SGR and examine its key applications, such as human-robot interaction (HRI), sign language recognition, gaming and entertainment, and healthcare and rehabilitation. Furthermore, we analyze state-of-the-art methodologies and compare their strengths and limitations in detail. Based on a thorough evaluation of existing research, we identify current challenges and unresolved bottlenecks. Finally, we propose future research directions to advance SGR, focusing on model robustness, multimodal fusion, and dataset expansion.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148290484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Recommender Systems: Taxonomy, Applications and Current Research Trends 推荐系统：分类、应用和当前研究趋势

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-29 DOI: 10.1002/widm.70095

Daniel Ranchal-Parrado, Carlos Porcel, Jesús Alcalá-Fdez

{"title":"Recommender Systems: Taxonomy, Applications and Current Research Trends","authors":"Daniel Ranchal-Parrado, Carlos Porcel, Jesús Alcalá-Fdez","doi":"10.1002/widm.70095","DOIUrl":"https://doi.org/10.1002/widm.70095","url":null,"abstract":"Recommender Systems play an essential role in assisting users to navigate the immense amount of information and services available online, aiding them in the decision-making process and adding a lot to the overall user experience. However, the rapid advancement and widespread adoption of technology have ushered in a framework in which enormous amounts of data (complex and heterogeneous) are available from different information sources (such as Internet of Things or social networks). This vast amount of information has led to develop advanced techniques in recent years that offer great opportunities and challenges for business, education, health, and other domains, making more accurate and personalized recommendations, providing explanations that capture the multifaceted information underlying recommendations and clarify their generation, and allowing the performance of the systems to be adequately assessed. This work provides an overview of theoretical research and practical developments in recommender systems, based on the Web of Science and following the guidelines for systematic literature reviews in software engineering. It aims to present a well-defined framework that allows students and researchers without a strong background in the field to easily identify current issues and develop new and significant advances. To this end, a comprehensive and practical taxonomy is first proposed based on two criteria, the recommending approach and the target users. This is followed by a report of recent practical developments, free/open source recommender systems software, and a snapshot of the status of publications, in order to unravel current research trends. And finally, some potential and significant future research directions are presented to assist interested researchers make significant advances in the area.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148290374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward Automated Deep Learning: Advances and Challenges in Neural Architecture Search 迈向自动化深度学习：神经架构搜索的进展与挑战

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-29 DOI: 10.1002/widm.70091

Jingxia Ren, Liang Wan, Lan Xiong

引用次数: 0

Large Language Models for Explainable Medical Text Summarization: A Systematic Literature Review 可解释医学文本摘要的大型语言模型：系统文献综述

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-28 DOI: 10.1002/widm.70089

Aleka Melese Ayalew, Md Rabiul Hasan, Tapio Seppänen, Mourad Oussalah

{"title":"Large Language Models for Explainable Medical Text Summarization: A Systematic Literature Review","authors":"Aleka Melese Ayalew, Md Rabiul Hasan, Tapio Seppänen, Mourad Oussalah","doi":"10.1002/widm.70089","DOIUrl":"https://doi.org/10.1002/widm.70089","url":null,"abstract":"Recently, large language models have gained momentum in several areas, including medical text summarization and clinical decision support in healthcare. In this systematic review, we focus on how LLMs are used for summarization and explainability, and on how they improve the precision of clinical decisions. Initially, by screening eight distinct databases, we identified 1601 studies using the PRISMA protocol. Following strict qualifying criteria, 61 studies were selected for the final review. Our results show that decoder-only architectures dominate the field (60.7% of studies), with zero-shot prompting emerging as the predominant approach (55.7%), while 24.6% of studies employed fine-tuning. General clinical decision support (26.2%) and diagnostic assistance (19.7%) constitute the two most widely used clinical applications across multiple clinical specialties. Identified in 26.2% of studies, the intersection of summarization and explainability becomes a key focus area, with fine-tuned models obtaining 38.6% higher average ROUGE-1 scores compared to zero-shot approaches, and studies including robust explainability features report 27.3% higher clinician acceptance rates. Despite great potential, major obstacles still exist, including model hallucinations (63.9% of studies), minimal workflow integration (only 14.8% of studies), and inadequate attention to regulatory paths (8.2%). Although LLMs offer significant potential for transforming clinical decision support via improved information handling and clear reasoning, realizing these goals requires overcoming essential challenges in clinical validation, system integration, and ethical oversight. This review aims to provide an extensive framework for understanding the current capabilities, limitations, and prospects of LLM-based explainable summarization in clinical settings, guiding future research and practical deployment.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Knowledge Graphs and Critical Infrastructures: Friends or Foes? 知识图谱与关键基础设施：是敌是友？

