Federated learning with differential privacy, or private federated learning, provides a strategy to train machine learning models while respecting users' privacy. However, differential privacy can disproportionately degrade the performance of the models on under-represented groups, as these parts of the distribution are difficult to learn in the presence of noise. Existing approaches for enforcing fairness in machine learning models have considered the centralized setting, in which the algorithm has access to the users' data. This paper introduces an algorithm to enforce group fairness in private federated learning, where users' data does not leave their devices. First, the paper extends the modified method of differential multipliers to empirical risk minimization with fairness constraints, thus providing an algorithm to enforce fairness in the central setting. Then, this algorithm is extended to the private federated learning setting. The proposed algorithm, \texttt{FPFL}, is tested on a federated version of the Adult dataset and an "unfair" version of the FEMNIST dataset. The experiments on these datasets show how private federated learning accentuates unfairness in the trained models, and how FPFL is able to mitigate such unfairness.
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, \emph{FNNC}, to achieve fairness while maintaining high accurac…
University of Michigan（密歇根大学）；IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Many instances of algorithmic bias are caused by subpopulation shifts. For example, ML models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we study whether enforcing algorithmic fairness during training improves the performance of the trained model in the \emph{target domain}. On one hand, we conceive scenarios in which enforcing fairness does not improve performance in the target domain. In fact, it may even harm performance. On the other hand, we derive necessary and sufficient conditions under which enforcing algorithmic fairness l…
IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）；University of Michigan（密歇根大学）
In this paper, we cast fair machine learning as invariant machine learning. We first formulate a version of individual fairness that enforces invariance on certain sensitive sets. We then design a transport-based regularizer that enforces this version of individual fairness and develop an algorithm to minimize the regularizer efficiently. Our theoretical results guarantee the proposed approach trains certifiably fair ML models. Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are suscep…
We use disparate impact, i.e., the extent that the probability of observing an output depends on protected attributes such as race and gender, to measure fairness. We prove that disparate impact is upper bounded by the total variation distance between the distribution of the inputs given the protected attributes. We then use pre-processing, also known as data repair, to enforce fairness. We show that utility degradation, i.e., the extent that the success of a forecasting model changes by pre-processing the data, is upper bounded by the total variation distance between the distribution of the d…
Nowadays Machine Learning (ML) techniques are extensively adopted in many socially sensitive systems, thus requiring to carefully study the fairness of the decisions taken by such systems. Many approaches have been proposed to address and to make sure there is no bias against individuals or specific groups which might originally come from biased training datasets or algorithm design. In this regard, we propose a fairness enforcing approach called EiFFFeL:Enforcing Fairness in Forests by Flipping Leaves which exploits tree-based or leaf-based post-processing strategies to relabel leaves of sele…
The rise of graph representation learning as the primary solution for many different network science tasks led to a surge of interest in the fairness of this family of methods. Link prediction, in particular, has a substantial social impact. However, link prediction algorithms tend to increase the segregation in social networks by disfavoring the links between individuals in specific demographic groups. This paper proposes a novel way to enforce fairness on graph neural networks with a fine-tuning strategy. We Drop the unfair Edges and, simultaneously, we Adapt the model's parameters to those …
Manning College of Information and Computer Sciences（曼宁信息与计算机科学学院）；University of Massachusetts（马萨诸塞大学）
Recent research has shown that seemingly fair machine learning models, when used to inform decisions that have an impact on peoples' lives or well-being (e.g., applications involving education, employment, and lending), can inadvertently increase social inequality in the long term. This is because prior fairness-aware algorithms only consider static fairness constraints, such as equal opportunity or demographic parity. However, enforcing constraints of this type may result in models that have negative long-term impact on disadvantaged individuals and communities. We introduce ELF (Enforcing Lo…
A number of machine learning (ML) methods have been proposed recently to maximize model predictive accuracy while enforcing notions of group parity or fairness across sub-populations. We propose a desirable property for these procedures, slack-consistency: For any individual, the predictions of the model should be monotonic with respect to allowed slack (i.e., maximum allowed group-parity violation). Such monotonicity can be useful for individuals to understand the impact of enforcing fairness on their predictions. Surprisingly, we find that standard ML methods for enforcing fairness violate t…
