Big Data Management – serie

This book introduces readers to a workload-aware methodology for large-scale graph algorithm optimization in graph-computing systems, and proposes several optimization techniques that can enable these systems to handle advanced graph algorithms efficiently. More concretely, it proposes a workload-aware cost model to guide the development of high-performance algorithms. On the basis of the cost model, the book subsequently presents a system-level optimization resulting in a partition-aware graph-computing engine, PAGE. In addition, it presents three efficient and scalable advanced graph algorithms – the subgraph enumeration, cohesive subgraph detection, and graph extraction algorithms.This book offers a valuable reference guide for junior researchers, covering the latest advances in large-scale graph analysis; and for senior researchers, sharing state-of-the-art solutions based on advanced graph algorithms. In addition, all readers will find a workload-aware methodology fordesigning efficient large-scale graph algorithms.

This book introduces readers to a workload-aware methodology for large-scale graph algorithm optimization in graph-computing systems, and proposes several optimization techniques that can enable these systems to handle advanced graph algorithms efficiently. More concretely, it proposes a workload-aware cost model to guide the development of high-performance algorithms. On the basis of the cost model, the book subsequently presents a system-level optimization resulting in a partition-aware graph-computing engine, PAGE. In addition, it presents three efficient and scalable advanced graph algorithms – the subgraph enumeration, cohesive subgraph detection, and graph extraction algorithms.This book offers a valuable reference guide for junior researchers, covering the latest advances in large-scale graph analysis; and for senior researchers, sharing state-of-the-art solutions based on advanced graph algorithms. In addition, all readers will find a workload-aware methodology fordesigning efficient large-scale graph algorithms.

Graph data is powerful, thanks to its ability to model arbitrary relationship between objects and is encountered in a range of real-world applications in fields such as bioinformatics, traffic network, scientific collaboration, world wide web and social networks. Graph data mining is used to discover useful information and knowledge from graph data. The complications of nodes, links and the semi-structure form present challenges in terms of the computation tasks, e.g., node classification, link prediction, and graph classification. In this context, various advanced techniques, including graph embedding and graph neural networks, have recently been proposed to improve the performance of graph data mining. This book provides a state-of-the-art review of graph data mining methods. It addresses a current hot topic – the security of graph data mining – and proposes a series of detection methods to identify adversarial samples in graph data. In addition, it introduces readers to graph augmentation and subgraph networks to further enhance the models, i.e., improve their accuracy and robustness. Lastly, the book describes the applications of these advanced techniques in various scenarios, such as traffic networks, social and technical networks, and blockchains.

Graph data is powerful, thanks to its ability to model arbitrary relationship between objects and is encountered in a range of real-world applications in fields such as bioinformatics, traffic network, scientific collaboration, world wide web and social networks. Graph data mining is used to discover useful information and knowledge from graph data. The complications of nodes, links and the semi-structure form present challenges in terms of the computation tasks, e.g., node classification, link prediction, and graph classification. In this context, various advanced techniques, including graph embedding and graph neural networks, have recently been proposed to improve the performance of graph data mining. This book provides a state-of-the-art review of graph data mining methods. It addresses a current hot topic – the security of graph data mining – and proposes a series of detection methods to identify adversarial samples in graph data. In addition, it introduces readers to graph augmentation and subgraph networks to further enhance the models, i.e., improve their accuracy and robustness. Lastly, the book describes the applications of these advanced techniques in various scenarios, such as traffic networks, social and technical networks, and blockchains.

This book presents the state of the art in distributed machine learning algorithms that are based on gradient optimization methods. In the big data era, large-scale datasets pose enormous challenges for the existing machine learning systems. As such, implementing machine learning algorithms in a distributed environment has become a key technology, and recent research has shown gradient-based iterative optimization to be an effective solution. Focusing on methods that can speed up large-scale gradient optimization through both algorithm optimizations and careful system implementations, the book introduces three essential techniques in designing a gradient optimization algorithm to train a distributed machine learning model: parallel strategy, data compression and synchronization protocol.Written in a tutorial style, it covers a range of topics, from fundamental knowledge to a number of carefully designed algorithms and systems of distributed machine learning. It will appealto a broad audience in the field of machine learning, artificial intelligence, big data and database management.

