Knowledge Graphs For Explainable Artificial Intelligence Foundations Applications And Challenges

The latest advances in Artificial Intelligence and (deep) Machine Learning in particular revealed a major drawback of modern intelligent systems, namely the inability to explain their decisions in a way that humans can easily understand. While eXplainable AI rapidly became an active area of research in response to this need for improved understandability and trustworthiness, the field of Knowledge Representation and Reasoning (KRR) has on the other hand a long-standing tradition in managing information in a symbolic, human-understandable form. This book provides the first comprehensive collection of research contributions on the role of knowledge graphs for eXplainable AI (KG4XAI), and the papers included here present academic and industrial research focused on the theory, methods and implementations of AI systems that use structured knowledge to generate reliable explanations. Introductory material on knowledge graphs is included for those readers with only a minimal background in the field, as well as specific chapters devoted to advanced methods, applications and case-studies that use knowledge graphs as a part of knowledge-based, explainable systems (KBX-systems). The final chapters explore current challenges and future research directions in the area of knowledge graphs for eXplainable AI. The book not only provides a scholarly, state-of-the-art overview of research in this subject area, but also fosters the hybrid combination of symbolic and subsymbolic AI methods, and will be of interest to all those working in the field.

If only it were possible to develop automated and trainable neural systems that could justify their behavior in a way that could be interpreted by humans like a symbolic system. The field of Neurosymbolic AI aims to combine two disparate approaches to AI; symbolic reasoning and neural or connectionist approaches such as Deep Learning. The quest to unite these two types of AI has led to the development of many innovative techniques which extend the boundaries of both disciplines. This book, Compendium of Neurosymbolic Artificial Intelligence, presents 30 invited papers which explore various approaches to defining and developing a successful system to combine these two methods. Each strategy has clear advantages and disadvantages, with the aim of most being to find some useful middle ground between the rigid transparency of symbolic systems and the more flexible yet highly opaque neural applications. The papers are organized by theme, with the first four being overviews or surveys of the field. These are followed by papers covering neurosymbolic reasoning; neurosymbolic architectures; various aspects of Deep Learning; and finally two chapters on natural language processing. All papers were reviewed internally before publication. The book is intended to follow and extend the work of the previous book, Neuro-symbolic artificial intelligence: The state of the art (IOS Press; 2021) which laid out the breadth of the field at that time. Neurosymbolic AI is a young field which is still being actively defined and explored, and this book will be of interest to those working in AI research and development.

Semantic computing is an integral part of modern technology, an essential component of fields as diverse as artificial intelligence, data science, knowledge discovery and management, big data analytics, e-commerce, enterprise search, technical documentation, document management, business intelligence, and enterprise vocabulary management. This book presents the proceedings of SEMANTICS 2023, the 19th International Conference on Semantic Systems, held in Leipzig, Germany, from 20 to 22 September 2023. The conference is a pivotal event for those professionals and researchers actively engaged in harnessing the power of semantic computing, an opportunity to increase their understanding of the subject’s transformative potential while confronting its practical limitations. Attendees include information managers, IT architects, software engineers, and researchers from a broad spectrum of organizations, including research facilities, non-profit entities, public administrations, and the world's largest corporations. For this year’s conference a total of 54 submissions were received in response to a call for papers. These were subjected to a rigorous, double-blind review process, with at least three independent reviews conducted for each submission. The 16 papers included here were ultimately accepted for presentation, with an acceptance rate of 29.6%. Areas covered include novel research challenges in areas such as data science, machine learning, logic programming, content engineering, social computing, and the Semantic Web. The book provides an up-to-date overview, which will be of interest to all those wishing to stay abreast of emerging trends and themes within the vast field of semantic computing.

The two volume set LNCS 12506 and 12507 constitutes the proceedings of the 19th International Semantic Web Conference, ISWC 2020, which was planned to take place in Athens, Greece, during November 2-6, 2020. The conference changed to a virtual format due to the COVID-19 pandemic. The papers included in this volume deal with the latest advances in fundamental research, innovative technology, and applications of the Semantic Web, linked data, knowledge graphs, and knowledge processing on the Web. They were carefully reviewed and selected for inclusion in the proceedings as follows: Part I: Features 38 papers from the research track which were accepted from 170 submissions; Part II: Includes 22 papers from the resources track which were accepted from 71 submissions; and 21 papers in the in-use track, which had a total of 46 submissions. Chapter “Transparent Integration and Sharing of Life Cycle Sustainability Data with Provenance ” is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

