Multisided Fairness for Recommendation.
Citations
286 citations
Cites background from "Multisided Fairness for Recommendat..."
...user attributes, the concept of fairness has been generalized to multiple dimensions in recommender systems [178], spanning from fairness-aware ranking [114], [115], [116], supplier fairness in two-sided marketplace platforms [179], provider-side fairness to make items from different providers have a fair chance of being recommended [108], [180], fairness in group recommendation to minimize the unfairness between group members [129]....
[...]
240 citations
236 citations
Cites background from "Multisided Fairness for Recommendat..."
...The concept of multiple stakeholders in recommender systems is also suggested in prior research [1], including a previous attempt on considering multi-sided fairness in marketplaces [5]....
[...]
[...]
189 citations
Cites background from "Multisided Fairness for Recommendat..."
...[26] notes that many recommender system applications involve multiple stakeholders and may therefore give rise to fairness issues for more than one group of participants simultaneously, as well as achieving fairness at a regulatory level or the level of the entire system (referred to as multisided fairness)....
[...]
...Moreover, note that an individual definition of P-fairness, rather than group-fairness, may be somewhat similar to the definition of coverage in recommender systems, requiring that each item be recommended fairly [26]....
[...]
...A recent paper, [26], notes that extending the notion of fairness from general classification tasks to recommender systems should take personalization into account....
[...]
173 citations
References
2,027 citations
"Multisided Fairness for Recommendat..." refers background in this paper
...In the motivating example from [6], a credit card company is recommending consumer credit o ers....
[...]
...group fairness in fairness-aware classi cation [6]....
[...]
...Bias and fairness in machine learning are topics of considerable recent research interest [4, 6, 17]....
[...]
2,003 citations
1,444 citations
"Multisided Fairness for Recommendat..." refers background in this paper
...One intriguing possibility is to design a recommender system following the approach of [23] in generating fair classi cation....
[...]
1,406 citations
1,094 citations
"Multisided Fairness for Recommendat..." refers background in this paper
...The dominant recommendation paradigm, collaborative ltering [13], uses user behavior as its input, ignoring user demographics and item attributes....
[...]