Characterizing Fairness Over the Set of Good Models Under Selective Labels

Certifying and Removing Disparate Impact

What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. This legal determination hinges on a definition of a protected class (ethnicity, gender) and an explicit description of the process.When computers are involved, determining disparate impact (and hence bias) is harder. It might not be possible to disclose the process. In addition, even if the process is open, it might be hard to elucidate in a legal setting how the algorithm makes its decisions. Instead of requiring access to the process, we propose making inferences based on the data it uses.We present four contributions. First, we link disparate impact to a measure of classification accuracy that while known, has received relatively little attention. Second, we propose a test for disparate impact based on how well the protected class can be predicted from the other attributes. Third, we describe methods by which data might be made unbiased. Finally, we present empirical evidence supporting the effectiveness of our test for disparate impact and our approach for both masking bias and preserving relevant information in the data. Interestingly, our approach resembles some actual selection practices that have recently received legal scrutiny.

Learning Fair Representations

We propose a learning algorithm for fair classification that achieves both group fairness (the proportion of members in a protected group receiving positive classification is identical to the proportion in the population as a whole), and individual fairness (similar individuals should be treated similarly). We formulate fairness as an optimization problem of finding a good representation of the data with two competing goals: to encode the data as well as possible, while simultaneously obfuscating any information about membership in the protected group. We show positive results of our algorithm relative to other known techniques, on three datasets. Moreover, we demonstrate several advantages to our approach. First, our intermediate representation can be used for other classification tasks (i.e., transfer learning is possible); secondly, we take a step toward learning a distance metric which can find important dimensions of the data for classification.

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

As the scope of machine learning broadens, we observe a recurring theme of algorithmic monoculture: the same systems, or systems that share components (e.g. datasets, models), are deployed by multiple decision-makers. While sharing offers advantages like amortizing effort, it also has risks. We introduce and formalize one such risk, outcome homogenization: the extent to which particular individuals or groups experience the same outcomes across different deployments. If the same individuals or groups exclusively experience undesirable outcomes, this may institutionalize systemic exclusion and reinscribe social hierarchy. We relate algorithmic monoculture and outcome homogenization by proposing the component sharing hypothesis: if algorithmic systems are increasingly built on the same data or models, then they will increasingly homogenize outcomes. We test this hypothesis on algorithmic fairness benchmarks, demonstrating that increased data-sharing reliably exacerbates homogenization and individual-level effects generally exceed group-level effects. Further, given the current regime in AI of foundation models, i.e. pretrained models that can be adapted to myriad downstream tasks, we test whether model-sharing homogenizes outcomes across tasks. We observe mixed results: we find that for both vision and language settings, the specific methods for adapting a foundation model significantly influence the degree of outcome homogenization. We also identify societal challenges that inhibit the measurement, diagnosis, and rectification of outcome homogenization in deployed machine learning systems.

From Predictive Algorithms to Automatic Generation of Anomalies

Machine learning algorithms can find predictive signals that researchers fail to notice; yet they are notoriously hard-to-interpret. How can we extract theoretical insights from these black boxes? History provides a clue. Facing a similar problem – how to extract theoretical insights from their intuitions – researchers often turned to “anomalies:” constructed examples that highlight flaws in an existing theory and spur the development of new ones. Canonical examples include the Allais paradox and the Kahneman-Tversky choice experiments for expected utility theory. We suggest anomalies can extract theoretical insights from black box predictive algorithms. We develop procedures to automatically generate anomalies for an existing theory when given a predictive algorithm. We cast anomaly generation as an adversarial game between a theory and a falsifier, the solutions to which are anomalies: instances where the black box algorithm predicts - were we to collect data - we would likely observe violations of the theory. As an illustration, we generate anomalies for expected utility theory using a large, publicly available dataset on real lottery choices. Based on an estimated neural network that predicts lottery choices, our procedures recover known anomalies and discover new ones for expected utility theory. In incentivized experiments, subjects violate expected utility theory on these algorithmically generated anomalies; moreover, the violation rates are similar to observed rates for the Allais paradox and Common ratio effect.

Algorithmic Bias in Lending: Evidence from a Fintech Audit

Algorithmic lending has transformed the consumer credit landscape, with machine learning models commonly facilitating underwriting decisions. To comply with fair lending laws, these algorithms exclude legally protected characteristics, such as race and gender. Yet algorithmic underwriting can still inadvertently favor certain groups, prompting concerns about whether lending algorithms exhibit discriminatory behavior. Using proprietary loan-level data from a major U.S. fintech platform, we audit lending decisions across approximately 80,000 personal loans. We find that loans made to men and Black borrowers yielded lower profits than loans to other groups, suggesting that men and Black borrowers benefited from relatively favorable pricing. We trace these disparities to miscalibration in the platform's underwriting model, which overestimates risk for women and underestimates risk for Black borrowers. We then show that one could correct this miscalibration -- and the corresponding disparities -- by including race and gender in underwriting models, illustrating a tension between competing notions of fairness.

