题 目：Knowledge Graph Embedding for Recommender Systems
Knowledge graph (KG) is a large scale semantic network consisting of entities/concepts as well as the semantic relationships among them, which could be considered as a concise version of Semantic Web. Recently KG is emerging as a hot topic of knowledge discovery and management under artificial intelligence, facilitating semantic computing. Embedding is an effective way for dimensionality reduction and latent semantic representation, which is able to be applied in high dimensional space context such as network and graph. In this seminar, I am going to present our recent researches about combining KG and embedding for recommender systems, to address the inherent research challenges in recommender systems, such as cold-start and sparsity.
Dr Guandong Xu is a Professor at School of Computer Science, University of Technology Sydney and CUHK visiting Professor, specialising in Data Science, Data Analytics, Recommender Systems, Web Mining, Text mining and NLP, Social Network Analysis, and Social Media Mining. He has published three monographs, dozens of book chapters and edited conference proceedings, and 200+ journal and conference papers in decent journals and conferences. He leads Data Science and Machine Intelligence Lab at UTS. He is the assistant Editor-in-Chief of World Wide Web Journal and has been serving in editorial board or as guest editors for several international journals. He has received a number of Awards from academia and industry community, such as 2018 Top-10 Australian Analytics Leader Award.