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% fairness improvement on the first attribute while it makes the second attribute unfair by 1.85%. On the other hand, the proposed Muffin can unite multiple models to achieve simultaneously 26.32% and 20.37% fairness improvement on both attributes; meanwhile, it obtains 5.58% accuracy gain.

翻译：模型公平性（又称偏差）已成为众多AI应用中最关键的问题之一。若自动驾驶中的不公模型无法公正地处理边缘案例（如极端天气），可能引发交通事故；若AI模型误诊特定人群（如棕色和黑色皮肤），则会导致医疗不平等。近年来，针对不公平性问题的研究不断涌现，但主要集中在单一不公平属性（如肤色）上。然而，现实数据通常包含多个属性，且不公平性可能存在于多个属性中，称为“多维公平性”。本文首先揭示了不同不公平属性之间的强相关性——即优化某一属性的公平性会导致其他属性公平性的崩溃。随后，我们提出了一种新颖的多维公平性框架Muffin，该框架包含一个自动化工具，可融合现有模型同时提升多个属性的公平性。在包含两个不公平属性的皮肤病数据集上的案例研究表明：现有方法可实现第一个属性21.05%的公平性提升，却导致第二个属性产生1.85%的不公平性；而所提出的Muffin可融合多个模型，在两者上分别实现26.32%和20.37%的公平性提升，同时获得5.58%的准确率增益。