The multisided complexity of fairness in recommender systems

@article{Sonboli2022TheMC,
  title={The multisided complexity of fairness in recommender systems},
  author={Nasim Sonboli and Robin D. Burke and Michael D. Ekstrand and Rishabh Mehrotra},
  journal={AI Magazine},
  year={2022}
}
Measuring Commonality in Recommendation of Cultural Content: Recommender Systems to Enhance Cultural Citizenship
TLDR
This work introduces commonality as a new measure of recommender systems that reflects the degree to which recommendations famil-iarize a given user population with specified categories of cultural content and empirically compares the performance of recommendation algorithms with existing utility, diversity, novelty, and fairness metrics.

References

SHOWING 1-10 OF 43 REFERENCES
Fairness and Transparency in Recommendation: The Users’ Perspective
TLDR
An exploratory interview study that investigates user perceptions of fairness, recommender systems, and fairness-aware objectives is described and three features are proposed – informed by the needs of the authors' participants – that could improve user understanding of and trust in Fairness-aware recommender Systems.
Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems
TLDR
This paper provides theory for a set of conditions under which fairness of individual models does compose, and presents an analytical framework for both understanding whether a real system's signals can achieve compositional fairness, and improving which component would have the greatest impact on the fairness of the overall system.
Shifting Consumption towards Diverse Content on Music Streaming Platforms
TLDR
This work views diversity as an enabler for shifting consumption and considers two notions of music diversity, based on taste similarity and popularity, and finds that the reward modeling based RL approach achieves the best trade-off between optimizing the satisfaction metric and surfing diverse content, thereby enabling consumption shifting at scale.
Break the Loop: Gender Imbalance in Music Recommenders
TLDR
This work analyzes a widely-used collaborative filtering approach with two public datasets-enriched with gender information-to understand how this approach performs with respect to the artists' gender and proposes a progressive re-ranking method based on the insights from the interviews.
I agree with the decision, but they didn't deserve this: Future Developers' Perception of Fairness in Algorithmic Decisions
TLDR
Quantitative analysis indicates that 'agreeing' with a decision does not mean the person 'deserves the outcome', and perceiving the factors used in the decision-making as 'appropriate' does not make the decision of the system 'fair' and c) perceiving a system's decision as 'not fair' is affecting the participants' 'trust' in the system.
Algorithmic Fairness: Choices, Assumptions, and Definitions
TLDR
It is shown how choices and assumptions made—often implicitly—to justify the use of prediction-based decision-making can raise fairness concerns and a notationally consistent catalog of fairness definitions from the literature is presented.
Bandit based Optimization of Multiple Objectives on a Music Streaming Platform
TLDR
This paper proposes an online gradient ascent learning algorithm to maximise the long-term vectorial rewards for different objectives scalarised using the GGI function and shows that the proposed algorithm learns a superior policy among the disparate objectives compared with other state-of-the-art approaches.
Opportunistic Multi-aspect Fairness through Personalized Re-ranking
TLDR
It is shown that the opportunistic and metric-agnostic approach achieves a better trade-off between accuracy and fairness than prior re-ranking approaches and does so across multiple fairness dimensions.
FairMatch: A Graph-based Approach for Improving Aggregate Diversity in Recommender Systems
TLDR
FairMatch is introduced, a general graph-based algorithm that works as a post-processing approach after recommendation generation for improving aggregate diversity and fair distribution of recommended items and can be adapted to other recommendation scenarios using different underlying definitions of fairness.
FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms
TLDR
The proposed FairRec algorithm guarantees at least Maximin Share of exposure for most of the producers and Envy-Free up to One Good fairness for every customer and extensive evaluations show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in the overall recommendation quality.
...
...