Empirical risk minimization (ERM) is typically designed to perform well on the average loss, which can result in estimators that are sensitive to outliers, generalize poorly, or treat subgroups unfairly. While many methods aim to address these problems individually, in this work, we explore them through a unified framework -- tilted empirical risk minimization (TERM). In particular, we show that it is possible to flexibly tune the impact of individual losses through a straightforward extension to ERM using a hyperparameter called the tilt. We provide several interpretations of the resulting fr…
Enforcing Consistency and Fairness in Multi-level Hierarchical Classification with a Mask-based Output Layer
University of New South Wales（新南威尔士大学）；University of Southampton（南安普顿大学）；Deakin University（迪肯大学）；Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Macquarie University（麦考瑞大学）；Technology Innovation Institute（技术创新研究院）
On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computer and Information Engineering, Jiangxi Normal University（江西师范大学计算机与信息工程学院）；La Trobe Business School, La Trobe University（拉筹伯大学拉筹伯商学院）；School of Computing Technologies, RMIT University（皇家墨尔本理工大学计算技术学院）；Hong Kong University of Science and Technology（香港科技大学）
University of Zurich（苏黎世大学）；Zurich University of Applied Sciences（苏黎世应用科学大学）
Binary decision making classifiers are not fair by default. Fairness requirements are an additional element to the decision making rationale, which is typically driven by maximizing some utility function. In that sense, algorithmic fairness can be formulated as a constrained optimization problem. This paper contributes to the discussion on how to implement fairness, focusing on the fairness concepts of positive predictive value (PPV) parity, false omission rate (FOR) parity, and sufficiency (which combines the former two). We show that group-specific threshold rules are optimal for PPV parity …
Missouri University of Science and Technology（密苏里科技大学）
Algorithmic fairness literature presents numerous mathematical notions and metrics, and also points to a tradeoff between them while satisficing some or all of them simultaneously. Furthermore, the contextual nature of fairness notions makes it difficult to automate bias evaluation in diverse algorithmic systems. Therefore, in this paper, we propose a novel model called latent assessment model (LAM) to characterize binary feedback provided by human auditors, by assuming that the auditor compares the classifier's output to his or her own intrinsic judgment for each input. We prove that individu…
DPBalance: Efficient and Fair Privacy Budget Scheduling for Federated Learning as a Service
UM-SJTU Joint Institute, Shanghai Jiao Tong University（上海交通大学密西根学院）；Cooperative Medianet Innovation Center (CMIC), Shanghai Jiao Tong University（上海交通大学合作媒体创新中心）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）
University of Michigan（密歇根大学）；ShanghaiTech University（上海科技大学）；IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
We consider the task of enforcing individual fairness in gradient boosting. Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern. At a high level, our approach is a functional gradient descent on a (distributionally) robust loss function that encodes our intuition of algorithmic fairness for the ML task at hand. Unlike prior approaches to individual fairness that only work with smooth ML models, our approach also works with non-smooth models such as decision trees. We show that our algorithm conv…
DP-SGD-Global-Adapt-V2-S: Triad Improvements of Privacy, Accuracy and Fairness via Step Decay Noise Multiplier and Step Decay Upper Clipping Threshold
University of Louisiana at Lafayette（路易斯安那大学拉斐特分校）；College of Saint Benedict and Saint John’s University（圣本笃学院与圣约翰大学）；Mississippi State University（密西西比州立大学）
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Consider an actor making selection decisions using a series of classifiers, which we term a sequential screening process. The early stages filter out some applicants, and in the final stage an expensive but accurate test is applied to the individuals that make it to the final stage. Since the final stage is expensive, if there are multiple groups with different fractions of positives at the penultimate stage (even if a slight gap), then the firm may naturally only choose to the apply the final (interview) stage solely to the highest precision group which would be clearly unfair to the other gr…
Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
Barnard College, Columbia University（哥伦比亚大学巴纳德学院）；Georgia Institute of Technology（佐治亚理工学院）；Carnegie Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；HEC Montréal（蒙特利尔高等商学院）
Algorithmic decision making driven by neural networks has become very prominent in applications that directly affect people's quality of life. In this paper, we study the problem of verifying, training, and guaranteeing individual fairness of neural network models. A popular approach for enforcing fairness is to translate a fairness notion into constraints over the parameters of the model. However, such a translation does not always guarantee fair predictions of the trained neural network model. To address this challenge, we develop a counterexample-guided post-processing technique to provably…
