Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various representation debiasing techniques have been proposed in the literature. However, as neural networks are inherently opaque, these methods are hard to comprehend, which limits their usefulness. We propose a new framework for fair representation learning that is centered around the learning of "correction vectors", which have the same dimensionality as the given data vectors. Correction vectors may be computed either explicitly via architectural constraints or implicitly by training an invertible model based on Normalizing Flows. We show experimentally that several fair representation learning models constrained in such a way do not exhibit losses in ranking or classification performance. Furthermore, we demonstrate that state-of-the-art results can be achieved by the invertible model. Finally, we discuss the law standing of our methodology in light of recent legislation in the European Union.
Johannes Gutenberg-Universität Mainz（美因茨约翰内斯·古腾堡大学）
Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various "representation debiasing" techniques have been proposed in the literature. However, as neural networks are inherently opaque, these methods are hard to comprehend, which limits their usefulness. We propose a new framework for fair representation learning which is centered around the learning of "correction vectors", which have the same dimensionality as the given d…
The rapid growth of data in the recent years has led to the development of complex learning algorithms that are often used to make decisions in real world. While the positive impact of the algorithms has been tremendous, there is a need to mitigate any bias arising from either training samples or implicit assumptions made about the data samples. This need becomes critical when algorithms are used in automated decision making systems that can hugely impact people's lives. Many approaches have been proposed to make learning algorithms fair by detecting and mitigating bias in different stages of …
To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms. However, recent research suggests that this does not remove discrimination, and can perpetuate harmful stereotypes. While algorithms have been developed to improve fairness, they typically face at least one of three shortcomings: they are not interpretable, their prediction quality deteriorates quickly compared to unbiased equivalents, and they are not easily transferable across models. To address these shortcomings, we propose a geometric method that removes correlations between data a…
Université du Québec à Montréal（蒙特利尔魁北克大学）；LAAS-CNRS（法国国家科学研究中心自动化、计算机工程与信号实验室）；Université de Toulouse（图卢兹大学）
As the use of black-box models becomes ubiquitous in high stake decision-making systems, demands for fair and interpretable models are increasing. While it has been shown that interpretable models can be as accurate as black-box models in several critical domains, existing fair classification techniques that are interpretable by design often display poor accuracy/fairness tradeoffs in comparison with their non-interpretable counterparts. In this paper, we propose FairCORELS, a fair classification technique interpretable by design, whose objective is to learn fair rule lists. Our solution is a …
Microsoft Research（微软研究院）；BenevolentAI（BenevolentAI公司）；University of Oxford（牛津大学）；Human Technopole（人类技术园）
Learning meaningful representations of data that can address challenges such as batch effect correction and counterfactual inference is a central problem in many domains including computational biology. Adopting a Conditional VAE framework, we show that marginal independence between the representation and a condition variable plays a key role in both of these challenges. We propose the Contrastive Mixture of Posteriors (CoMP) method that uses a novel misalignment penalty defined in terms of mixtures of the variational posteriors to enforce this independence in latent space. We show that CoMP h…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；The University of Washington（华盛顿大学）；Duke University（杜克大学）
Objectives: We study interpretable recidivism prediction using machine learning (ML) models and analyze performance in terms of prediction ability, sparsity, and fairness. Unlike previous works, this study trains interpretable models that output probabilities rather than binary predictions, and uses quantitative fairness definitions to assess the models. This study also examines whether models can generalize across geographic locations. Methods: We generated black-box and interpretable ML models on two different criminal recidivism datasets from Florida and Kentucky. We compared predictive per…
School of Operations Research and Information Engineering（运筹学与信息工程学院）；Cornell University（康奈尔大学）
In recent years, machine learning has begun automating decision making in fields as varied as college admissions, credit lending, and criminal sentencing. The socially sensitive nature of some of these applications together with increasing regulatory constraints has necessitated the need for algorithms that are both fair and interpretable. In this paper we consider the problem of building Boolean rule sets in disjunctive normal form (DNF), an interpretable model for binary classification, subject to fairness constraints. We formulate the problem as an integer program that maximizes classificat…
Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learning
Southern University of Science and Technology（南方科技大学）；Beijing Normal-Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；Nanyang Technological University（南洋理工大学）；Lingnan University（岭南大学）
We propose to learn invariant representations, in the data domain, to achieve interpretability in algorithmic fairness. Invariance implies a selectivity for high level, relevant correlations w.r.t. class label annotations, and a robustness to irrelevant correlations with protected characteristics such as race or gender. We introduce a non-trivial setup in which the training set exhibits a strong bias such that class label annotations are irrelevant and spurious correlations cannot be distinguished. To address this problem, we introduce an adversarially trained model with a null-sampling proced…
University of California, Irvine（加州大学欧文分校）；Haverford College（哈弗福德学院）
