Multistakeholder recommendation with provider constraints

Sürer, Özge; Burke, Robin; Malthouse, Edward C.

doi:10.1145/3240323.3240350

Cited by 50 publications

(45 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DRR [15] is a deep reinforcement learning framework designed for IRS to maximize the long-term reward; (vi) MRPC. Multi-sided Recommendation with Provider Constraints (MRPC) [21] is the state-of-the-art fairness-aware method by formulating the fairness problem as an integer programming. Table 1 shows the results.…”

Section: Results and Analysismentioning

confidence: 99%

“…The balanced neighborhoods method [4] formulates the fairness problem into balancing protected and unprotected groups by imposing a regularizer on the Sparse Linear Method (SLIM). The fairness constraint is formulated as an integer programming optimization in [25]. However, all the existing methods (i) only consider the distribution of the number of recommendations (exposure) an item group received.…”

Section: Fairness-aware Recommendationmentioning

confidence: 99%

“…Individual attention fairness is discussed in [3]. [25] models re-ranking with fairness constraints in Multi-sided Recommender Systems (MRS) as an integer linear programming. The balanced neighborhoods method [4] balances protected and unprotected groups by reformulating the Sparse LInear Method (SLIM) with a new regularizer.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Balancing Between Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning

Liu

Tang

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Fairness in recommendation has attracted increasing attention due to bias and discrimination possibly caused by traditional recommenders. In Interactive Recommender Systems (IRS), user preferences and the system's fairness status are constantly changing over time. Existing fairness-aware recommenders mainly consider fairness in static settings. Directly applying existing methods to IRS will result in poor recommendation. To resolve this problem, we propose a reinforcement learning based framework, FairRec, to dynamically maintain a longterm balance between accuracy and fairness in IRS. User preferences and the system's fairness status are jointly compressed into the state representation to generate recommendations. FairRec aims at maximizing our designed cumulative reward that combines accuracy and fairness. Extensive experiments validate that FairRec can improve fairness, while preserving good recommendation quality.

show abstract

Section: Results and Analysismentioning

confidence: 99%

Section: Fairness-aware Recommendationmentioning

confidence: 99%

See 1 more Smart Citation

Balancing Between Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning

Liu

Tang

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…Few recent works have also explored fairness for both producers and customers. For example, (Abdollahpouri and Burke 2019;Burke 2017) categorized different types of multi-stakeholder platforms and their desired fairness properties, (Sühr et al 2019) presented a mechanism for twosided fairness in matching problems, (Sürer, Burke, and Malthouse 2018) used minimum guarantee constraints for producers and diversity constraints for customers while recommending. However, these works have assumed that the underlying customer-item relevance model remains unchanged, whereas in reality, the algorithms go through frequent updates.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Several recent studies have shown how sole focus on the customers may adversely affect the well-being of the producers, as more and more people are depending on twosided platforms to earn a living (Edelman, Luca, and Svirsky 2017;Hannák et al 2017;Abdollahpouri and Burke 2019;Chakraborty et al 2017;Burke 2017;Graham, Hjorth, and Lehdonvirta 2017). Subsequently, few research works have attempted to reduce unfairness in these platforms (Sühr et al 2019;Sürer, Burke, and Malthouse 2018;Geyik, Ambler, and Kenthapadi 2019). However, existing works have overlooked an important issue.…”

mentioning

confidence: 99%

Incremental Fairness in Two-Sided Market Platforms: On Smoothly Updating Recommendations

Patro

Chakraborty

Ganguly

et al. 2020

AAAI

View full text Add to dashboard Cite

Major online platforms today can be thought of as two-sided markets with producers and customers of goods and services. There have been concerns that over-emphasis on customer satisfaction by the platforms may affect the well-being of the producers. To counter such issues, few recent works have attempted to incorporate fairness for the producers. However, these studies have overlooked an important issue in such platforms -- to supposedly improve customer utility, the underlying algorithms are frequently updated, causing abrupt changes in the exposure of producers. In this work, we focus on the fairness issues arising out of such frequent updates, and argue for incremental updates of the platform algorithms so that the producers have enough time to adjust (both logistically and mentally) to the change. However, naive incremental updates may become unfair to the customers. Thus focusing on recommendations deployed on two-sided platforms, we formulate an ILP based online optimization to deploy changes incrementally in η steps, where we can ensure smooth transition of the exposure of items while guaranteeing a minimum utility for every customer. Evaluations over multiple real world datasets show that our proposed mechanism for platform updates can be efficient and fair to both the producers and the customers in two-sided platforms.

show abstract

The multisided complexity of fairness in recommender systems

et al. 2022

Self Cite

View full text Add to dashboard Cite

Recommender systems are poised at the interface between stakeholders: for example, job applicants and employers in the case of recommendations of employment listings, or artists and listeners in the case of music recommendation. In such multisided platforms, recommender systems play a key role in enabling discovery of products and information at large scales. However, as they have become more and more pervasive in society, the equitable distribution of their benefits and harms have been increasingly under scrutiny, as is the case with machine learning generally. While recommender systems can exhibit many of the biases encountered in other machine learning settings, the intersection of personalization and multisidedness makes the question of fairness in recommender systems manifest itself quite differently. In this article, we discuss recent work in the area of multisided fairness in recommendation, starting with a brief introduction to core ideas in algorithmic fairness and multistakeholder recommendation. We describe techniques for measuring fairness and algorithmic approaches for enhancing fairness in recommendation outputs. We also discuss feedback and popularity effects that can lead to unfair recommendation outcomes. Finally, we introduce several promising directions for future research in this area.

show abstract

Multistakeholder recommendation with provider constraints

Cited by 50 publications

References 8 publications

Balancing Between Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning

Balancing Between Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning

Incremental Fairness in Two-Sided Market Platforms: On Smoothly Updating Recommendations

The multisided complexity of fairness in recommender systems

Contact Info

Product

Resources

About