User Manipulation in Recommender Systems
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact James Allingham.
Zoom link available upon request (it is sent out on our mailing list, eng-mlg-rcc [at] lists.cam.ac.uk). Sign up to our mailing list for easier reminders via lists.cam.ac.uk.
Many recommender systems of today have switched to optimize long-term engagement metrics via approaches such as Reinforcement Learning. It has been shown theoretically that this will lead recommender systems to have incentives to manipulate users’ internal states (beliefs, preferences, or moods), in ways that lead to increases in the systems’ optimization metrics. But are recommendations sufficient to manipulate users? And equally importantly, will these incentives manipulation incentives be acted upon by real systems? In this talk I’ll give an overview of the research that has already been conducted in this area, and the open research questions which I’m currently investigating.
Recommended reading: None
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|