Equity of Attention: Amortizing Individual Fairness in Rankings

By Asia J. Biega, Krishna P. Gummadi, Gerhard Weikum. 2018

559 citations recorded by the source corpus.

Rankings of people and items are at the heart of selection-making, match-making, and recommender systems, ranging from employment sites to sharing economy platforms. As ranking positions influence the amount of attention the ranked subjects receive, biases in rankings can lead to unfair distribution of opportunities and resources such as jobs or income. This paper proposes new measures and mechanisms to quantify and mitigate unfairness from a bias inherent to all rankings, namely, the position bias which leads to disproportionately less attention being paid to low-ranked subjects. Our approach differs from recent fair ranking approaches in two important ways. First, existing works measure unfairness at the level of subject groups while our measures capture unfairness at the level of individual subjects, and as such subsume group unfairness. Second, as no single ranking can achieve individual attention fairness, we propose a novel mechanism that achieves amortized fairness, where attention accumulated across a series of rankings is proportional to accumulated relevance. We formulate the challenge of achieving amortized individual fairness subject to constraints on ranking quality as an online optimization problem and show that it can be solved as an integer linear program. Our experimental evaluation reveals that unfair attention distribution in rankings can be substantial, and demonstrates that our method can improve individual fairness while retaining high ranking quality.

Subfields: Computer Science Applications, Safety Research, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Science Applications

In Safety Research

In Sociology and Political Science

Citations in the corpus

Investigating Societal Biases in a Poetry Composition System (2020, background): “More recently, researchers have proposed different metrics to measure the amount of group and individual fairness in ranking systems (Zehlike et al., 2017; Biega et al., 2018; Singh and Joachims, 2018; Yang et al., 2020).”
Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search (2019, methodology): “ choices in practice (see §4.3). The problem of achieving individual equity-of-attention fairness in rankings, along with a mechanism for achieving amortized individual fairness, has been proposed in [7]. While this work aims to achieve individual fairness amortized across many rankings, our focus i”
Fairness of Exposure in Rankings (2018, methodology): “For example, in the case of Disparate Treatment, we could express individual fairness as a set of N − 1 constraints over N groups of size one, resulting in a notion of fairness similar to [3].”
Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommendation Systems (2018, background): “Recent work has explored the development of classification models with fairness-aware regularization [30], fairness aware decision making systems [9], prediction models for individual fairness [6], fair division of resources [2], auditing for fairness [17] and fairness in rankings [4, 25].”
Overcoming Failures of Imagination in AI Infused System Development and Deployment (2020, background): “For instance, while restricted access to some critical service for some stakeholders (Abbasi et al., 2019) affects them directly, the exposure or representation of stakeholders (Biega et al., 2018; Singh and Joachims, 2018) may also affect those creating or consuming the content.”
Bias and Debias in Recommender System: A Survey and Future Directions (2020, background): “Towards individual equityto-attention fairness in rankings, previous work [115], [116] propose multiple ranking functions to sort items and then achieve fairness amortized across these rankings.”
User-oriented Fairness in Recommendation (2021, background): “[8] capture unfairness at the level of individual subjects, as such subsume group unfairness.”
Fairness in Recommendation Ranking through Pairwise Comparisons (2019, methodology): “In contract, [52, 44, 45, 11] explore what is a fair ranking, but focus on unpersonalized rankings where relevancy is known for all items”
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach (2020, background): “Research that considers fairness w.r.t. content providers (rather than users), fairly allocating the exposure of providers to users (Singh & Joachims, 2018; Biega et al., 2018), is closely related to our work, especially in some aspects of its motivation.”
A Review on Fairness in Machine Learning (2022, background): “Several studies explore the notion of fair exposure of items in ranking based on their merit [25, 87, 189] (e.”
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting (2019, background): “Finally, although our paper does not directly consider ranking scenarios, fairness in ranking is particularly relevant to discussions about gender bias in online recruiting and automated hiring [7, 14, 22, 40, 42].”
A Survey of Model Architectures in Information Retrieval (2025, unknown): “…Ai et al., 2018c,b; Wang et al., 2018; Hu et al., 2019; Ren et al., 2022) while other focus on jointly optimizing effectiveness and fairness of the ranking systems (Singh and Joachims, 2018; Biega et al., 2018; Morik et al., 2020; Patro et al., 2020; Oosterhuis, 2021; Yang et al., 2023a,c,b).”