This book presents the state of the art in distributed machine learning algorithms that are based on gradient optimization methods. In the big data era, large-scale datasets pose enormous challenges for the existing machine learning systems. As such, implementing machine learning algorithms in a distributed environment has become a key technology, and recent research has shown gradient-based iterative optimization to be an effective solution. Focusing on methods that can speed up large-scale gradient optimization through both algorithm optimizations and careful system implementations, the book introduces three essential techniques in designing a gradient optimization algorithm to train a distributed machine learning model: parallel strategy, data compression and synchronization protocol.Written in a tutorial style, it covers a range of topics, from fundamental knowledge to a number of carefully designed algorithms and systems of distributed machine learning. It will appealto a broad audience in the field of machine learning, artificial intelligence, big data and database management.

The development of information technology has made it possible to collect large amounts of spatial data on a daily basis. It is of enormous significance when it comes to discovering implicit, non-trivial and potentially valuable information from this spatial data. Spatial co-location patterns reveal the distribution rules of spatial features, which can be valuable for application users. This book provides commercial software developers with proven and effective algorithms for detecting and filtering these implicit patterns, and includes easily implemented pseudocode for all the algorithms. Furthermore, it offers a basis for further research in this promising field.Preference-based co-location pattern mining refers to mining constrained or condensed co-location patterns instead of mining all prevalent co-location patterns. Based on the authors’ recent research, the book highlights techniques for solving a range of problems in this context, including maximal co-location pattern mining, closed co-location pattern mining, top-k co-location pattern mining, non-redundant co-location pattern mining, dominant co-location pattern mining, high utility co-location pattern mining, user-preferred co-location pattern mining, and similarity measures between spatial co-location patterns.Presenting a systematic, mathematical study of preference-based spatial co-location pattern mining, this book can be used both as a textbook for those new to the topic and as a reference resource for experienced professionals.

The development of information technology has made it possible to collect large amounts of spatial data on a daily basis. It is of enormous significance when it comes to discovering implicit, non-trivial and potentially valuable information from this spatial data. Spatial co-location patterns reveal the distribution rules of spatial features, which can be valuable for application users. This book provides commercial software developers with proven and effective algorithms for detecting and filtering these implicit patterns, and includes easily implemented pseudocode for all the algorithms. Furthermore, it offers a basis for further research in this promising field.Preference-based co-location pattern mining refers to mining constrained or condensed co-location patterns instead of mining all prevalent co-location patterns. Based on the authors’ recent research, the book highlights techniques for solving a range of problems in this context, including maximal co-location pattern mining, closed co-location pattern mining, top-k co-location pattern mining, non-redundant co-location pattern mining, dominant co-location pattern mining, high utility co-location pattern mining, user-preferred co-location pattern mining, and similarity measures between spatial co-location patterns.Presenting a systematic, mathematical study of preference-based spatial co-location pattern mining, this book can be used both as a textbook for those new to the topic and as a reference resource for experienced professionals.

Urban environments generate massive streams of spatio-temporal data, yet accurately predicting urban dynamics remains a fundamental challenge due to complex human mobility patterns, evolving environmental conditions, and distributional shifts across time and space. Mechanism-Driven Explainable Urban Spatio-Temporal Prediction offers a comprehensive and innovative framework that integrates physical mechanisms, causal modeling, and information-theoretic principles into modern deep learning methods, enabling more interpretable, reliable, and generalizable spatio-temporal forecasting.This monograph presents a unified perspective across intrinsic and extrinsic factors that shape urban mobility. It introduces a gravity-inspired potential energy field model to capture intrinsic behavioral mechanisms at both regional and road-network scales, bridging discrete and continuous temporal modeling through differential equation networks. Beyond intrinsic mechanisms, the book proposes a causal basis-vector representation to model spatio-temporal distribution shifts caused by unknown confounders, enhancing robustness under varying scenarios. Furthermore, it develops a theoretically grounded information-theoretic decomposition framework that reduces the complexity of mixed urban data distributions and pushes the predictive performance beyond existing limits.Combining theoretical foundations, methodological innovations, and extensive empirical studies on real-world urban traffic datasets, this book provides a rigorous yet accessible resource for researchers in spatio-temporal modeling, intelligent transportation systems, machine learning, and urban computing. It also serves as a valuable reference for practitioners seeking interpretable and mechanism-aware prediction models for smart city applications.

