报告题目: Causality-inspired Recommendation: Robustness, Transparency and Fairness

时间：2023年12月4日下午3:00

地点：B7-303

报告人：Professor Guandong Xu

主持人：蔡毅教授

Abstract:

Recommendation System (RS) as an information filtering tool to alleviate the information explosion has gained prominence in academia and industry. Trustworthy recommender system studies how to assure robustness, transparency and fairness in RS, which directly impact user satisfaction, recommendation persuasiveness and stakeholder interest. In this talk, we will discuss the challenges of conventional RS and show how causality can fulfill the trustworthy RS by using causal inference approaches. We will provide our explorations in causality-inspired recommendations and discuss our major findings. Specifically, we will discuss recommendation robustness facing low-quality data bias scenarios, show how causality-based explanations can enhance recommendation explainability and build fairness-aware recommendation algorithms. We finally highlight some future directions and open questions.

Guandong Xu is a Full Professor in Data Science at School of Computer Science and Advanced Analytics Institute, University of Technology Sydney with PhD degree in Computer Science. His research interests cover Data Science, Recommender Systems, and Social Computing. He has published three monographs in Springer and CRC press, and 220+ journal and conference papers. He is the Editor-in-Chief of Human-centric Intelligent Systems and the assistant Editor-in-Chief of World Wide Web Journal by Springer Nature, and serving in editorial board or guest editors for several international journals. He is a Fellow of Institute of Engineering and Technology (IET) and of Australian Computer Society (ACS).