Estimating and Penalizing Induced Preference Shifts in Recommender Systems

• URL: http://arxiv.org/abs/2204.11966v1
• Date: Mon, 25 Apr 2022 21:04:46 GMT
• Title: Estimating and Penalizing Induced Preference Shifts in Recommender Systems
• Authors: Micah Carroll, Dylan Hadfield-Menell, Stuart Russell, Anca Dragan
• Abstract summary: We argue that system designers should: estimate the shifts a recommender would induce; evaluate whether such shifts would be undesirable; and even actively optimize to avoid problematic shifts. We do this by using historical user interaction data to train predictive user model which implicitly contains their preference dynamics. 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.
• Score: 10.052697877248601
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The content that a recommender system (RS) shows to users influences them. Therefore, when choosing which 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. In this work 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 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 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. 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.

Related papers

• Preference Diffusion for Recommendation [50.8692409346126]
  We propose PreferDiff, a tailored optimization objective for DM-based recommenders. PreferDiff transforms BPR into a log-likelihood ranking objective to better capture user preferences. It is the first personalized ranking loss designed specifically for DM-based recommenders.
  arXiv  Detail & Related papers  (2024-10-17T01:02:04Z)
• Algorithmic Drift: A Simulation Framework to Study the Effects of Recommender Systems on User Preferences [7.552217586057245]
  We propose a simulation framework that mimics user-recommender system interactions in a long-term scenario. We introduce two novel metrics for quantifying the algorithm's impact on user preferences, specifically in terms of drift over time.
  arXiv  Detail & Related papers  (2024-09-24T21:54:22Z)
• Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content [66.71102704873185]
  We test for user strategization by conducting a lab experiment and survey. We find strong evidence of strategization across outcome metrics, including participants' dwell time and use of "likes" Our findings suggest that platforms cannot ignore the effect of their algorithms on user behavior.
  arXiv  Detail & Related papers  (2024-05-09T07:36:08Z)
• Influential Recommender System [12.765277278599541]
  We present Influential Recommender System (IRS), a new recommendation paradigm that aims to proactively lead a user to like a given objective item. IRS progressively recommends to the user a sequence of carefully selected items (called an influence path) We show that IRN significantly outperforms the baseline recommenders and demonstrates its capability of influencing users' interests.
  arXiv  Detail & Related papers  (2022-11-18T03:04:45Z)
• Latent User Intent Modeling for Sequential Recommenders [92.66888409973495]
  Sequential recommender models learn to predict the next items a user is likely to interact with based on his/her interaction history on the platform. Most sequential recommenders however lack a higher-level understanding of user intents, which often drive user behaviors online. Intent modeling is thus critical for understanding users and optimizing long-term user experience.
  arXiv  Detail & Related papers  (2022-11-17T19:00:24Z)
• Recommendation with User Active Disclosing Willingness [20.306413327597603]
  We study a novel recommendation paradigm, where the users are allowed to indicate their "willingness" on disclosing different behaviors. We conduct extensive experiments to demonstrate the effectiveness of our model on balancing the recommendation quality and user disclosing willingness.
  arXiv  Detail & Related papers  (2022-10-25T04:43:40Z)
• Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction [97.99938802797377]
  Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in recommender systems. Recent deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. We propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper.
  arXiv  Detail & Related papers  (2022-06-28T03:28:15Z)
• Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation [133.8758914874593]
  Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time. Many existing recommendation algorithms -- including both shallow and deep ones -- often model such dynamics independently. This paper considers the problem of embedding a user's sequential behavior into the latent space of user preferences.
  arXiv  Detail & Related papers  (2022-04-02T03:23:46Z)
• Control Variates for Slate Off-Policy Evaluation [112.35528337130118]
  We study the problem of off-policy evaluation from batched contextual bandit data with multidimensional actions. We obtain new estimators with risk improvement guarantees over both the PI and self-normalized PI estimators.
  arXiv  Detail & Related papers  (2021-06-15T06:59:53Z)
• Measuring Recommender System Effects with Simulated Users [19.09065424910035]
  Popularity bias and filter bubbles are two of the most well-studied recommender system biases. We offer a simulation framework for measuring the impact of a recommender system under different types of user behavior.
  arXiv  Detail & Related papers  (2021-01-12T14:51:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.