Automated Machine Learning for Data-centric Systems provides a system-oriented and knowledge-driven perspective on automated machine learning in modern data-centric environments. As machine learning models become core components of data management systems, the manual design and optimization of models increasingly limit scalability, reproducibility, and long-term adaptability. This book addresses these challenges by rethinking AutoML not merely as a collection of optimization algorithms, but as a foundational capability embedded within data-centric systems.The book presents a unified framework that connects core AutoML techniques—such as hyperparameter optimization, combined algorithm selection and configuration, neural architecture search, and model compression—with system-level considerations and diverse data scenarios. It emphasizes how knowledge, experience, and structural properties of data can guide automation, enabling AutoML systems to move beyond blind search toward more efficient, interpretable, and sustainable model design. Through detailed discussions of temporal, sequential, graph, and federated data settings, the book demonstrates how AutoML techniques can be adapted to real-world constraints including data heterogeneity, resource limitations, and deployment complexity.Designed for researchers, graduate students, and practitioners, this book bridges the gap between algorithm-centric AutoML research and the practical needs of data-centric systems. By integrating theoretical foundations with system-level insights and emerging research directions, Automated Machine Learning for Data-centric Systems serves as both a comprehensive reference and a forward-looking guide for building scalable, intelligent, and automated data-driven systems.

This book systematically and comprehensively explores and discusses the theory and technology of big data analysis. The main topics include the basic concept of big data analytics, its core architecture, the calculation model used, the clash between big data and information security, big data and natural language processing, and big data and biological information processing.Given its scope, the book can meet the long-term training needs of diverse talents at colleges and universities, as well as teaching and research staff engaged in cyberspace security, computer science and technology, software engineering, artificial intelligence, information and communication engineering, and related disciplines. The book also has essential practical and reference value for all those engaged in research related to big data analytics.

The book provides a systematic overview of data privacy and data governance from both conceptual and technical perspectives. The first section introduces the fundamentals of data privacy and data governance from a historical and systemic standpoint. Sections two through four focus on large-scale data collection, machine learning, and data ecosystem scenarios, respectively, providing an introduction to their corresponding technical foundations and summarizing key current issues and technological solutions.This book offers a fresh perspective on data privacy and data governance within the context of the new data ecosystem. It primarily explains technical concepts and algorithms, supplemented by case studies, in a balanced and informative manner. It is intended for both technical professionals seeking information and general readers interested in developing a basic understanding of data privacy and data governance, as well as cultivating data literacy.The translation was done with the help of artificial intelligence. A subsequent human revision was done primarily in terms of content.

Artificial Intelligence (AI) is revolutionizing the education industry, particularly in understanding and enhancing student learning engagement in online learning. The book aims to get an in-depth exploration into a three-stage framework of AI-enabled learning engagement analysis, which provides effective tools and methodologies for education researchers and practitioners, facilitating intelligent transformation and optimization. It delves into intelligent recognition, including emotional and cognitive engagement, supported by detailed algorithmic introductions and case studies. The book further examines the relationship between engagement and outcomes, covering cognition, emotion, self-regulation, and social network characteristics. Furthermore, it presents adaptive interventions, offering a comprehensive guide to leveraging AI for personalized learning experiences and improved learning outcomes.The book provides valuable insights and practical tools for enhancing teaching and learning outcomes. Whether you are an educator seeking to integrate AI into your teaching strategies or a researcher exploring the frontiers of educational technology, this book equips you with the knowledge and resources to navigate the evolving landscape of AI-enabled education.This publication underscores the significance of practical applications, presenting a compendium of pioneering research methodologies and case studies that elucidate the integration of AI and data analytics within pedagogical contexts. Whether the objective is to refine comprehension of online learning engagement dynamics or to deploy AI-infused strategies in educational settings, this text serves as an invaluable resource for revolutionizing education with AI.Chapter 2 is available for open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

This book demystifies the core principles and architectural design of spatiotemporal big data systems, offering incisive analysis of the unique attributes of spatiotemporal data and its broad applicability in real-world scenarios, aiming to impart a profound understanding of the intrinsic value of spatiotemporal big data and its far-reaching impact across various fields.In the core technology section, particular emphasis is placed on the pivotal role of GIS (Geographic Information Systems) technology in the processing of spatiotemporal big data, comprehensively covering the entire process from data collection, pre-processing, in-depth analysis to final visualization. Through carefully selected real-world cases and detailed technical explanations, readers will gain proficiency in leveraging GIS technology to uncover the latent value of spatiotemporal big data.The book also delves into the essential techniques and algorithms required for building efficient spatiotemporal big data systems, such as efficient data storage and management, intelligent data mining and analysis, alongside specific application cases under the smart city framework, including advanced practices in urban planning optimization, traffic management innovation, and environmental monitoring upgrades. Rich in content and blending theoretical depth with practical guidance, it serves as a valuable resource and reference guide for both academic experts and practitioners in the field, as well as a quality read for those intrigued by spatiotemporal big data systems.The translation was done with the help of artificial intelligence. A subsequent human revision was done primarily in terms of content.

