In social choice, traditional Kemeny rank aggregation combines the preferences of voters, expressed as rankings, into a single consensus ranking without consideration for how this ranking may unfairly affect marginalized groups (i.e., racial or gender). Developing fair rank aggregation methods is critical due to their societal influence in applications prioritizing job applicants, funding proposals, and scheduling medical patients. In this work, we introduce the Fair Exposure Kemeny Aggregation Problem (FairExp-kap) for combining vast and diverse voter preferences into a single ranking that is not only a suitable consensus, but ensures opportunities are not withheld from marginalized groups. In formalizing FairExp-kap, we extend the fairness of exposure notion from information retrieval to the rank aggregation context and present a complimentary metric for voter preference representation. We design algorithms for solving FairExp-kap that explicitly account for position bias, a common ranking-based concern that end-users pay more attention to higher ranked candidates. epik solves FairExp-kap exactly by incorporating non-pairwise fairness of exposure into the pairwise Kemeny optimization; while the approximate epira is a candidate swapping algorithm, that guarantees ranked candidate fairness. Utilizing comprehensive synthetic simulations and six real-world datasets, we show the efficacy of our approach illustrating that we succeed in mitigating disparate group exposure unfairness in consensus rankings, while maximally representing voter preferences.
Algorithmic decision-making using rankings— prevalent in areas from hiring and bail to university admissions— raises concerns of potential bias. In this paper, we explore the alignment between people’s perceptions of fairness and two popular fairness metrics designed for rankings. In a crowdsourced experiment with 480 participants, people rated the perceived fairness of a hypothetical scholarship distribution scenario. Results suggest a strong inclination towards relying on explicit score values. There is also evidence of people’s preference for one fairness metric, NDKL, over the other metric, ARP. Qualitative results paint a more complex picture: some participants endorse meritocratic award schemes and express concerns about fairness metrics being used to modify rankings; while other participants acknowledge socio-economic factors in score-based rankings as justification for adjusting rankings. In summary, we find that operationalizing algorithmic fairness in practice is a balancing act between mitigating harms towards marginalized groups and societal conventions of leveraging traditional performance scores such as grades in decision-making contexts.
For applications where multiple stakeholders provide recommendations, a fair consensus ranking must not only ensure that the preferences of rankers are well represented, but must also mitigate disadvantages among socio-demographic groups in the final result. However, there is little empirical guidance on the value or challenges of visualizing and integrating fairness metrics and algorithms into human-in-the-loop systems to aid decision-makers. In this work, we design a study to analyze the effectiveness of integrating such fairness metrics-based visualization and algorithms. We explore this through a task-based crowdsourced experiment comparing an interactive visualization system for constructing consensus rankings, ConsensusFuse, with a similar system that includes visual encodings of fairness metrics and fair-rank generation algorithms, FairFuse. We analyze the measure of fairness, agreement of rankers’ decisions, and user interactions in constructing the fair consensus ranking across these two systems. In our study with 200 participants, results suggest that providing these fairness-oriented support features nudges users to align their decision with the fairness metrics while minimizing the tedious process of manually having to amend the consensus ranking. We discuss the implications of these results for the design of next-generation fairness oriented-systems and along with emerging directions for future research.
Preference aggregation mechanisms help decision-makers combine diverse preference rankings produced by multiple voters into a single consensus ranking. Prior work has developed methods for aggregating multiple rankings into a fair consensus over the same set of candidates. Yet few real-world problems present themselves as such precisely formulated aggregation tasks with each voter fully ranking all candidates. Instead, preferences are often expressed as rankings over partial and even disjoint subsets of candidates. For instance, hiring committee members typically opt to rank their top choices instead of exhaustively ordering every single job applicant. However, the existing literature does not offer a framework for characterizing nor ensuring group fairness in such partial preference aggregation tasks. Unlike fully ranked settings, partial preferences imply both a selection decision of whom to rank plus an ordering decision of how to rank the selected candidates. Our work fills this gap by conceptualizing the open problem of fair partial preference aggregation. We introduce an impossibility result for fair selection from partial preferences and design a computational framework showing how we can navigate this obstacle. Inspired by Single Transferable Voting, our proposed solution PreFair produces consensus rankings that are fair in the selection of candidates and also in their relative ordering. Our experimental study demonstrates that PreFair achieves the best performance in this dual fairness objective compared to state-of-the-art alternatives adapted to this new problem while still satisfying voter preferences.
We present FairRankTune, a multi-purpose open-source Python toolkit offering three primary services: quantifying fairness-related harms, leveraging bias mitigation algorithms, and constructing custom fairness-relevant datasets. FairRankTune provides researchers and practitioners with a self-contained resource for fairness auditing, experimentation, and advancing research. The central piece of FairRankTune is a novel fairness-tunable ranked data generator, RankTune, that streamlines the creation of custom fairness-relevant ranked datasets. FairRankTune also offers numerous fair ranking metrics and fairness-aware ranking algorithms within the same plug-and-play package. We demonstrate the key innovations of FairRankTune, focusing on features that are valuable to stakeholders via use cases highlighting workflows in the end-to-end process of mitigating bias in ranking systems. FairRankTune addresses the gap of limited publicly available datasets, auditing tools, and implementations for fair ranking.