Popularity Bias in Dynamic Recommendation

Popularity bias is a long-standing challenge in recommender systems: popular items are overly recommended at the expense of less popular items that users may be interested in being under-recommended. Such a bias exerts detrimental impact on both users and item providers, and many efforts have been dedicated to studying and solving such a bias. However, most existing works situate the popularity bias in a static setting, where the bias is analyzed only for a single round of recommendation with logged data. These works fail to take account of the dynamic nature of real-world recommendation process, leaving several important research questions unanswered: how does the popularity bias evolve in a dynamic scenario? what are the impacts of unique factors in a dynamic recommendation process on the bias? and how to debias in this long-term dynamic process? In this work, we investigate the popularity bias in dynamic recommendation and aim to tackle these research gaps. Concretely, we conduct an empirical study by simulation experiments to analyze popularity bias in the dynamic scenario and propose a dynamic debiasing strategy and a novel False Positive Correction method utilizing false positive signals to debias, which show effective performance in extensive experiments.

[1]  Yuta Saito,et al.  Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback , 2020, WSDM.

[2]  Bamshad Mobasher,et al.  Controlling Popularity Bias in Learning-to-Rank Recommendation , 2017, RecSys.

[3]  M. C. Brown,et al.  Using Gini-style indices to evaluate the spatial patterns of health practitioners: theoretical considerations and an application based on Alberta data. , 1994, Social Science & Medicine (1967).

[4]  Huan Liu,et al.  mTrust: discerning multi-faceted trust in a connected world , 2012, WSDM '12.

[5]  Guy Aridor,et al.  Deconstructing the Filter Bubble: User Decision-Making and Recommender Systems , 2019, RecSys.

[6]  Olfa Nasraoui,et al.  Theoretical Modeling of the Iterative Properties of User Discovery in a Collaborative Filtering Recommender System , 2020, RecSys.

[7]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[8]  Bamshad Mobasher,et al.  Managing Popularity Bias in Recommender Systems with Personalized Re-ranking , 2019, FLAIRS.

[9]  David M. Blei,et al.  Causal Inference for Recommendation , 2016 .

[10]  Barbara E. Engelhardt,et al.  How algorithmic confounding in recommendation systems increases homogeneity and decreases utility , 2017, RecSys.

[11]  Tor Lattimore,et al.  Degenerate Feedback Loops in Recommender Systems , 2019, AIES.

[12]  Blake Lemoine,et al.  Mitigating Unwanted Biases with Adversarial Learning , 2018, AIES.

[13]  Alexander Tuzhilin,et al.  The long tail of recommender systems and how to leverage it , 2008, RecSys '08.

[14]  Thorsten Joachims,et al.  Unbiased Learning-to-Rank with Biased Feedback , 2016, WSDM.

[15]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[16]  Wei Niu,et al.  Neural Personalized Ranking for Image Recommendation , 2018, WSDM.

[17]  Tat-Seng Chua,et al.  Neural Graph Collaborative Filtering , 2019, SIGIR.

[18]  Harald Steck.  Collaborative Filtering via High-Dimensional Regression , 2019, ArXiv.

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[21]  Thorsten Joachims,et al.  Controlling Fairness and Bias in Dynamic Learning-to-Rank , 2020, SIGIR.

[22]  Jinfeng Yi,et al.  Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System , 2020, KDD.

[23]  A. Wagstaff,et al.  On the measurement of inequalities in health. , 1991, Social science & medicine.

[24]  Olfa Nasraoui,et al.  Debiasing the Human-Recommender System Feedback Loop in Collaborative Filtering , 2019, WWW.

[25]  Unbiased Learning-to-Rank with Biased Feedback , 2018, IJCAI.

[26]  James Caverlee,et al.  Popularity-Opportunity Bias in Collaborative Filtering , 2021, WSDM.

[27]  Harald Steck,et al.  Item popularity and recommendation accuracy , 2011, RecSys '11.

[28]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[29]  Jun Wang,et al.  Interactive collaborative filtering , 2013, CIKM.

[30]  Karthik Ramani,et al.  Deconvolving Feedback Loops in Recommender Systems , 2016, NIPS.

[31]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[32]  Deborah Estrin,et al.  Unbiased offline recommender evaluation for missing-not-at-random implicit feedback , 2018, RecSys.

[33]  Robin Burke,et al.  The Unfairness of Popularity Bias in Recommendation , 2019, RMSE@RecSys.