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-27 DOI: 10.1002/widm.70090

José Miguel Blanco, Felix Cuadrado, Jose M. del Alamo, Juan C. Dueñas

{"title":"Knowledge Graphs and Critical Infrastructures: Friends or Foes?","authors":"José Miguel Blanco, Felix Cuadrado, Jose M. del Alamo, Juan C. Dueñas","doi":"10.1002/widm.70090","DOIUrl":"https://doi.org/10.1002/widm.70090","url":null,"abstract":"Knowledge Graphs (KGs) are a natural evolution of data models representing and connecting data in a network of nodes and relations. Their application has already shown multiple benefits due to them being a flexible technology. They have a higher predisposition for interconnectedness, adaptation for data growth, and improved reasoning among other benefits. Critical Infrastructures provide goods and services considered essential to support modern societies. Their r esilience, security, and continuous operation have become a stable concern of multiple international organisms. Given this, there is an overlap in the application of KGs to the domain of Critical Infrastructures. The former can be leveraged for gaining greater visibility, enhanced operational intelligence, and more proactive approaches to maintenance, security, and optimization, thus ensuring reliability of such important systems. Nonetheless, the current landscape on what role KGs play within the domain is unclear. With this in mind, we perform a systematic search for KGs that focus on Critical Infrastructures, as defined by the European Union. This way, we analyze how KGs are applied to different critical infrastructure domains. Additionally, an in-depth discussion of the results is provided to understand how KGs are intertwined with Critical Infrastructures data, processes, and architecture. We conclude the paper with potential recommendations to improve their resilience through further KG integration.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148290408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Combating Digital Deception: A Taxonomical and Systematic Review of Deepfake Detection Approaches 打击数字欺骗：深度伪造检测方法的分类和系统综述

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-24 DOI: 10.1002/widm.70087

Pratishtha Gupta, Bhawna Narwal, Amar Kumar Mohapatra

{"title":"Combating Digital Deception: A Taxonomical and Systematic Review of Deepfake Detection Approaches","authors":"Pratishtha Gupta, Bhawna Narwal, Amar Kumar Mohapatra","doi":"10.1002/widm.70087","DOIUrl":"https://doi.org/10.1002/widm.70087","url":null,"abstract":"The contemporary world is fuelled by the social web, with approximately 504.17 h of video content and 1,050,000 photos going up online every minute. This open‐access media is swiftly exploited to facilitate deepfake generation that can disseminate misleading information and tarnish reputations. Furthermore, the subtlety of deepfakes has escalated to the point where deep learning‐based techniques yield deepfakes that are perceptibly flawless and indistinguishable from reality. Moreover, the existing detection models suffer severe affliction when in the crosshairs of adversarial attacks. Therefore, it is paramount to promote the development of resilient evasion strategies against this societal bane, which “takes the bull by the horns” while shielding them from hostile adversaries. In this direction, the presented article outlines the neoteric progression in deepfake topography, assimilating generation, detection, and adversarial attack‐based techniques. It delineates an all‐inclusive taxonomy based on topical research stemming from the deepfake landscape. Based on the taxonomical classification, a systematic and exhaustive review of the avant‐garde deepfake detection techniques is conducted. Furthermore, this article reviews state‐of‐the‐art active defense techniques against audio/video deepfakes, incorporating both generator‐ and detector‐based adversarial attacks, and discusses issues with deepfake datasets. Lastly, the trends in deepfake detection and dataset utilization have been highlighted, bringing to the fore the all‐important spheres requiring futuristic investigation. This article is categorized under: Technologies > Artificial Intelligence Technologies > Machine Learning Commercial, Legal, and Ethical Issues > Security and Privacy ","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"149 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147739447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Review of Feature Selection Methods and Their Ensembles 特征选择方法及其集成综述

