Timezone: »

 
Poster
Estimating and Penalizing Induced Preference Shifts in Recommender Systems
Micah Carroll · Anca Dragan · Stuart Russell · Dylan Hadfield-Menell

Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #923
in Poster Session 1 »

The content that a recommender system (RS) shows to users influences them. Therefore, when choosing a recommender to deploy, one is implicitly also choosing to induce specific internal states in users. Even more, systems trained via long-horizon optimization will have direct incentives to manipulate users, e.g. shift their preferences so they are easier to satisfy. We focus on induced preference shifts in users. We argue that – before deployment – system designers should: estimate the shifts a recommender would induce; evaluate whether such shifts would be undesirable; and perhaps even actively optimize to avoid problematic shifts. These steps involve two challenging ingredients: estimation requires anticipating how hypothetical policies would influence user preferences if deployed – we do this by using historical user interaction data to train a predictive user model which implicitly contains their preference dynamics;evaluation and optimization additionally require metrics to assess whether such influences are manipulative or otherwise unwanted – we use the notion of "safe shifts", that define a trust region within which behavior is safe: for instance, the natural way in which users would shift without interference from the system could be deemed "safe". In simulated experiments, we show that our learned preference dynamics model is effective in estimating user preferences and how they would respond to new recommenders. Additionally, we show that recommenders that optimize for staying in the trust region can avoid manipulative behaviors while still generating engagement.

Keywords: APP: Everything Else · SA: Everything Else · SA: Accountability, Transparency and Interpretability · SA: Fairness, Equity, Justice and Safety

Author Information

Micah Carroll (UC Berkeley)
Anca Dragan (University of California, Berkeley)
Stuart Russell (UC Berkeley)
Dylan Hadfield-Menell (Massachusetts Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors