Fairness-aware classification is receiving increasing attention in the machine learning fields. Recently research proposes to formulate the fairness-aware classification as constrained optimization problems. However, several limitations exist in previous works due to the lack of a theoretical framework for guiding the formulation. In this paper, we propose a general framework for learning fair classifiers which addresses previous limitations. The framework formulates various commonly-used fairness metrics as convex constraints that can be directly incorporated into classic classification models. Within the framework, we propose a constraint-free criterion on the training data which ensures that any classifier learned from the data is fair. We also derive the constraints which ensure that the real fairness metric is satisfied when surrogate functions are used to achieve convexity. Our framework can be used to for formulating fairness-aware classification with fairness guarantee and computational efficiency. The experiments using real-world datasets demonstrate our theoretical results and show the effectiveness of proposed framework and methods.
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Carnegie Mellon University（卡内基梅隆大学）
Developing classification methods with high accuracy that also avoid unfair treatment of different groups has become increasingly important for data-driven decision making in social applications. Many existing methods enforce fairness constraints on a selected classifier (e.g., logistic regression) by directly forming constrained optimizations. We instead re-derive a new classifier from the first principles of distributional robustness that incorporates fairness criteria into a worst-case logarithmic loss minimization. This construction takes the form of a minimax game and produces a parametri…
In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective. We propose a fairness criterion where a classifier achieves minimax risk and is Pareto-efficient w.r.t. all groups, avoiding unnecessary harm, and can lead to the best zero-gap model if policy dictates so. We provide a simple optimization algorithm compatible with deep neural networks to satisfy these constraints. Since our method does not require test-time access to sensitive attributes, it can be applied to reduce worst-case cl…
University of Edinburgh（爱丁堡大学）；Samsung AI Centre, Cambridge（三星剑桥人工智能中心）
A multitude of work has shown that machine learning-based medical diagnosis systems can be biased against certain subgroups of people. This has motivated a growing number of bias mitigation algorithms that aim to address fairness issues in machine learning. However, it is difficult to compare their effectiveness in medical imaging for two reasons. First, there is little consensus on the criteria to assess fairness. Second, existing bias mitigation algorithms are developed under different settings, e.g., datasets, model selection strategies, backbones, and fairness metrics, making a direct comp…
Texas A&M University（德克萨斯农工大学）；Rice University（莱斯大学）；University of Texas Health Science Center（德克萨斯大学健康科学中心）
Clinical trials are indispensable in developing new treatments, but they face obstacles in patient recruitment and retention, hindering the enrollment of necessary participants. To tackle these challenges, deep learning frameworks have been created to match patients to trials. These frameworks calculate the similarity between patients and clinical trial eligibility criteria, considering the discrepancy between inclusion and exclusion criteria. Recent studies have shown that these frameworks outperform earlier approaches. However, deep learning models may raise fairness issues in patient-trial …
The old empathetic adage, ``Walk a mile in their shoes,'' asks that one imagine the difficulties others may face. This suggests a new ML counterfactual fairness criterion, based on a \textit{group} level: How would members of a nonprotected group fare if their group were subject to conditions in some protected group? Instead of asking what sentence would a particular Caucasian convict receive if he were Black, take that notion to entire groups; e.g. how would the average sentence for all White convicts change if they were Black, but with their same White characteristics, e.g. same number of pr…
Machine learning models are vulnerable to biases that result in unfair treatment of individuals from different populations. Recent work that aims to test a model's fairness at the individual level either relies on domain knowledge to choose metrics, or on input transformations that risk generating out-of-domain samples. We describe a new approach for testing individual fairness that does not have either requirement. We propose a novel criterion for evaluating individual fairness and develop a practical testing method based on this criterion which we call fAux (pronounced fox). This is based on…
Fairness-aware kidney exchange and kidney paired donation
Division of Biostatistics, University of California, Berkeley（加州大学伯克利分校生物统计学系）；Department of Statistics and Data Science and Department of Biostatistics, University of California, Los Angeles（加州大学洛杉矶分校统计与数据科学系和生物统计学系）；University of California, Berkeley（加州大学伯克利分校）
