Fairness Challenges in AI: Insights into Data-set Valuation and Matching Markets
le 12 janvier 2024
12h45
Manufacture des Tabacs Bâtiment F (Salle MF103)
Felipe GARRIDO LUCERO, Postdoc FAIRPLAY, CREST, ENSAE INRIA Saclay Île-de-France
Abstract:
Fairness is an increasingly research subject within various computer science sub-disciplines such as machine learning and market design. In this presentation we will discuss two possible fairness challenges: the data-set valuation problem and the price of fairness in bipartite matching markets.
The data-set valuation problem addresses measuring the contributions of agents when collaborating on machine learning tasks. By employing tools from both machine learning and game theory, we model this as a cooperative game and present an approach to approximate the Shapley value of players. The method demonstrates superior performance compared to Monte-Carlo state-of-the-art techniques, supported by theoretical guarantees.
The price of fairness (PoF) quantifies the optimality loss when applying fairness constraints to a problem. Examining the egalitarian PoF in bipartite matching markets, where agents belong to distinct groups, we exploit matroid and geometric tools to characterize fair matchings, optimal matchings, and their intersection. An adversarial analysis reveals that a PoF of 1 is always achievable for two groups, while for a greater number of groups, the PoF can be arbitrarily large.
En appuyant sur le bouton "j'accepte" vous nous autorisez à déposer des cookies afin de mesurer l'audience de notre site. Ces données sont à notre seul usage et ne sont pas communiquées. Consultez notre politique relative aux cookies