Blockchain, a decentralized ledger technology based on cryptographic algorithms, ensures the creation of immutable and tamper-proof ledgers in decentralized systems. The transparent nature of blockchain allows public access to transaction records, providing unprecedented opportunities for blockchain data analytics and mining. The primary value of blockchain transaction data analytics lies in two aspects: 1) by delving into the details of blockchain transaction data, we can extensively explore various types of user behavior patterns and the evolutionary process of blockchain transaction networks; and 2) analyzing blockchain transaction data aids in identifying illicit activities, offering effective regulatory solutions for the establishment of a healthier blockchain ecosystem. This book focuses on data analytics based on network-based approaches, providing a comprehensive analysis of blockchain data analytics problems, key technologies, and future directions. Different from most existing book, this book takes a unique approach to blockchain data analysis research, focusing on data analytics based on network-based approaches. Leveraging network analysis methods, the book concentrates on three main aspects of blockchain transaction data analytics and mining: (1) transaction network modelling and pattern mining, including macro and micro-level account attributes, money laundering network patterns, and network evolution patterns; (2) account business classification, such as account label prediction based on graph neural networks; and (3) anomaly behavior identification, covering phishing detection, risk scoring, and transaction tracking. Designed as a valuable resource for students, researchers, engineers, and policymakers in various fields related to blockchain data analytics, this book holds significant importance for understanding blockchain transaction behavior and addressing the detection of illicit activities in the blockchain space.

Blockchain, a decentralized ledger technology based on cryptographic algorithms, ensures the creation of immutable and tamper-proof ledgers in decentralized systems. The transparent nature of blockchain allows public access to transaction records, providing unprecedented opportunities for blockchain data analytics and mining. The primary value of blockchain transaction data analytics lies in two aspects: 1) by delving into the details of blockchain transaction data, we can extensively explore various types of user behavior patterns and the evolutionary process of blockchain transaction networks; and 2) analyzing blockchain transaction data aids in identifying illicit activities, offering effective regulatory solutions for the establishment of a healthier blockchain ecosystem. This book focuses on data analytics based on network-based approaches, providing a comprehensive analysis of blockchain data analytics problems, key technologies, and future directions. Different from most existing book, this book takes a unique approach to blockchain data analysis research, focusing on data analytics based on network-based approaches. Leveraging network analysis methods, the book concentrates on three main aspects of blockchain transaction data analytics and mining: (1) transaction network modelling and pattern mining, including macro and micro-level account attributes, money laundering network patterns, and network evolution patterns; (2) account business classification, such as account label prediction based on graph neural networks; and (3) anomaly behavior identification, covering phishing detection, risk scoring, and transaction tracking. Designed as a valuable resource for students, researchers, engineers, and policymakers in various fields related to blockchain data analytics, this book holds significant importance for understanding blockchain transaction behavior and addressing the detection of illicit activities in the blockchain space.

This book describes theoretical elements, practical approaches, and specialized tools that systematically organize, characterize, and analyze big data gathered from educational affairs and settings. Moreover, the book shows several inference criteria to leverage and produce descriptive, explanatory, and predictive closures to study and understand education phenomena at in classroom and online environments.This is why diverse researchers and scholars contribute with valuable chapters to ground with well-–sounded theoretical and methodological constructs in the novel field of Educational Data Science (EDS), which examines academic big data repositories, as well as to introduces systematic reviews, reveals valuable insights, and promotes its application to extend its practice. EDS as a transdisciplinary field relies on statistics, probability, machine learning, data mining, and analytics, in addition to biological, psychological, and neurological knowledge aboutlearning science. With this in mind, the book is devoted to those that are in charge of educational management, educators, pedagogues, academics, computer technologists, researchers, and postgraduate students, who pursue to acquire a conceptual, formal, and practical landscape of how to deploy EDS to build proactive, real- time, and reactive applications that personalize education, enhance teaching, and improve learning!Chapter “Sync Ratio and Cluster Heat Map for Visualizing Student Engagement” is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

This book describes theoretical elements, practical approaches, and specialized tools that systematically organize, characterize, and analyze big data gathered from educational affairs and settings. Moreover, the book shows several inference criteria to leverage and produce descriptive, explanatory, and predictive closures to study and understand education phenomena at in classroom and online environments.This is why diverse researchers and scholars contribute with valuable chapters to ground with well-–sounded theoretical and methodological constructs in the novel field of Educational Data Science (EDS), which examines academic big data repositories, as well as to introduces systematic reviews, reveals valuable insights, and promotes its application to extend its practice. EDS as a transdisciplinary field relies on statistics, probability, machine learning, data mining, and analytics, in addition to biological, psychological, and neurological knowledge aboutlearning science. With this in mind, the book is devoted to those that are in charge of educational management, educators, pedagogues, academics, computer technologists, researchers, and postgraduate students, who pursue to acquire a conceptual, formal, and practical landscape of how to deploy EDS to build proactive, real- time, and reactive applications that personalize education, enhance teaching, and improve learning!Chapter “Sync Ratio and Cluster Heat Map for Visualizing Student Engagement” is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