Motivated by concerns surrounding the fairness effects of sharing and transferring fair machine learning tools, we propose two algorithms: Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be quickly fine-tuned to specific tasks from only a few number of sample instances while balancing fairness and accuracy. We demonstrate experimentally th…
Fix Representation (Optimally) Before Fairness: Finite-Sample Shrinkage Population Correction and the True Price of Fairness Under Subpopulation Shift
Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN 37232, USA（生物统计学系，范德比尔特大学医学中心）；Department of Informatics, King's College London, WC2R 2LS London, UK（信息学系，国王学院伦敦）
Discrimination has been shown in many machine learning applications, which calls for sufficient fairness testing before their deployment in ethic-relevant domains such as face recognition, medical diagnosis and criminal sentence. Existing fairness testing approaches are mostly designed for identifying individual discrimination, i.e., discrimination against individuals. Yet, as another widely concerning type of discrimination, testing against group discrimination, mostly hidden, is much less studied. To address the gap, in this work, we propose TESTSGD, an interpretable testing approach which s…
Huawei Technologies Canada（华为技术加拿大公司）；McMaster University（麦克马斯特大学）；University of British Columbia（不列颠哥伦比亚大学）；Simon Fraser University（西蒙弗雷泽大学）；Tianjin University（天津大学）
The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications, such as justice system, drug/vaccination design, and medical diagnosis. Although there are effective methods to train fair models from scratch, how to automatically reveal and explain the unfairness of a trained model remains a challenging task. Revealing unfairness of machine learning models in interpretable fashion is a critical step towards fair and trustworthy AI. In this paper, we systematically tackle the novel task of revealing unfair models by mining interpretable evi…
Machine Learning for Good Laboratory, New York University (NYU)（纽约大学机器学习为善实验室）；Courant Institute of Mathematical Sciences, Department of Computer Science, NYU（纽约大学数学科学学院计算机科学系）；Robert F. Wagner Graduate School of Public Service, NYU（纽约大学罗伯特·F·瓦格纳公共事务研究生院）；Center for Urban Science and Progress, Tandon School of Engineering, NYU（纽约大学城市科学与进步中心土木工程学院）
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Hospital of Sickkids（病童医院）；Microsoft Research（微软研究院）
Deployment of machine learning models in real high-risk settings (e.g. healthcare) often depends not only on the model's accuracy but also on its fairness, robustness, and interpretability. Generalized Additive Models (GAMs) are a class of interpretable models with a long history of use in these high-risk domains, but they lack desirable features of deep learning such as differentiability and scalability. In this work, we propose a neural GAM (NODE-GAM) and neural GA$^2$M (NODE-GA$^2$M) that scale well and perform better than other GAMs on large datasets, while remaining interpretable compared…
Interpretable Rules for Online Failure Prediction: A Case Study on the Metro do Porto dataset
Lamarr Institute for Machine Learning and Artificial Intelligence, TU Dortmund University（拉马尔机器学习与人工智能研究所，多特蒙德工业大学）；Faculty of Economics - University of Porto（波尔图大学经济学院）
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Algorithmic decision making based on computer vision and machine learning technologies continue to permeate our lives. But issues related to biases of these models and the extent to which they treat certain segments of the population unfairly, have led to concern in the general public. It is now accepted that because of biases in the datasets we present to the models, a fairness-oblivious training will lead to unfair models. An interesting topic is the study of mechanisms via which the de novo design or training of the model can be informed by fairness measures. Here, we study mechanisms that …
Bernoulli Institute, University of Groningen（格罗宁根大学伯努利研究所）；School of Computer Science, University of Birmingham（伯明翰大学计算机学院）
Increasing number of sectors which affect human lives, are using Machine Learning (ML) tools. Hence the need for understanding their working mechanism and evaluating their fairness in decision-making, are becoming paramount, ushering in the era of Explainable AI (XAI). In this contribution we introduced a few intrinsically interpretable models which are also capable of dealing with missing values, in addition to extracting knowledge from the dataset and about the problem. These models are also capable of visualisation of the classifier and decision boundaries: they are the angle based variants…
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore interpretability of learning models. And yet the most successful contemporary Machine Learning approaches, the Deep Neural Networks, produce models that are highly non-interpretable. We attempt to address this challenge by proposing a technique called CNN-INTE to interpret deep Convolutional Neural Networks (CNN) via meta-learning. In this work, we interpret a specific…
University of Maryland, Baltimore County（马里兰大学巴尔的摩郡分校）；Hong Kong University of Science and Technology（香港科技大学）
A growing proportion of human interactions are digitized on social media platforms and subjected to algorithmic decision-making, and it has become increasingly important to ensure fair treatment from these algorithms. In this work, we investigate gender bias in collaborative-filtering recommender systems trained on social media data. We develop neural fair collaborative filtering (NFCF), a practical framework for mitigating gender bias in recommending sensitive items (e.g. jobs, academic concentrations, or courses of study) using a pre-training and fine-tuning approach to neural collaborative …
Domains where supervised models are deployed often come with task-specific constraints, such as prior expert knowledge on the ground-truth function, or desiderata like safety and fairness. We introduce a novel probabilistic framework for reasoning with such constraints and formulate a prior that enables us to effectively incorporate them into Bayesian neural networks (BNNs), including a variant that can be amortized over tasks. The resulting Output-Constrained BNN (OC-BNN) is fully consistent with the Bayesian framework for uncertainty quantification and is amenable to black-box inference. Unl…
