題目：Trustworthy Recommender Systems: Algorithms and Solutions

　　報告人：Guandong Xu

　　時間：2025年04月17日(周四)，15：00-16：00

　　會議地點：31-904

　　報告摘要：

　　With the exponential growth of information, Recommender Systems (RecSys) have become pivotal tools in managing data overload. Similar to other AI applications, trustworthy issues, including data bais, explainability, and fairness, are widely observed in recommender systems, attracting a lot of research attention from both academia and industry. This talk will report our recent research progress in trustworthy recommender systems, from data debiasing and explainable recommendations to fairness assurance algorithms. Specifically, for the explainability of recommendations, we studied using meta-path, temporal modeling, counterfactual learning, causal inference and disentanglement learning approaches. For the fairness of recommendations, we studied selection bias in static scenarios, and bias problems in dynamic scenarios, and introduced a conformalized prediction framework. These research efforts have led to satisfactory results in recommendations, explainability, and fairness. They have also made meaningful theoretical innovations and experimental validations for building reliable and credible recommender systems in future.

　　報告人簡介：

　　Guandong Xu is a Chair Professor of Artificial Intelligence at the Education University of Hong Kong. Before joining EdUHK, he is a Professor at the School of Computer Science, University of Technology Sydney. His research interests cover Data Science, Recommender Systems, User Modelling, and Social Computing. He has published 220+ journal and conference papers, including TOIS, TKDD, TKDE, TNNLS, TCYB, TMM, VLDB, IJCAI, AAAI, SIGMOD, KDD, SIGIR, ICML, CVPR, NIPS, ACL and WWW conferences. He is the Editor-in-Chief of Human-centric Intelligent Systems and the assistant Editor-in-Chief of World Wide Web Journal. He has been serving on the editorial board or as a guest editor for several international journals, such as TOIS, TII, TCSS, PR etc. He has received several Awards from the academic and industry community. He is elevated as a Fellow of the Institute of Engineering and Technology (IET) and Australian Computer Society (ACS) in 2022 and 2021, respectively.