This open access book systematically investigates the topic of entity alignment, which aims to detect equivalent entities that are located in different knowledge graphs. Entity alignment represents an essential step in enhancing the quality of knowledge graphs, and hence is of significance to downstream applications, e.g., question answering and recommender systems. Recent years have witnessed a rapid increase in the number of entity alignment frameworks, while the relationships among them remain unclear. This book aims to fill that gap by elaborating the concept and categorization of entity alignment, reviewing recent advances in entity alignment approaches, and introducing novel scenarios and corresponding solutions.Specifically, the book includes comprehensive evaluations and detailed analyses of state-of-the-art entity alignment approaches and strives to provide a clear picture of the strengths and weaknesses of the currently available solutions, so as to inspire follow-upresearch. In addition, it identifies novel entity alignment scenarios and explores the issues of large-scale data, long-tail knowledge, scarce supervision signals, lack of labelled data, and multimodal knowledge, offering potential directions for future research.The book offers a valuable reference guide for junior researchers, covering the latest advances in entity alignment, and a valuable asset for senior researchers, sharing novel entity alignment scenarios and their solutions. Accordingly, it will appeal to a broad audience in the fields of knowledge bases, database management, artificial intelligence and big data.

This open access book systematically investigates the topic of entity alignment, which aims to detect equivalent entities that are located in different knowledge graphs. Entity alignment represents an essential step in enhancing the quality of knowledge graphs, and hence is of significance to downstream applications, e.g., question answering and recommender systems. Recent years have witnessed a rapid increase in the number of entity alignment frameworks, while the relationships among them remain unclear. This book aims to fill that gap by elaborating the concept and categorization of entity alignment, reviewing recent advances in entity alignment approaches, and introducing novel scenarios and corresponding solutions.Specifically, the book includes comprehensive evaluations and detailed analyses of state-of-the-art entity alignment approaches and strives to provide a clear picture of the strengths and weaknesses of the currently available solutions, so as to inspire follow-upresearch. In addition, it identifies novel entity alignment scenarios and explores the issues of large-scale data, long-tail knowledge, scarce supervision signals, lack of labelled data, and multimodal knowledge, offering potential directions for future research.The book offers a valuable reference guide for junior researchers, covering the latest advances in entity alignment, and a valuable asset for senior researchers, sharing novel entity alignment scenarios and their solutions. Accordingly, it will appeal to a broad audience in the fields of knowledge bases, database management, artificial intelligence and big data.

With the growing advances in technology and transformation to digital services, the world is becoming more connected and more complex. Huge heterogeneous data are generated at rapid speed from various types of sensors. Augmented with artificial intelligence and machine learning and internet of things, latent relations, and new insights can be captured helping in optimizing plans and resource utilization, improving infrastructure, and enhancing quality of services.A “spatial data management system” is a way to take care of data that has something to do with space. This could include data such as maps, satellite images, and GPS data. A temporal data management system is a system designed to manage data that has a temporal component. This could include data such as weather data, financial data, and social media data. Some advanced techniques used in spatial and temporal data management systems include geospatial indexing for efficient querying and retrieval of location-based data, time-series analysis for understanding and predicting temporal patterns in datasets like weather or financial trends, machine learning algorithms for uncovering hidden patterns and correlations in large and complex datasets, and integration with Internet of Things (IoT) technologies for real-time data collection and analysis. These techniques, augmented with artificial intelligence, enable the extraction of latent relations and insights, thereby optimizing plans, improving infrastructure, and enhancing the quality of services. This book provides essential technical knowledge, best practices, and case studies on the state-of-the-art techniques of artificial intelligence and machine learning for spatiotemporal data analysis and modeling. The book is composed of several chapters written by experts in their fields and focusing on several applications including recommendation systems, big data analytics, supply chains and e-commerce, energy consumption and demand forecasting,and traffic and environmental monitoring. It can be used as academic reference at graduate level or by professionals in science and engineering related fields such as data science and engineering, big data analytics and mining, artificial intelligence, machine learning and deep learning, cloud computing, and internet of things.