The Unfairness of Popularity Bias in Recommendation

Abdollahpouri, Himan; Mansoury, Masoud; Burke, Robin; Mobasher, Bamshad

doi:10.48550/arxiv.1907.13286

Cited by 36 publications

(84 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a typical data-driven system, recommender systems could be biased by data and the algorithm, arousing increasing concerns on the fairness [4,86,108]. Specifically, according to the involved stakeholders, fairness in recommender systems can be divided into two categories [4,86,108]: user fairness, which attempts to ensure no algorithmic bias among specific users or demographic groups [9,78,84], and item fairness, which indicates fair exposures of different items, or no popularity bias among different items [2,3,86,108]. Here, we focus on the user fairness, and leave item fairness in the section of diversity for their close connection in terms of interpretations and solutions [2,105].…”

Section: Low Highmentioning

confidence: 99%

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Chen¹,

Zheng²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach of recommender systems. In this survey, we conduct a comprehensive review of the literature in graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data, and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions of this area. We summarize the representative papers along with their codes repositories in https://github.com/tsinghua-fib-lab/GNN-Recommender-Systems.

show abstract

Section: Low Highmentioning

confidence: 99%

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Chen¹,

Zheng²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It has been discovered and reported that various types of bias could exist in recommender systems, such as those with respect to user demographics (gender, age, and race, etc.) [27,88,99], user activeness [23], and item popularity [1][2][3]94]. Hence, many different metrics of fairness [8] have been proposed in order to build fairnessaware recommender systems.…”

Section: Static Recommendation Fairnessmentioning

confidence: 99%

Recommendation Fairness: From Static to Dynamic

Zhang¹,

Wang²

2021

Preprint

View full text Add to dashboard Cite

Driven by the need to capture users' evolving interests and optimize their long-term experiences, more and more recommender systems have started to model recommendation as a Markov decision process and employ reinforcement learning to address the problem. Shouldn't research on the fairness of recommender systems follow the same trend from static evaluation and one-shot intervention to dynamic monitoring and non-stop control? In this paper, we portray the recent developments in recommender systems first and then discuss how fairness could be baked into the reinforcement learning techniques for recommendation. Moreover, we argue that in order to make further progress in recommendation fairness, we may want to consider multi-agent (game-theoretic) optimization, multi-objective (Pareto) optimization, and simulationbased optimization, in the general framework of stochastic games. CCS CONCEPTS• Information systems → Recommender systems; • Computing methodologies → Reinforcement learning.

show abstract

“…We now present our inference algorithm for (1). Appendix E contains the proofs of this section and describes a similar approach for the objective functions of the previous section.…”

Section: Efficient Inference Of Fair Rankings With the Frank-wolfe Al...mentioning

confidence: 99%

“…The question of fairness in rankings originated from independent audits on recommender systems or search engines, which showed that results could exhibit bias against relevant social groups [57,33,21,40,35] Our work follows the subsequent work on ranking algorithms that promote fairness of exposure for individual or sensitive groups of items [10,8,7,54,42,65]. The goal is often to prevent winner-take-all effects, combat popularity bias [1] or promote smaller producers [39,41]. Section 3 is devoted to the comparison with this type of approaches.…”

Section: Related Workmentioning

confidence: 99%

“…It involves a complex multidimensional trade-off. Fairness towards item producers requires boosting the exposure of small producers (e.g., to avoid winner-take-all effects and popularity biases [1]) at the expense of average user utility. Fairness towards users aims at increasing the utility of the least served users (e.g., so that least served users do not support the cost of item-side fairness), once again at the expense of average user utility.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Two-sided fairness in rankings via Lorenz dominance

Do¹,

Corbett-Davies²,

Atif³

et al. 2021

Preprint

View full text Add to dashboard Cite

We consider the problem of generating rankings that are fair towards both users and item producers in recommender systems. We address both usual recommendation (e.g., of music or movies) and reciprocal recommendation (e.g., dating). Following concepts of distributive justice in welfare economics, our notion of fairness aims at increasing the utility of the worse-off individuals, which we formalize using the criterion of Lorenz efficiency. It guarantees that rankings are Pareto efficient, and that they maximally redistribute utility from better-off to worse-off, at a given level of overall utility. We propose to generate rankings by maximizing concave welfare functions, and develop an efficient inference procedure based on the Frank-Wolfe algorithm. We prove that unlike existing approaches based on fairness constraints, our approach always produces fair rankings. Our experiments also show that it increases the utility of the worse-off at lower costs in terms of overall utility.35th Conference on Neural Information Processing Systems (NeurIPS 2021).

show abstract

The Unfairness of Popularity Bias in Recommendation

Cited by 36 publications

References 0 publications

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Recommendation Fairness: From Static to Dynamic

Two-sided fairness in rankings via Lorenz dominance

Contact Info

Product

Resources

About