CS Events Monthly View

Qualifying Exam User-oriented Fairness in Recommendations
× Export Event Save iCal Send to Google Calendar Send to Yahoo Calendar Send to Outlook Live Send to Microsoft Outlook Save iCal Preserve formatting in description (only supported in some calendar applications) Close Friday, April 23, 2021, 02:30pm - 04:00pm

Speaker: Yunqi Li

Location : Remote via Zoom

Committee: 

Prof. Yongfeng Zhang (Advisor) 

Prof. Desheng Zhang 

Prof. Hao Wang 

Prof. Shiqing Ma 

Event Type: Qualifying Exam

Abstract: Recommender systems are gaining increasing and critical impacts on human and society since a growing number of users use them for information seeking and decision making. Therefore, it is crucial to address the potential unfairness problems in recommendations. We study unfairness problems in recommendations from user perspective. First, we conduct experiments to show that current recommender systems will behave unfairly between groups of users with different activity level. Specifically, the active users who only account for a small proportion in data enjoy much higher recommendation quality than those inactive users. Such bias can also affect the overall performance since the inactive users are the majority. To solve this problem, we provide a re-ranking approach to mitigate this unfairness problem by adding constraints over evaluation metrics. Furthermore, considering users' demands for fairness are personalized in many scenarios, we consider achieving personalized fair recommendations for users to satisfy their personalized fairness requirements through adversary learning.

: 

Link: https://rutgers.zoom.us/j/7352843633?pwd=amxuOFVEREF2S2xKeXJhUEJ5RGpvdz09

Meeting number: 735 284 3633
Password: 04232021