Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models

2026-02-09

AI Summary

This work addresses a critical limitation in existing fairness definitions for generative models, which focus solely on balancing generation probabilities across sensitive groups while neglecting disparities in generation quality, thereby yielding fragile fairness evaluations. To remedy this, we propose a novel paradigm termed Equal Generative Treatment (EGT), which requires that all sensitive groups exhibit comparable generation quality as measured by f-divergence, and we uncover an intrinsic coupling between EGT and overall model performance. To operationalize this principle, we develop a min-max optimization–based fine-tuning strategy that significantly improves fairness in generation quality across groups in both image and text generation tasks, without compromising overall model competitiveness. This study is the first to formally incorporate generation quality into the fairness framework, establishing a theoretical foundation for fair generative modeling.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Game Theory and Economic Paradigms: Fair Division

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

Fairness is a crucial concern for generative models, which not only reflect but can also amplify societal and cultural biases. Existing fairness notions for generative models are largely adapted from classification and focus on balancing the probability of generating samples from each sensitive group. We show that such criteria are brittle, as they can be met even when different sensitive groups are modeled with widely varying quality. To address this limitation, we introduce a new fairness definition for generative models, termed as equalized generative treatment (EGT), which requires comparable generation quality across all sensitive groups, with quality measured via a reference f-divergence. We further analyze the trade-offs induced by EGT, demonstrating that enforcing fairness constraints necessarily couples the overall model quality to that of the most challenging group to approximate. This indicates that a simple yet efficient min-max fine-tuning method should be able to balance f-divergences across sensitive groups to satisfy EGT. We validate this theoretical insight through a set of experiments on both image and text generation tasks. We demonstrate that min-max methods consistently achieve fairer outcomes compared to other approaches from the literature, while maintaining competitive overall performance for both tasks.

Problem

• fairness
• generative models
• sensitive groups
• generation quality
• f-divergences

Innovation

• equalized generative treatment
• f-divergence
• fairness in generative models
• min-max fine-tuning
• sensitive groups