Predictive Churn with the Set of Good Models

TL;DR

This paper investigates the connection between predictive multiplicity and predictive churn, revealing theoretical and empirical links that enhance understanding of model stability and fairness in machine learning.

Contribution

It introduces a unified perspective on predictive inconsistency, bridging fairness and deployment concerns through theoretical and empirical analysis.

Findings

Predictive multiplicity and churn are fundamentally linked.

Model updates can significantly affect individual predictions.

Understanding these links can improve fairness and stability in ML deployment.

Abstract

Issues can arise when research focused on fairness, transparency, or safety is conducted separately from research driven by practical deployment concerns and vice versa. This separation creates a growing need for translational work that bridges the gap between independently studied concepts that may be fundamentally related. This paper explores connections between two seemingly unrelated concepts of predictive inconsistency that share intriguing parallels. The first, known as predictive multiplicity, occurs when models that perform similarly (e.g., nearly equivalent training loss) produce conflicting predictions for individual samples. This concept is often emphasized in algorithmic fairness research as a means of promoting transparency in ML model development. The second concept, predictive churn, examines the differences in individual predictions before and after model updates, a key challenge in deploying ML models in consumer-facing applications. We present theoretical and empirical results that uncover links between these previously disconnected concepts.