(2024 WWW) New Frontiers of Knowledge Graph Reasoning: Recent Advances and Future Trends
WWW 2024 Tutorial
Introduction
Knowledge graph reasoning plays an important role in data mining, AI, Web, and social science. These knowledge graphs serve as intuitive repositories of human knowledge, allowing for the inference of new information. However, traditional symbolic reasoning, while powerful in its own right, faces challenges posed by incomplete and noisy data in the knowledge graphs. In contrast, recent years have witnessed the emergence of Neural Symbolic AI, an exciting development that fuses the capabilities of deep learning and symbolic reasoning. It aims to create AI systems that are not only highly interpretable and explainable but also incredibly versatile, effectively bridging the gap between symbolic and neural approaches. Furthermore, with the advent of large language models, the integration of LLMs with knowledge graph reasoning has emerged as a prominent frontier, offering the potential to unlock unprecedented capabilities. This tutorial aims to comprehensively review different aspects of knowledge graph reasoning applications and also introduce the recent advances about Neural Symbolic reasoning and combining knowledge graph reasoning with large language models. It is intended to benefit researchers and practitioners in the fields of data mining, AI, Web, and social science.
Outline
Introduction
Part I: Knowledge Graph Reasoning: Basic Concepts and Techniques
Part II: Recent Advance #1: Neural Reasoning for Natural Language Queries
Part III: Recent Advance #2: Neural Reasoning for Logical Queries
Part IV: Recent Advance #3: Neural Reasoning Beyond Entities and Relations
Part V: Recent Advance #4: LLM+KGR
Part VI: Open Challenges and Future Directions
Slides can be found in
Speakers
Lihui Liu
Lihui Liu is a Ph.D. student in the Department of Computer Science at the University of Illinois at Urbana-Champaign. He is the corresponding tutor. His research focuses on large-scale data mining and machine learning, particularly on graphs, with an emphasis on knowledge graph reasoning. Lihui's research has been published at several major conferences and journals in data mining and artificial intelligence, and he has 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. More information about Lihui can be found on his personal website at https://lihuiliullh.github.io/
Zihao Wang
Zihao Wang is a Ph.D. student in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology. His research focuses on the intersection of graph machine learning and the semantic web, with an emphasis on graph knowledge representation and reasoning. Zihao's research has been published at top-tier conferences and journals in machine learning, data mining, and natural language processing. He has served as a program committee member for top-tier conferences including AAAI, ACL, CIKM, EMNLP, KDD, NeurIPS, and ICLR.
Jiaxin Bai
Jiaxin Bai is a Ph.D. student in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology. His research focuses on the logical reasoning of knowledge graphs. He has work published in top-tier conferences and journals in machine learning, data mining, and natural language processing. He also serves as a reviewer of data mining and natural language processing conferences and journals including KDD, TKDE, ACL, and EMNLP.
Yangqiu Song
Yangqiu Song is an associate professor at Department of CSE at HKUST, and an associate director of HKUST-WeBank Joint Lab. He was an assistant professor at Lane Department of CSEE at WVU (2015-2016); a post-doc researcher at UIUC (2013-2015), a post-doc researcher at HKUST and visiting researcher at Huawei Noah's Ark Lab, Hong Kong (2012-2013); an associate researcher at Microsoft Research Asia (2010-2012); a staff researcher at IBM Research-China (2009-2010). He received B.E. and PhD degrees from Tsinghua University, China, in July 2003 and January 2009. He is now also a visiting academic scholar at Amazon Search Science and AI Team@A9 (Jan. 2022 - present).
Hanghang Tong
Hanghang Tong is currently an associate professor at Department of Computer Science at University of Illinois at Urbana-Champaign. Before that, he worked at Arizona State University as an associate professor, at City University of New York (City College) as an assistant professor and at IBM T. J. Watson Research Center as a Research Staff Member. He received his Ph.D. from the Machine Learning Department of School of Computer Science at Carnegie Mellon University in 2009. His major research interest lies in large-scale data mining for graphs and multimedia. In the past, He has published 200+ papers at these areas and his research has received several awards, including IEEE Fellow (2021), ACM distinguished member (2020), ICDM Tao Li award (2019), SDM/IBM Early Career Data Mining Research award (2018), NSF CAREER award (2017), ICDM 10-Year Highest Impact Paper award (2015), and several best paper awards. (e.g., ICDM’06 best paper, SDM’08 best paper, CIKM’12 best paper, etc.). He was Editor-in-Chief of ACM SIGKDD Explorations (2018 – 2022).