Abstract

Algorithmic fairness in the context of personalized recommendation presents significantly different challenges to those commonly encountered in classification tasks. Researchers studying classification have generally considered fairness to be a matter of achieving equality of outcomes (or some other metric) between a protected and unprotected group and built algorithmic interventions on this basis. We argue that fairness in real-world application settings in general, and especially in the context of personalized recommendation, is much more complex and multi-faceted, requiring a more general approach. To address the fundamental problem of fairness in the presence of multiple stakeholders, with different definitions of fairness, we propose the Social Choice for Recommendation Under Fairness–Dynamic architecture, which formalizes multistakeholder fairness in recommender systems as a two-stage social choice problem. In particular, we express recommendation fairness as a combination of an allocation and an aggregation problem, which integrate both fairness concerns and personalized recommendation provisions, and derive new recommendation techniques based on this formulation. We demonstrate the ability of our framework to dynamically incorporate multiple fairness concerns using both real-world and synthetic datasets.

Reference

Aird, Amanda, Paresha Farastu, Joshua Sun, Elena Stefancová, Cassidy All, Amy Voida, Nicholas Mattei, and Robin Burke. "Dynamic fairness-aware recommendation through multi-agent social choice." ACM Transactions on Recommender Systems 3, no. 2 (2024): 1-35.

Bibtex

@article{aird2024dynamic,
  title={Dynamic fairness-aware recommendation through multi-agent social choice},
  author={Aird, Amanda and Farastu, Paresha and Sun, Joshua and Stefancov{\'a}, Elena and All, Cassidy and Voida, Amy and Mattei, Nicholas and Burke, Robin},
  journal={ACM Transactions on Recommender Systems},
  volume={3},
  number={2},
  pages={1--35},
  year={2024},
  publisher={ACM New York, NY}
}