Data preprocessing techniques for classification without discrimination

Recently, the following Discrimination-Aware Classification Problem was introduced: Suppose we are given training data that exhibit unlawful discrimination; e.g., toward sensitive attributes such as gender or ethnicity. The task is to learn a classifier that optimizes accuracy, but does not have this discrimination in its predictions on test data. This problem is relevant in many settings, such as when the data are generated by a biased decision process or when the sensitive attribute serves as a proxy for unobserved features. In this paper, we concentrate on the case with only one binary sensitive attribute and a two-class classification problem. We first study the theoretically optimal trade-off between accuracy and non-discrimination for pure classifiers. Then, we look at algorithmic solutions that preprocess the data to remove discrimination before a classifier is learned. We survey and extend our existing data preprocessing techniques, being suppression of the sensitive attribute, massaging the dataset by changing class labels, and reweighing or resampling the data to remove discrimination without relabeling instances. These preprocessing techniques have been implemented in a modified version of Weka and we present the results of experiments on real-life data.

Data Valuation in the Absence of a Reliable Validation Set

Data valuation plays a pivotal role in ensuring data quality and equitably compensating data contributors. Existing game-theoretic data valuation techniques mostly rely on the availability of a high-quality validation set for their efficacy. However, the feasibility of obtaining a clean validation set drawn from the test distribution may be limited in practice. In this work, we show that the choice of validation set can significantly impact the final data value scores. In order to mitigate this, we introduce a general paradigm that converts a traditional validation-based game-theoretic data valuation method into a validation-free alternative. Specifically, we utilize the cross-validation error as a surrogate for to evaluate the model's performance on a validation set. As computing the cross-validation error can be computationally expensive, we propose using the cross-validation error of a kernel regression model as an effective and efficient surrogate for the true performance score on the population. We compare the performance of the validation-free variant of existing data valuation techniques with their original validation-based counterparts. Our results indicate that the validation-free variants generally match or often significantly surpass the performance of their validation-based counterparts.

Data Shapley: Equitable Valuation of Data for Machine Learning

As data becomes the fuel driving technological and economic growth, a fundamental challenge is how to quantify the value of data in algorithmic predictions and decisions. For example, in healthcare and consumer markets, it has been suggested that individuals should be compensated for the data that they generate, but it is not clear what is an equitable valuation for individual data. In this work, we develop a principled framework to address data valuation in the context of supervised machine learning. Given a learning algorithm trained on $n$ data points to produce a predictor, we propose data Shapley as a metric to quantify the value of each training datum to the predictor performance. Data Shapley uniquely satisfies several natural properties of equitable data valuation. We develop Monte Carlo and gradient-based methods to efficiently estimate data Shapley values in practical settings where complex learning algorithms, including neural networks, are trained on large datasets. In addition to being equitable, extensive experiments across biomedical, image and synthetic data demonstrate that data Shapley has several other benefits: 1) it is more powerful than the popular leave-one-out or leverage score in providing insight on what data is more valuable for a given learning task; 2) low Shapley value data effectively capture outliers and corruptions; 3) high Shapley value data inform what type of new data to acquire to improve the predictor.

Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data

As governments and industry turn to increased use of automated decision systems, it becomes essential to consider how closely such systems can reproduce human judgment. We identify a core potential failure, finding that annotators label objects differently depending on whether they are being asked a factual question or a normative question. This challenges a natural assumption maintained in many standard machine-learning (ML) data acquisition procedures: that there is no difference between predicting the factual classification of an object and an exercise of judgment about whether an object violates a rule premised on those facts. We find that using factual labels to train models intended for normative judgments introduces a notable measurement error. We show that models trained using factual labels yield significantly different judgments than those trained using normative labels and that the impact of this effect on model performance can exceed that of other factors (e.g., dataset size) that routinely attract attention from ML researchers and practitioners. , Machine learning systems trained with factual features as labels do not reproduce human rule violation judgments on the same data.

Does Predictive Policing Lead to Biased Arrests? Results From a Randomized Controlled Trial

Racial bias in predictive policing algorithms has been the focus of a number of recent news articles, statements of concern by several national organizations (e.g., the ACLU and NAACP), and simulat...

Does Predictive Policing Lead to Biased Arrests? Results From a Randomized Controlled Trial

Racial bias in predictive policing algorithms has been the focus of a number of recent news articles, statements of concern by several national organizations (e.g., the ACLU and NAACP), and simulat...

Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits

Data Shapley provides a principled approach to data valuation and plays a crucial role in data-centric machine learning (ML) research. Data selection is considered a standard application of Data Shapley. However, its data selection performance has shown to be inconsistent across settings in the literature. This study aims to deepen our understanding of this phenomenon. We introduce a hypothesis testing framework and show that Data Shapley’s performance can be no better than random selection without specific constraints on utility functions. We identify a class of utility functions, monotonically transformed modular functions, within which Data Shapley optimally selects data. Based on this insight, we propose a heuristic for predicting Data Shapley’s effectiveness in data selection tasks. Our experiments corroborate these findings, adding new insights into when Data Shapley may or may not succeed.

Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining

Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI. Despite a recent surge of new methods developed in this space, the impact of hyperparameter tuning in these methods remains under-explored. In this work, we present the first large-scale empirical study to understand the hyperparameter sensitivity of common data attribution methods. Our results show that most methods are indeed sensitive to certain key hyperparameters. However, unlike typical machine learning algorithms---whose hyperparameters can be tuned using computationally-cheap validation metrics---evaluating data attribution performance often requires retraining models on subsets of training data, making such metrics prohibitively costly for hyperparameter tuning. This poses a critical open challenge for the practical application of data attribution methods. To address this challenge, we advocate for better theoretical understandings of hyperparameter behavior to inform efficient tuning strategies. As a case study, we provide a theoretical analysis of the regularization term that is critical in many variants of influence function methods. Building on this analysis, we propose a lightweight procedure for selecting the regularization value without model retraining, and validate its effectiveness across a range of standard data attribution benchmarks. Overall, our study identifies a fundamental yet overlooked challenge in the practical application of data attribution, and highlights the importance of careful discussion on hyperparameter selection in future method development.

Optimized Pre-Processing for Discrimination Prevention

Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling discrimination, limiting distortion in individual data samples, and preserving utility. We characterize the impact of limited sample size in accomplishing this objective. Two instances of the proposed optimization are applied to datasets, including one on real-world criminal recidivism. Results show that discrimination can be greatly reduced at a small cost in classification accuracy.

Machine Learning Who to Nudge: Causal vs Predictive Targeting in a Field Experiment on Student Financial Aid Renewal

In many settings, interventions may be more effective for some individuals than others, so that targeting interventions may be beneficial. We analyze the value of targeting in the context of a large-scale field experiment with over 53,000 college students, where the goal was to use "nudges" to encourage students to renew their financial-aid applications before a non-binding deadline. We begin with baseline approaches to targeting. First, we target based on a causal forest that estimates heterogeneous treatment effects and then assigns students to treatment according to those estimated to have the highest treatment effects. Next, we evaluate two alternative targeting policies, one targeting students with low predicted probability of renewing financial aid in the absence of the treatment, the other targeting those with high probability. The predicted baseline outcome is not the ideal criterion for targeting, nor is it a priori clear whether to prioritize low, high, or intermediate predicted probability. Nonetheless, targeting on low baseline outcomes is common in practice, for example because the relationship between individual characteristics and treatment effects is often difficult or impossible to estimate with historical data. We propose hybrid approaches that incorporate the strengths of both predictive approaches (accurate estimation) and causal approaches (correct criterion); we show that targeting intermediate baseline outcomes is most effective in our specific application, while targeting based on low baseline outcomes is detrimental. In one year of the experiment, nudging all students improved early filing by an average of 6.4 percentage points over a baseline average of 37% filing, and we estimate that targeting half of the students using our preferred policy attains around 75% of this benefit.

Distributionally Robust Data Valuation

Data valuation quantifies the contribution of each data point to the performance of a machine learning model. Existing works typically define the value of data by its improvement of the validation performance of the trained model. However, this approach can be impractical to apply in collaborative machine learning and data marketplace since it is difficult for the parties/buyers to agree on a common validation dataset or determine the exact validation distribution a priori. To address this, we propose a distributionally robust data valuation approach to perform data valuation without known/fixed validation distributions. Our approach defines the value of data by its improvement of the distributionally robust generalization error (DRGE), thus providing a worst-case performance guarantee without a known/fixed validation distribution. However, since computing DRGE directly is infeasible, we propose using model deviation as a proxy for the marginal improvement of DRGE (for kernel regression and neural networks) to compute data values. Furthermore, we identify a notion of uniqueness where low uniqueness characterizes low-value data. We empirically demonstrate that our approach outperforms existing data valuation approaches in data selection and data removal tasks on real-world datasets (e.g., housing price prediction, diabetes hospitalization prediction).