Timezone: »
In many real-world situations, data is distributed across multiple locations and can't be combined for training. For example, multiple hospitals might have comparable data related to patient outcomes. Federated learning is a novel distributed learning approach that allows multiple federating agents to jointly learn a model. While this approach might reduce the error each agent experiences, it also raises questions of fairness: to what extent can the error experienced by one agent be significantly lower than the error experienced by another agent? In this work, we consider two notions of fairness that each may be appropriate in different circumstances: \emph{egalitarian fairness} (which aims to bound how dissimilar error rates can be) and \emph{proportional fairness} (which aims to reward players for contributing more data). For egalitarian fairness, we obtain a tight multiplicative bound on how widely error rates can diverge between agents federating together. For proportional fairness, we show that sub-proportional error (relative to the number of data points contributed) is guaranteed for any individually rational federating coalition.
Author Information
Kate Donahue (Cornell University)
Jon Kleinberg (Cornell University)
More from the Same Authors
-
2021 : Models of fairness in federated learning »
Kate Donahue · Jon Kleinberg -
2022 : Panel »
Meena Jagadeesan · Avrim Blum · Jon Kleinberg · Celestine Mendler-Dünner · Jennifer Wortman Vaughan · Chara Podimata -
2022 Poster: Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures »
Emmanuel Abbe · Samy Bengio · Elisabetta Cornacchia · Jon Kleinberg · Aryo Lotfi · Maithra Raghu · Chiyuan Zhang -
2021 : Algorithmic Monoculture and Social Welfare »
Jon Kleinberg -
2021 : Spotlight 2: Models of fairness in federated learning »
Kate Donahue · Jon Kleinberg -
2021 Poster: Approximate Decomposable Submodular Function Minimization for Cardinality-Based Components »
Nate Veldt · Austin Benson · Jon Kleinberg -
2021 Poster: Optimality and Stability in Federated Learning: A Game-theoretic Approach »
Kate Donahue · Jon Kleinberg -
2021 Poster: Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess »
Reid McIlroy-Young · Russell Wang · Siddhartha Sen · Jon Kleinberg · Ashton Anderson -
2020 : Contributed Talk 2: Better Together? How Externalities of Size Complicate Notions of Solidarity and Actuarial Fairness »
Kate Donahue · Solon Barocas