Knowledge graphs (KGs) have become indispensable components of intelligent systems, offering an efficient means to represent complex information. They are a powerful tool for multiple exploratory tasks, including complex information storage, organization, and querying. Their complex structure, comprising interconnected entities and relationships, facilitates the process of knowledge discovery which is crucial for machine reasoning. By encapsulating complex knowledge from diverse data sources, KGs play a pivotal role in advancing AI-related knowledge acquisition and interpretation. They provide a general picture of the knowledge by integrating data from various sources such as traditional databases, social media, and the web. Nonetheless, harnessing KGs poses significant challenges, including integrating heterogeneous information, constructing unambiguous KGs, predicting links accurately, addressing entity redundancy, and more. Additionally, real-time processing, dynamic modification, and ensuring data integrity present further hurdles for KG applications.
To advance various KG-guided applications, this Research Topic concentrates on advanced technologies and techniques to establish a comprehensive framework for KG construction, integrate multiple KGs via fusion methods, and employ deep learning for effective entity link representation. The primary objective of this collection is to forge meaningful connections between artificial intelligence methodologies and KG-guided applications to lay the groundwork for future KG application development. Thus, the research questions for authors are as follows: What are the predominant applications of knowledge graphs within AI-related technologies? In what ways do deep learning techniques enhance knowledge graph representation, link prediction, and interpretability? How can we safeguard information privacy and security when constructing a knowledge graph from diverse sources? What strategies can be employed to enhance the integrity of knowledge graph information? How can the large language models and knowledge graphs be merged to contribute to AI-based applications?
This Research Topic emphasizes cutting-edge developments and techniques within the KG domain, serving as a platform for researchers, technology experts, and AI enthusiasts to share their insights, research findings, and surveys on various KG challenges and AI-related knowledge acquisition. Topics covered include KG construction, representation, learning, AI-driven applications, state-of-the-art KG technologies, integration and fusion techniques, and intelligence-enhanced data analytics.
Topics of interest include, but are not limited to:
• Knowledge graph construction models and algorithms
• Knowledge graph completion techniques
• Knowledge graph integration and information fusion techniques
• Multi-modal knowledge graph modelling and representation learning
• Big data and knowledge graphs
• Large language model and knowledge graphs
• Ontologies, knowledge interpretation, link prediction
• Knowledge-driven AI applications and technologies, e.g., for health informatics
• Knowledge graph and information integrity, privacy, and security
• Dynamic knowledge graph theories, models, representation, and processing
Keywords:
Knowledge graphs, language models, fusion, multi-modal, artifical intelligence
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Knowledge graphs (KGs) have become indispensable components of intelligent systems, offering an efficient means to represent complex information. They are a powerful tool for multiple exploratory tasks, including complex information storage, organization, and querying. Their complex structure, comprising interconnected entities and relationships, facilitates the process of knowledge discovery which is crucial for machine reasoning. By encapsulating complex knowledge from diverse data sources, KGs play a pivotal role in advancing AI-related knowledge acquisition and interpretation. They provide a general picture of the knowledge by integrating data from various sources such as traditional databases, social media, and the web. Nonetheless, harnessing KGs poses significant challenges, including integrating heterogeneous information, constructing unambiguous KGs, predicting links accurately, addressing entity redundancy, and more. Additionally, real-time processing, dynamic modification, and ensuring data integrity present further hurdles for KG applications.
To advance various KG-guided applications, this Research Topic concentrates on advanced technologies and techniques to establish a comprehensive framework for KG construction, integrate multiple KGs via fusion methods, and employ deep learning for effective entity link representation. The primary objective of this collection is to forge meaningful connections between artificial intelligence methodologies and KG-guided applications to lay the groundwork for future KG application development. Thus, the research questions for authors are as follows: What are the predominant applications of knowledge graphs within AI-related technologies? In what ways do deep learning techniques enhance knowledge graph representation, link prediction, and interpretability? How can we safeguard information privacy and security when constructing a knowledge graph from diverse sources? What strategies can be employed to enhance the integrity of knowledge graph information? How can the large language models and knowledge graphs be merged to contribute to AI-based applications?
This Research Topic emphasizes cutting-edge developments and techniques within the KG domain, serving as a platform for researchers, technology experts, and AI enthusiasts to share their insights, research findings, and surveys on various KG challenges and AI-related knowledge acquisition. Topics covered include KG construction, representation, learning, AI-driven applications, state-of-the-art KG technologies, integration and fusion techniques, and intelligence-enhanced data analytics.
Topics of interest include, but are not limited to:
• Knowledge graph construction models and algorithms
• Knowledge graph completion techniques
• Knowledge graph integration and information fusion techniques
• Multi-modal knowledge graph modelling and representation learning
• Big data and knowledge graphs
• Large language model and knowledge graphs
• Ontologies, knowledge interpretation, link prediction
• Knowledge-driven AI applications and technologies, e.g., for health informatics
• Knowledge graph and information integrity, privacy, and security
• Dynamic knowledge graph theories, models, representation, and processing
Keywords:
Knowledge graphs, language models, fusion, multi-modal, artifical intelligence
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.