The University of Melbourne（墨尔本大学）；Huawei Technologies Co., Ltd.（华为技术有限公司）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
This paper presents fairlib, an open-source framework for assessing and improving classification fairness. It provides a systematic framework for quickly reproducing existing baseline models, developing new methods, evaluating models with different metrics, and visualizing their results. Its modularity and extensibility enable the framework to be used for diverse types of inputs, including natural language, images, and audio. In detail, we implement 14 debiasing methods, including pre-processing, at-training-time, and post-processing approaches. The built-in metrics cover the most commonly use…
UIUC（伊利诺伊大学厄巴纳-香槟分校）；ETH Zurich（苏黎世联邦理工学院）；UC Santa Cruz（加州大学圣克鲁兹分校）
Extensive efforts have been made to understand and improve the fairness of machine learning models based on observational metrics, especially in high-stakes domains such as medical insurance, education, and hiring decisions. However, there is a lack of certified fairness considering the end-to-end performance of an ML model. In this paper, we first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem based on the model performance loss bound on a fairness constrained distribution, which is within bounded distributional distance with th…
When dealing with sensitive data in automated data-driven decision-making, an important concern is to learn predictors with high performance towards a class label, whilst minimising for the discrimination towards any sensitive attribute, like gender or race, induced from biased data. A few hybrid tree optimisation criteria exist that combine classification performance and fairness. Although the threshold-free ROC-AUC is the standard for measuring traditional classification model performance, current fair tree classification methods mainly optimise for a fixed threshold on both the classificati…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Stanford University（斯坦福大学）
We propose a distributionally robust classification model with a fairness constraint that encourages the classifier to be fair in view of the equality of opportunity criterion. We use a type-$\infty$ Wasserstein ambiguity set centered at the empirical distribution to model distributional uncertainty and derive a conservative reformulation for the worst-case equal opportunity unfairness measure. We establish that the model is equivalent to a mixed binary optimization problem, which can be solved by standard off-the-shelf solvers. To improve scalability, we further propose a convex, hinge-loss-b…
As deep image classification applications, e.g., face recognition, become increasingly prevalent in our daily lives, their fairness issues raise more and more concern. It is thus crucial to comprehensively test the fairness of these applications before deployment. Existing fairness testing methods suffer from the following limitations: 1) applicability, i.e., they are only applicable for structured data or text without handling the high-dimensional and abstract domain sampling in the semantic level for image classification applications; 2) functionality, i.e., they generate unfair samples with…
Fairness across different demographic groups is an essential criterion for face-related tasks, Face Attribute Classification (FAC) being a prominent example. Apart from this trend, Federated Learning (FL) is increasingly gaining traction as a scalable paradigm for distributed training. Existing FL approaches require data homogeneity to ensure fairness. However, this assumption is too restrictive in real-world settings. We propose F3, a novel FL framework for fair FAC under data heterogeneity. F3 adopts multiple heuristics to improve fairness across different demographic groups without requirin…
Fairness-aware machine learning seeks to maximise utility in generating predictions while avoiding unfair discrimination based on sensitive attributes such as race, sex, religion, etc. An important line of work in this field is enforcing fairness during the training step of a classifier. A simple yet effective binary classification algorithm that follows this strategy is two-naive-Bayes (2NB), which enforces statistical parity - requiring that the groups comprising the dataset receive positive labels with the same likelihood. In this paper, we generalise this algorithm into N-naive-Bayes (NNB)…
We investigate the problem of algorithmic fairness in the case where sensitive and non-sensitive features are available and one aims to generate new, `oblivious', features that closely approximate the non-sensitive features, and are only minimally dependent on the sensitive ones. We study this question in the context of kernel methods. We analyze a relaxed version of the Maximum Mean Discrepancy criterion which does not guarantee full independence but makes the optimization problem tractable. We derive a closed-form solution for this relaxed optimization problem and complement the result with …
Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone
Artefact Research Center, Paris, France（阿切夫特研究中心，法国巴黎）；Institut de Mathématiques de Toulouse (UMR 5219), CNRS, Université de Toulouse, F-31062 Toulouse, France（图卢兹数学研究所（UMR 5219），CNRS，图卢兹大学，法国图卢兹）；L’Oréal Research（欧莱雅研究）；INRIA, ANITI, France（INRIA，ANITI，法国）