In this article, we propose a new variational approach to learn private and/or fair representations. This approach is based on the Lagrangians of a new formulation of the privacy and fairness optimization problems that we propose. In this formulation, we aim to generate representations of the data that keep a prescribed level of the relevant information that is not shared by the private or sensitive data, while minimizing the remaining information they keep. The proposed approach (i) exhibits the similarities of the privacy and fairness problems, (ii) allows us to control the trade-off between…
Florida International University（佛罗里达国际大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Mississippi（密西西比大学）；National Institutes of Health（美国国立卫生研究院）
California Institute of Technology（加州理工学院）；Microsoft Research（微软研究院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Many modern machine learning algorithms mitigate bias by enforcing fairness constraints across coarsely-defined groups related to a sensitive attribute like gender or race. However, these algorithms seldom account for within-group heterogeneity and biases that may disproportionately affect some members of a group. In this work, we characterize Social Norm Bias (SNoB), a subtle but consequential type of algorithmic discrimination that may be exhibited by machine learning models, even when these systems achieve group fairness objectives. We study this issue through the lens of gender bias in occ…
Georgia Institute of Technology（佐治亚理工学院）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Machine learning (ML) is increasingly being used to make decisions in our society. ML models, however, can be unfair to certain demographic groups (e.g., African Americans or females) according to various fairness metrics. Existing techniques for producing fair ML models either are limited to the type of fairness constraints they can handle (e.g., preprocessing) or require nontrivial modifications to downstream ML training algorithms (e.g., in-processing). We propose a declarative system OmniFair for supporting group fairness in ML. OmniFair features a declarative interface for users to specif…
Fairness-aware machine learning (fair-ml) techniques are algorithmic interventions designed to ensure that individuals who are affected by the predictions of a machine learning model are treated fairly. The problem is often posed as an optimization problem, where the objective is to achieve high predictive performance under a quantitative fairness constraint. However, any attempt to design a fair-ml algorithm must assume a world where Goodhart's law has an exception: when a fairness measure becomes an optimization constraint, it does not cease to be a good measure. In this paper, we argue that…
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)…
University of Maryland（马里兰大学）；Wellesley College（韦尔斯利学院）
Clustering is a fundamental unsupervised learning problem where a dataset is partitioned into clusters that consist of nearby points in a metric space. A recent variant, fair clustering, associates a color with each point representing its group membership and requires that each color has (approximately) equal representation in each cluster to satisfy group fairness. In this model, the cost of the clustering objective increases due to enforcing fairness in the algorithm. The relative increase in the cost, the ''price of fairness,'' can indeed be unbounded. Therefore, in this paper we propose to…
Brandeis University（布兰迪斯大学）；Michtom School of Computer Science（米奇托姆计算机科学学院）
In this paper, we focus on the fairness issues regarding unsupervised outlier detection. Traditional algorithms, without a specific design for algorithmic fairness, could implicitly encode and propagate statistical bias in data and raise societal concerns. To correct such unfairness and deliver a fair set of potential outlier candidates, we propose Deep Clustering based Fair Outlier Detection (DCFOD) that learns a good representation for utility maximization while enforcing the learnable representation to be subgroup-invariant on the sensitive attribute. Considering the coupled and reciprocal …
Credit is an essential component of financial wellbeing in America, and unequal access to it is a large factor in the economic disparities between demographic groups that exist today. Today, machine learning algorithms, sometimes trained on alternative data, are increasingly being used to determine access to credit, yet research has shown that machine learning can encode many different versions of "unfairness," thus raising the concern that banks and other financial institutions could -- potentially unwittingly -- engage in illegal discrimination through the use of this technology. In the US, …
There is substantial evidence that Artificial Intelligence (AI) and Machine Learning (ML) algorithms can generate bias against minorities, women, and other protected classes. Federal and state laws have been enacted to protect consumers from discrimination in credit, housing, and employment, where regulators and agencies are tasked with enforcing these laws. Additionally, there are laws in place to ensure that consumers understand why they are denied access to services and products, such as consumer loans. In this article, we provide an overview of the potential benefits and risks associated w…
