Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Models

by   Yi Sheng, et al.

Model fairness (a.k.a., bias) has become one of the most critical problems in a wide range of AI applications. An unfair model in autonomous driving may cause a traffic accident if corner cases (e.g., extreme weather) cannot be fairly regarded; or it will incur healthcare disparities if the AI model misdiagnoses a certain group of people (e.g., brown and black skin). In recent years, there have been emerging research works on addressing unfairness, and they mainly focus on a single unfair attribute, like skin tone; however, real-world data commonly have multiple attributes, among which unfairness can exist in more than one attribute, called 'multi-dimensional fairness'. In this paper, we first reveal a strong correlation between the different unfair attributes, i.e., optimizing fairness on one attribute will lead to the collapse of others. Then, we propose a novel Multi-Dimension Fairness framework, namely Muffin, which includes an automatic tool to unite off-the-shelf models to improve the fairness on multiple attributes simultaneously. Case studies on dermatology datasets with two unfair attributes show that the existing approach can achieve 21.05 first attribute while it makes the second attribute unfair by 1.85 other hand, the proposed Muffin can unite multiple models to achieve simultaneously 26.32 meanwhile, it obtains 5.58


page 1

page 2

page 3

page 5

page 6


Multiple Attribute Fairness: Application to Fraud Detection

We propose a fairness measure relaxing the equality conditions in the po...

An Empirical Study on Fairness Improvement with Multiple Protected Attributes

Existing research mostly improves the fairness of Machine Learning (ML) ...

M^3Fair: Mitigating Bias in Healthcare Data through Multi-Level and Multi-Sensitive-Attribute Reweighting Method

In the data-driven artificial intelligence paradigm, models heavily rely...

Estimating and Improving Fairness with Adversarial Learning

Fairness and accountability are two essential pillars for trustworthy Ar...

CAT: Controllable Attribute Translation for Fair Facial Attribute Classification

As the social impact of visual recognition has been under scrutiny, seve...

Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility

This paper investigates to what degree and magnitude tradeoffs exist bet...

ICON^2: Reliably Benchmarking Predictive Inequity in Object Detection

As computer vision systems are being increasingly deployed at scale in h...

Please sign up or login with your details

Forgot password? Click here to reset