Committee

General Chairs
Yi Pan Shenzhen Institute of Advanced  Technology Chinese Academy  of Sciences, China	Xiaohua Hu Drexel University, USA
Conference Chairs
Shaoliang Peng Hunan University, China	Weiwei Liu Wuhan University, China
Program Chairs
Chi Man PUN University of Macau, China	Hebah H . O. Nasereddin Middle East University, Jordan	Xiaofeng Ding Huazhong University of Science  and Technology, China
Program Committee
L. M. Patnaik Indian Institute of Science, India	Massimo Marchiori University of Padua, Italy

Publication Chair

 Alfredo Cuzzocrea

 University of Calabria, Italy

Publicity Chair

 Xiuwen Gong

 The University of Sydney, Australia

WBDC 2023 Speakers

Keynote Speaker Ⅰ

Professor Axel-Cyrille Ngonga Ngomo

Paderborn University, Germany

Biography: Axel holds a Ph.D and habilitation in Computer Science from Leipzig University, Germany. He is currently a Full Professor for Data Science at Paderborn University, where he leads the DICE group. The group focuses on both foundational and applied research all along the lifecycle of knowledge graphs. Hence, it has developed a plethora of algorithms and platforms for knowledge extraction, integration, fusion, and application in intelligent systems. DICE’s research has attracted several international research prizes including best paper awards at top conferences such as ISWC and ESWC. Moreover, Axel is the grateful recipient of several prestigious fellowships for his research, including Northrhine Westphalia’s 2023 Lamarr Fellowship. In his talk, Axel will present some of his recent work on machine learning on knowledge graph with a focus on scalability and explainability. 

Speech Title: Scaling up hybrid learning on knowledge graphs 

Abstract: Knowledge graphs are an increasingly popular family of data structures for knowledge representation, of which some are endowed with explicit semantics. While learning on graphs is becoming increasingly more popular and scalable, learning on (semantically rich) knowledge graphs is significantly more difficult to achieve. In this talk, we will present recent results on achieving time-efficient and accurate learning on knowledge graphs. We will begin by giving a brief introduction to the class expression learning problem, a supervised learning task on knowledge graphs. We will build upon refinement operators and the corresponding learning principles to derive novel, increasingly more scalable approaches to learning on knowledge graphs while respecting their semantics. 

Invited Speaker Ⅰ

Associate Professor Hao Li

IEEE member

Xidian University, China

Biography: Hao Li is an Associate Professor at the School of Electronic Engineering, Xidian University. He received the B.Eng. degree in electronic engineering and the Ph.D. degree in pattern recognition and intelligent systems from Xidian University, Xi’an, China, in 2013 and 2018, respectively. His major research interests include computational intelligence, machine learning and remote sensing image understanding. He was a recipient of the Young Distinguished Talent in Shaanxi, China and the Young Talent of University Association for Science and Technology in Shaanxi, China. He received the Outstanding Doctoral Dissertation Award in Shaanxi, China and the Best Student Paper Award at the International Conference on CIS. He is an IEEE member and serves as a member of IEEE Neural Networks Technical Committee.