When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction
Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are personalized with group attributes can reduce performance at a group level. We propose formal conditions to ensure the...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Machine learning models are often personalized with categorical attributes
that are protected, sensitive, self-reported, or costly to acquire. In this
work, we show models that are personalized with group attributes can reduce
performance at a group level. We propose formal conditions to ensure the "fair
use" of group attributes in prediction tasks by training one additional model
-- i.e., collective preference guarantees to ensure that each group who
provides personal data will receive a tailored gain in performance in return.
We present sufficient conditions to ensure fair use in empirical risk
minimization and characterize failure modes that lead to fair use violations
due to standard practices in model development and deployment. We present a
comprehensive empirical study of fair use in clinical prediction tasks. Our
results demonstrate the prevalence of fair use violations in practice and
illustrate simple interventions to mitigate their harm. |
---|---|
DOI: | 10.48550/arxiv.2206.02058 |