Artificial intelligence (AI)---including the sub-fields of machine learning and deep learning has advanced considerably in recent years. In tandem with these performance improvements, understanding how AI systems make decisions has become increasingly difficult due to many nonlinear transformations of input data and the complex nature of the algorithms involved. Explainable AI (XAI) are the techniques to examine these decision processes. A main desideratum of XAI is user understandability, while explanations should take into account the context and domain knowledge of the problem. Humans understand and reason mostly in terms of concepts and combinations thereof. A knowledge graph (KG) embodies such understanding in links between concepts; such a natural conceptual network creates a pathway to use knowledge graphs in XAI applications to improve overall understandability of complex AI algorithms. Over the course of this dissertation, we outline a number of contributions towards explaining the AI decision in a human friendly way. We show a proof-of-concept on how domain knowledge can be used to analyze the input and output data of AI algorithms. We materialize the domain knowledge into knowledge graph (more technically ontology) and by using concept induction algorithm find the pattern between input and output. After demonstrating this, we start to experiment on a large scale, as we found that the current state of the art concept induction algorithm does not scale well with large amounts of data. To solve this runtime issue, we develop a new algorithm efficient concept induction (ECII), which improves the runtime significantly. During this process, we also find that current tools are not adequate to create and edit the knowledge graphs, as well as that there is scarcity to quality knowledge graph. We make the creation and editing process easier, by creating OWLAx and ROWLTab plugin for the industry-standard ontology editor, Protégé. We also develop a large knowledge graph from the Wikipedia category hierarchy. Overall, these research contributions improved the software support to create knowledge graph, developed a better knowledge graph, and showed a new direction on how AI decision making can be explained by using a contextual knowledge graph.

This open access book is part of the LAMBDA Project (Learning, Applying, Multiplying Big Data Analytics), funded by the European Union, GA No. 809965. Data Analytics involves applying algorithmic processes to derive insights. Nowadays it is used in many industries to allow organizations and companies to make better decisions as well as to verify or disprove existing theories or models. The term data analytics is often used interchangeably with intelligence, statistics, reasoning, data mining, knowledge discovery, and others. The goal of this book is to introduce some of the definitions, methods, tools, frameworks, and solutions for big data processing, starting from the process of information extraction and knowledge representation, via knowledge processing and analytics to visualization, sense-making, and practical applications. Each chapter in this book addresses some pertinent aspect of the data processing chain, with a specific focus on understanding Enterprise Knowledge Graphs, Semantic Big Data Architectures, and Smart Data Analytics solutions. This book is addressed to graduate students from technical disciplines, to professional audiences following continuous education short courses, and to researchers from diverse areas following self-study courses. Basic skills in computer science, mathematics, and statistics are required.

The field of semantic computing is highly diverse, linking areas such as artificial intelligence, data science, knowledge discovery and management, big data analytics, e-commerce, enterprise search, technical documentation, document management, business intelligence, and enterprise vocabulary management. As such it forms an essential part of the computing technology that underpins all our lives today. This volume presents the proceedings of SEMANTiCS 2021, the 17th International Conference on Semantic Systems. As a result of the continuing Coronavirus restrictions, SEMANTiCS 2021 was held in a hybrid form in Amsterdam, the Netherlands, from 6 to 9 September 2021. The annual SEMANTiCS conference provides an important platform for semantic computing professionals and researchers, and attracts information managers, IT­architects, software engineers, and researchers from a wide range of organizations, such as research facilities, NPOs, public administrations and the largest companies in the world. The subtitle of the 2021 conference’s was “In the Era of Knowledge Graphs”, and 66 submissions were received, from which the 19 papers included here were selected following a rigorous single-blind reviewing process; an acceptance rate of 29%. Topics covered include data science, machine learning, logic programming, content engineering, social computing, and the Semantic Web, as well as the additional sub-topics of digital humanities and cultural heritage, legal tech, and distributed and decentralized knowledge graphs. Providing an overview of current research and development, the book will be of interest to all those working in the field of semantic systems.

This book constitutes the refereed proceedings of the 20th International Conference on Artificial Intelligence in Medicine, AIME 2022, held in Halifax, NS, Canada, in June 2022. The 39 full papers presented together with 7 short papers were selected from 113 submissions. The papers are grouped in topical sections on knowledge-based system; machine learning; medical image processing; predictive modeling; natural language processing.

Knowledge graphs are increasingly used in scientific and industrial applications. The large number and size of knowledge graphs published as Linked Data in autonomous sources has led to the development of various interfaces to query these knowledge graphs. Therefore, effective query processing approaches that enable efficient information retrieval from these knowledge graphs need to address the capabilities and limitations of different Linked Data Fragment interfaces. This book investigates novel approaches to addressing the challenges that arise in the presence of decentralized, heterogeneous sources of knowledge graphs. The effectiveness of these approaches is empirically evaluated and demonstrated using various real world and synthetic large-scale knowledge graphs throughout. First, a sample-based approach for generating fine-grained performance profiles is proposed, and it is demonstrated how the information from such profiles can be leveraged in cost model-based query planning. In addition, a sample-based data distribution profiling approach is advocated which aims to estimate the statistical profile features of large knowledge graphs and the applicability of these estimations in federated querying processing is demonstrated. The remainder of the book focuses on techniques to devise efficient query processing approaches when heterogeneous interfaces need to be queried but no fine-grained statistics are available. Robust techniques to support efficient query processing in these circumstances are investigated and results are shared to demonstrate the way in which these techniques can outperform state-of-the-art approaches. Finally, the author describes a framework for federated query processing over heterogeneous federations of Linked Data Fragments to exploit the capabilities of different sources by defining interface-aware approaches.