Heterogeneous graphs, also called heterogeneous information networks, are graphs composed of different types of entities and relationships. Heterogeneous graphs are a basic tool for modeling complex interactive systems. They are also a widely existing data form and have formed unique analysis methods. Heterogeneous graph analysis has become a research hotspot in the field of data mining and is widely used in industry. This talk systematically introduces the concepts, models, applications and platforms of heterogeneous graphs. In addition, this talk will also briefly discuss the impact of large language models on graph computing and point out the promising solution: graph foundation model.

Chuan Shi is the professor in School of Computer Sciences of Beijing University of Posts and Telecommunications, and he was appointed as a Changjiang Scholar Distinguished Professor by the Ministry of Education. The main research interests include data mining, machine learning, artificial intelligence and big data analysis. In the past 5 years, he has published over 100 papers in top journals and conferences, as well as four English monographs. In addition, he has been authorized more than 30 invention patents, and his researches have been applied to companies such as Alibaba, Tencent, Huawei, and Meituan. Moreover, he also won several awards, such as the first prize of science and technology progress of the Chinese Institute of Electronics (1st) and the second prize of Natural Science of Beijing/CCF (1st).