Neural Symbolic Knowledge Graph Reasoning: A Pathway Towards Neural Symbolic AI - Rilegato

Liu, Lihui; Tong, Hanghang

Rilegato

ISBN 10: 3032158575 ISBN 13: 9783032158574

Casa editrice: Springer-Verlag GmbH, 2026

Riassunto

This book explores various aspects of knowledge graph reasoning to solve different tasks, encompassing first, traditional symbolic methods for knowledge graph reasoning; second, recent developments in neural-based knowledge graph reasoning techniques; and third, cutting-edge advancements in neural-symbolic hybrid approaches to knowledge graph reasoning. The authors focus on the model and algorithm design aspect and study knowledge graphs from two perspectives: background knowledge graph and input query. Knowledge graph reasoning, which aims to infer and discover new knowledge from existing information in the knowledge graph, has played an important role in many real-world applications, such as question answering and recommender systems. A new trend in knowledge graph reasoning is the combination of neural models with symbolic knowledge graphs, allowing for the design of models that are not only efficient and accurate, but also interpretable. In this book, the authors study the application of neural-symbolic knowledge reasoning to different tasks from two perspectives: the input query and the background knowledge graph.

Su questo libro

Informazioni sull'autore

Lihui Liu, Ph.D., is an Assistant Professor in the Department of Computer Science at Wayne State University. He received his Ph.D. from the Department of Computer Science at the University of Illinois at Urbana-Champaign. His research focuses on large-scale data mining and machine learning, particularly on graphs, with an emphasis on knowledge graph reasoning. Dr. Liu’s research has been published at several major conferences and in journals on data mining and artificial intelligence.  He has also served as a reviewer and program committee member for top-tier data mining and artificial intelligence conferences and journals, including KDD, WWW, AAAI, IJCAI, and BigData.

Hanghang Tong, Ph.D, is a Professor and University Scholar at Siebel School of Computing and Data Science at the University of Illinois at Urbana-Champaign.  He received his M.Sc. and Ph.D. degrees from Carnegie Mellon University in 2008 and 2009, both in Machine Learning. His research interests include large scale data mining for graphs and multimedia.  Dr. Tong has published 300+ papers, and his research has received several awards, including SDM/IBM 2018 early career data mining research award, two ‘test of time’ awards (ICDM 2015 & 2022 10-Year Highest Impact Paper award), ICDM Tao Li award (2019), NSF CAREER award, and several best paper awards. He was Editor-in-Chief of ACM SIGKDD Explorations (2018 - 2022). He is also a distinguished member of ACM (2021) and a Fellow of IEEE (2022).

Dalla quarta di copertina

This book explores various aspects of knowledge graph reasoning to solve different tasks, encompassing first, traditional symbolic methods for knowledge graph reasoning; second, recent developments in neural-based knowledge graph reasoning techniques; and third, cutting-edge advancements in neural-symbolic hybrid approaches to knowledge graph reasoning. The authors focus on the model and algorithm design aspect and study knowledge graphs from two perspectives: background knowledge graph and input query. Knowledge graph reasoning, which aims to infer and discover new knowledge from existing information in the knowledge graph, has played an important role in many real-world applications, such as question answering and recommender systems. A new trend in knowledge graph reasoning is the combination of neural models with symbolic knowledge graphs, allowing for the design of models that are not only efficient and accurate, but also interpretable. In this book, the authors study the application of neural-symbolic knowledge reasoning to different tasks from two perspectives: the input query and the background knowledge graph.

In addition, this book:

• Presents existing practices at the methodology level by building index structure for saving query time
• Discusses how to iteratively find answers when acknowledge graph is incomplete and the query is dynamic
• Focuses on designing effective models that can answer conversational questions

Dettagli dell'edizione

• Editore: Springer-Verlag GmbH
• Data di pubblicazione: 2026
• Lingua: Inglese
• ISBN 10: 3032158575
• ISBN 13: 9783032158574
• Rilegatura: Copertina rigida
• Numero di pagine: 172
• Contatto del produttore: Springer Nature Customer Service Center GmbH; ProductSafety@springernature.com; ; Europaplatz 3; Heidelberg; 69115; Germania