Filter Bubble in Recommender System: Diversity and Beyond

The Data Science Discipline of the School of EECS is hosting the following guest seminar:

Filter Bubble in Recommender System: Diversity and Beyond

Speaker: Prof Chen Gao (Tsinghua University)
Host: Dr Ruihong Qiu

Abstract: Recommender system has reshaped how we access information in today’s world, make relevant content more accessible to everyone. However, it has also resulted in some negative side-effects, such as the filter bubble. The filter bubble refers to the phenomenon that the content the user is exposed to becomes more and more homogeneous and limited, causing increased bias and polarization. In this talk, we first discuss one of the most important aspects of the filter bubble, recommendation diversity, particularly diversified recommendation models and full-stage large-scale online experiments on short-video platforms. Then, we will present the quantitative analysis of the filter bubble on one of the largest short-video platforms, introducing a novel concept: deep filter bubble. Last, we will present a general and easy-to-use framework of controllable recommender system to break out of the filter bubble.

Speaker Bio: Chen Gao is now a Research Assistant Professor of BNRist, Tsinghua University. He obtained his Ph.D. Degree and Bachelor’s Degree from the Department of Electronic Engineering, Tsinghua University in 2021 and 2016, respectively. His research primarily focuses on data mining and information retrieval, with over 60 papers in top-tier venues (50+ CCF-A), including SIGIR, WWW, KDD, TKDE, TOIS, ICDE, ICLR, NeurIPS, MM, UbiComp, CSCW, NDSS, etc., attracting over 2500 citations. His work on GNN-based bundle recommendation received the Best Short Paper Honorable Mention Award in SIGIR 2020. He serves as the PC member for conferences such as WWW, KDD, SIGIR, WSDM, CIKM, NeurIPS, ICLR, ICML, MM, RecSys, AAAI, IJCAI, AISTATS, ECML-PKDD, etc., and the regular reviewer for journals including IEEE TKDE, ACM TOIS, etc. He was selected as one of Top 100 Chinese Rising Stars in Artificial Intelligence by Baidu Scholar in 2021. He was also at the finalist of 2021 China Computer Federation (CCF) Outstanding Doctoral Dissertation Award. He has also organized multiple tutorials in top-tier conferences including WWW, KDD, WSDM, IJCAI, etc.