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-24 DOI: 10.1002/widm.70085

Reem Salman, Ayman Alzaatreh, Hana Sulieman

引用次数: 0

The Intersection of Knowledge Graphs, Large Language Models, and Mass Spectrometry Data: Progress and Applications 知识图谱、大型语言模型和质谱数据的交叉：进展与应用

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-23 DOI: 10.1002/widm.70086

Donghui Shi, Longjian Shen, Jozef Zurada

{"title":"The Intersection of Knowledge Graphs, Large Language Models, and Mass Spectrometry Data: Progress and Applications","authors":"Donghui Shi, Longjian Shen, Jozef Zurada","doi":"10.1002/widm.70086","DOIUrl":"https://doi.org/10.1002/widm.70086","url":null,"abstract":"The rapid development of knowledge graphs (KGs) and large language models (LLMs) in artificial intelligence (AI) has provided a new approach to intelligent analysis of mass spectrometry (MS) data. KGs can enhance the ability to identify metabolites, perform functional annotation, and integrate multi‐omics data through structured knowledge representation and semantic association. Meanwhile, the powerful context‐understanding capabilities of LLMs and advanced natural language processing (NLP) technologies can assist in the automated analysis and application of MS data. When combined, they overcome the limitations of traditional technologies, which is significant for researching high‐dimensional data analysis, detecting low‐abundance signals, and integrating knowledge across domains. This article reviews cross‐domain applications of KGs and LLMs in MS data analysis. We focus on the latest progress in metabolite annotation, automated report generation, and multi‐omics data integration. Furthermore, from the perspectives of quality, evolution, and reliability of KGs, we outline technical challenges currently faced, such as insufficient data standardization, lack of traceability and version control in KGs, limited model interpretability, and obstacles in cross‐modal fusion. Finally, we summarize research directions that can promote integration of KG and LLM in the future, such as how to enhance knowledge representation and how to achieve multimodal learning and dynamic knowledge updates. All of these can improve the accuracy and efficiency of data interpretation and open new research directions in metabolomics, proteomics, and broader life sciences. This article is categorized under: Algorithmic Development > Biological Data Mining Application Areas > Health Care Fundamental Concepts of Data and Knowledge > Knowledge Representation ","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nature-Inspired Optimization Techniques in Deep Learning for Cybersecurity 网络安全深度学习中的自然启发优化技术

WIREs Data Mining and Knowledge Discovery Pub Date : 2026-04-20 DOI: 10.1002/widm.70088

S. Kumar Reddy Mallidi, Ravi Kiran Varma Penmatsa, Anant Wairagade, Imtiaz N. Mohamed, D. Rosy Salomi Victoria, Krishnanjaneyulu Payala

{"title":"Nature-Inspired Optimization Techniques in Deep Learning for Cybersecurity","authors":"S. Kumar Reddy Mallidi, Ravi Kiran Varma Penmatsa, Anant Wairagade, Imtiaz N. Mohamed, D. Rosy Salomi Victoria, Krishnanjaneyulu Payala","doi":"10.1002/widm.70088","DOIUrl":"https://doi.org/10.1002/widm.70088","url":null,"abstract":"Deep learning has become foundational in modern cybersecurity solutions, particularly, in intrusion detection, malware analysis, and anomaly detection. However, its effectiveness is often constrained by the challenges of high-dimensional feature spaces and complex hyperparameter settings. In recent years, nature-inspired optimization techniques—such as genetic algorithms, particle swarm optimization, ant colony optimization, firefly algorithm, and differential evolution—have been increasingly explored to overcome these limitations. These algorithms offer global search capabilities, flexibility, and robustness, making them well-suited for optimizing deep learning systems in adversarial and dynamic cyber environments. This article presents a comprehensive review of peer-reviewed literature published between 2020 and 2024, focusing on integrating nature-inspired optimization techniques into deep learning for cybersecurity. The review is structured around two core optimization dimensions: (i) feature selection and (ii) hyperparameter tuning. For each, we critically evaluate representative methods, discuss empirical findings across multiple application domains (e.g., IoT, ICS, Android), and highlight how these algorithms address key performance bottlenecks. This review aims to guide researchers in developing robust and adaptive deep learning models for security-critical applications by synthesizing trends, identifying gaps, and outlining design principles.","PeriodicalId":501013,"journal":{"name":"WIREs Data Mining and Knowledge Discovery","volume":"54 72 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0