Saved in:
Bibliographic Details
Main Authors: Hsu, Brian, DiCiccio, Cyrus, Sivasubramoniapillai, Natesh, Namkoong, Hongseok
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.04655
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915088007430144
author Hsu, Brian
DiCiccio, Cyrus
Sivasubramoniapillai, Natesh
Namkoong, Hongseok
author_facet Hsu, Brian
DiCiccio, Cyrus
Sivasubramoniapillai, Natesh
Namkoong, Hongseok
contents Fairness research in machine learning often centers on ensuring equitable performance of individual models. However, real-world recommendation systems are built on multiple models and even multiple stages, from candidate retrieval to scoring and serving, which raises challenges for responsible development and deployment. This system-level view, as highlighted by regulations like the EU AI Act, necessitates moving beyond auditing individual models as independent entities. We propose a holistic framework for modeling system-level fairness, focusing on the end-utility delivered to diverse user groups, and consider interactions between components such as retrieval and scoring models. We provide formal insights on the limitations of focusing solely on model-level fairness and highlight the need for alternative tools that account for heterogeneity in user preferences. To mitigate system-level disparities, we adapt closed-box optimization tools (e.g., BayesOpt) to jointly optimize utility and equity. We empirically demonstrate the effectiveness of our proposed framework on synthetic and real datasets, underscoring the need for a system-level framework.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04655
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Models to Systems: A Comprehensive Fairness Framework for Compositional Recommender Systems
Hsu, Brian
DiCiccio, Cyrus
Sivasubramoniapillai, Natesh
Namkoong, Hongseok
Artificial Intelligence
Fairness research in machine learning often centers on ensuring equitable performance of individual models. However, real-world recommendation systems are built on multiple models and even multiple stages, from candidate retrieval to scoring and serving, which raises challenges for responsible development and deployment. This system-level view, as highlighted by regulations like the EU AI Act, necessitates moving beyond auditing individual models as independent entities. We propose a holistic framework for modeling system-level fairness, focusing on the end-utility delivered to diverse user groups, and consider interactions between components such as retrieval and scoring models. We provide formal insights on the limitations of focusing solely on model-level fairness and highlight the need for alternative tools that account for heterogeneity in user preferences. To mitigate system-level disparities, we adapt closed-box optimization tools (e.g., BayesOpt) to jointly optimize utility and equity. We empirically demonstrate the effectiveness of our proposed framework on synthetic and real datasets, underscoring the need for a system-level framework.
title From Models to Systems: A Comprehensive Fairness Framework for Compositional Recommender Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2412.04655