Search

We study the problem of post-processing a supervised machine-learned regressor to maximize fair binary classification at all decision thresholds. Specifically, we show that by decreasing the statistical distance between each group's score distributions, we can increase fair performance across all thresholds at once, and that we can do so without a significant decrease in accuracy. To this end, we introduce a formal measure of distributional parity, which captures the degree of similarity in the distributions of classifications for different protected groups. In contrast to prior work, which has been limited to studies of demographic parity across all thresholds, our measure applies to a large class of fairness metrics. Our main result is to put forward a novel post-processing algorithm based on optimal transport, which provably maximizes distributional parity. We support this result with experiments on several fairness benchmarks.

Face recognition systems are deployed across the world by government agencies and contractors for sensitive and impactful tasks, such as surveillance and database matching. Despite their widespread use, these systems are known to exhibit bias across a range of sociodemographic dimensions, such as gender and race. Nonetheless, an array of works proposing pre-processing, training, and post-processing methods have failed to close these gaps. Here, we take a very different approach to this problem, identifying that both architectures and hyperparameters of neural networks are instrumental in reducing bias. We first run a large-scale analysis of the impact of architectures and training hyperparameters on several common fairness metrics and show that the implicit convention of choosing high-accuracy architectures may be suboptimal for fairness. Motivated by our findings, we run the first neural architecture search for fairness, jointly with a search for hyperparameters. We output a suite of models which Pareto-dominate all other competitive architectures in terms of accuracy and fairness. Furthermore, we show that these models transfer well to other face recognition datasets with similar and distinct protected attributes. We release our code and raw result files so that researchers and practitioners can replace our fairness metrics with a bias measure of their choice.

The study was designed to experimentally determine the rate of growth as it pertained to visual motor development of an experimental and a control group by using a resource teacher as the vehicle to administer the remediation. The study lasted for 7 months. Beery's Developmental Test of Visual-Motor Integration was administered in a pretest and posttest format to 93 first grade students. The experimental group experienced the Frostig Developmental remediation materials using either the first level of the eye or motor coordination materials. The experimental group met in groups of about 11 children for a period of 30 minutes twice weekly. Seven samples of remediation are included in the form of photographs. Comparison of pretest and posttest scores showed that the experimental group gained 3 months of visual motor growth above the control group. The growth was considered statistically significant. (CB)

The design of optimal auctions is a problem of interest in economics, game theory and computer science. Despite decades of effort, strategyproof, revenue-maximizing auction designs are still not known outside of restricted settings. However, recent methods using deep learning have shown some success in approximating optimal auctions, recovering several known solutions and outperforming strong baselines when optimal auctions are not known. In addition to maximizing revenue, auction mechanisms may also seek to encourage socially desirable constraints such as allocation fairness or diversity. However, these philosophical notions neither have standardization nor do they have widely accepted formal definitions. In this paper, we propose PreferenceNet, an extension of existing neural-network-based auction mechanisms to encode constraints using (potentially human-provided) exemplars of desirable allocations. In addition, we introduce a new metric to evaluate an auction allocations' adherence to such socially desirable constraints and demonstrate that our proposed method is competitive with current state-of-the-art neural-network based auction designs. We validate our approach through human subject research and show that we are able to effectively capture real human preferences. Our code is available at https://github.com/neeharperi/PreferenceNet, Comment: This work has been accepted to Neural Information Processing Systems (NeurIPS) 2021. First two authors contributed equally

Clustering is a fundamental problem in unsupervised machine learning, and fair variants of it have recently received significant attention due to its societal implications. In this work we introduce a novel definition of individual fairness for clustering problems. Specifically, in our model, each point $j$ has a set of other points $\mathcal{S}_j$ that it perceives as similar to itself, and it feels that it is fairly treated if the quality of service it receives in the solution is $��$-close (in a multiplicative sense, for a given $��\geq 1$) to that of the points in $\mathcal{S}_j$. We begin our study by answering questions regarding the structure of the problem, namely for what values of $��$ the problem is well-defined, and what the behavior of the \emph{Price of Fairness (PoF)} for it is. For the well-defined region of $��$, we provide efficient and easily-implementable approximation algorithms for the $k$-center objective, which in certain cases enjoy bounded-PoF guarantees. We finally complement our analysis by an extensive suite of experiments that validates the effectiveness of our theoretical results., To appear at AISTATS 2022

Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been proposed for bypassing facial recognition systems. However, existing methods fail on full-scale systems and commercial APIs. We develop our own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases. Additionally, we release an easy-to-use webtool that significantly degrades the accuracy of Amazon Rekognition and the Microsoft Azure Face Recognition API, reducing the accuracy of each to below 1%., Comment: Published as a conference paper at ICLR 2021

As machine learning (ML) systems take a more prominent and central role in contributing to life-impacting decisions, ensuring their trustworthiness and accountability is of utmost importance. Explanations sit at the core of these desirable attributes of a ML system. The emerging field is frequently called ``Explainable AI (XAI)'' or ``Explainable ML.'' The goal of explainable ML is to intuitively explain the predictions of a ML system, while adhering to the needs to various stakeholders. Many explanation techniques were developed with contributions from both academia and industry. However, there are several existing challenges that have not garnered enough interest and serve as roadblocks to widespread adoption of explainable ML. In this short paper, we enumerate challenges in explainable ML from an industry perspective. We hope these challenges will serve as promising future research directions, and would contribute to democratizing explainable ML., Comment: Presented at JOURNE workshop at MLSYS 2021 (https://sites.google.com/view/workshop-journe/home)

We provide a polynomial-time, scalable algorithm for equilibrium computation in multi-agent influence games on networks, extending work of Bindel, Kleinberg, and Oren (2015) from the single-agent to the multi-agent setting. In games of influence, agents have limited advertising budget to influence the initial predisposition of nodes in some network towards their products, but the eventual decisions of the nodes are determined by the stationary state of DeGroot opinion dynamics on the network, which takes over after the seeding (Ahmadinejad et al. 2014, 2015). In multi-agent systems, how should agents spend their budgets to seed the network to maximize their utility in anticipation of other advertising agents and the network dynamics? We show that Nash equilibria of this game are pure and (under weak assumptions) unique, and can be computed in polynomial time; we test our model by computing equilibria using mirror descent for the two-agent case on random graphs.

Counterfactual explanations (CFEs) are an emerging technique under the umbrella of interpretability of machine learning (ML) models. They provide ``what if'' feedback of the form ``if an input datapoint were $x'$ instead of $x$, then an ML model's output would be $y'$ instead of $y$.'' Counterfactual explainability for ML models has yet to see widespread adoption in industry. In this short paper, we posit reasons for this slow uptake. Leveraging recent work outlining desirable properties of CFEs and our experience running the ML wing of a model monitoring startup, we identify outstanding obstacles hindering CFE deployment in industry., Comment: Presented at CHI HCXAI 2021 workshop

Restless and collapsing bandits are often used to model budget-constrained resource allocation in settings where arms have action-dependent transition probabilities, such as the allocation of health interventions among patients. However, state-of-the-art Whittle-index-based approaches to this planning problem either do not consider fairness among arms, or incentivize fairness without guaranteeing it. We thus introduce ProbFair, a probabilistically fair policy that maximizes total expected reward and satisfies the budget constraint while ensuring a strictly positive lower bound on the probability of being pulled at each timestep. We evaluate our algorithm on a real-world application, where interventions support continuous positive airway pressure (CPAP) therapy adherence among patients, as well as on a broader class of synthetic transition matrices. We find that ProbFair preserves utility while providing fairness guarantees.