L. Elisa Celis’s research while affiliated with Yale University and other places

Real-world applications of machine learning (ML) algorithms often propagate negative stereotypes and social biases against marginalized groups. In response, the field of fair machine learning has proposed technical solutions for a variety of settings that aim to correct the biases in algorithmic predictions. These solutions remove the dependence of the final prediction on the protected attributes (like gender or race) and/or ensure that prediction performance is similar across demographic groups. Yet, recent studies assessing the impact of these solutions in practice demonstrate their ineffectiveness in tackling real-world inequalities. Given this lack of real-world success, it is essential to take a step back and question the design motivations of algorithmic fairness interventions. We use popular legal anti-discriminatory principles, specifically anti-classification and anti-subordination principles, to study the motivations of fairness interventions and their applications. The anti-classification principle suggests addressing discrimination by ensuring that decision processes and outcomes are independent of the protected attributes of individuals. The anti-subordination principle, on the other hand, argues that decision-making policies can provide equal protection to all only by actively tackling societal hierarchies that enable structural discrimination, even if that requires using protected attributes to address historical inequalities. Through a survey of the fairness mechanisms and applications, we assess different components of fair ML approaches from the perspective of these principles. We argue that the observed shortcomings of fair ML algorithms are similar to the failures of anti-classification policies and that these shortcomings constitute violations of the anti-subordination principle. Correspondingly, we propose guidelines for algorithmic fairness interventions to adhere to the anti-subordination principle. In doing so, we hope to bridge critical concepts between legal frameworks for non-discrimination and fairness in machine learning.

This paper considers the scenario in which there are multiple institutions, each with a limited capacity for candidates, and candidates, each with preferences over the institutions. A central entity evaluates the utility of each candidate to the institutions, and the goal is to select candidates for each institution in a way that maximizes utility while also considering the candidates' preferences. The paper focuses on the setting in which candidates are divided into multiple groups and the observed utilities of candidates in some groups are biased--systematically lower than their true utilities. The first result is that, in these biased settings, prior algorithms can lead to selections with sub-optimal true utility and significant discrepancies in the fraction of candidates from each group that get their preferred choices. Subsequently, an algorithm is presented along with proof that it produces selections that achieve near-optimal group fairness with respect to preferences while also nearly maximizing the true utility under distributional assumptions. Further, extensive empirical validation of these results in real-world and synthetic settings, in which the distributional assumptions may not hold, are presented.

We consider the problem of subset selection where one is given multiple rankings of items and the goal is to select the highest ``quality'' subset. Score functions from the multiwinner voting literature have been used to aggregate rankings into quality scores for subsets. We study this setting of subset selection problems when, in addition, rankings may contain systemic or unconscious biases toward a group of items. For a general model of input rankings and biases, we show that requiring the selected subset to satisfy group fairness constraints can improve the quality of the selection with respect to unbiased rankings. Importantly, we show that for fairness constraints to be effective, different multiwinner score functions may require a drastically different number of rankings: While for some functions, fairness constraints need an exponential number of rankings to recover a close-to-optimal solution, for others, this dependency is only polynomial. This result relies on a novel notion of ``smoothness'' of submodular functions in this setting that quantifies how well a function can ``correctly'' assess the quality of items in the presence of bias. The results in this paper can be used to guide the choice of multiwinner score functions for the subset selection setting considered here; we additionally provide a tool to empirically enable this.

Automatically assigning tasks to people is challenging because human performance can vary across tasks for many reasons. This challenge is further compounded in real-life settings in which no oracle exists to assess the quality of human decisions and task assignments made. Instead, we find ourselves in a "closed" decision-making loop in which the same fallible human decisions we rely on in practice must also be used to guide task allocation. How can imperfect and potentially biased human decisions train an accurate allocation model? Our key insight is to exploit weak prior information on human-task similarity to bootstrap model training. We show that the use of such a weak prior can improve task allocation accuracy, even when human decision-makers are fallible and biased. We present both theoretical analysis and empirical evaluation over synthetic data and a social media toxicity detection task. Results demonstrate the efficacy of our approach.

An increasing amount of work studies fairness in socio-technical settings from a computational perspective. This work has introduced a variety of metrics to measure fairness in different settings. Most of these metrics, however, do not account for the interactions between individuals or evaluate any underlying network's effect on the outcomes measured. While a wide body of work studies the organization of individuals into a network structure and how individuals access resources in networks, the impact of network structure on fairness has been largely unexplored. We introduce templates for group fairness metrics that account for network structure. More specifically, we present two types of group fairness metrics that measure distinct yet complementary forms of bias in networks. The first type of metric evaluates how access to others in the network is distributed across groups. The second type of metric evaluates how groups distribute their interactions across other groups, and hence captures inter-group biases. We find that ignoring the network can lead to spurious fairness evaluations by either not capturing imbalances in influence and reach illuminated by the first type of metric, or by overlooking interaction biases as evaluated by the second type of metric. Our empirical study illustrates these pronounced differences between network and non-network evaluations of fairness.

As Artificial Intelligence (AI) proliferates across important social institutions, many of the most powerful AI systems available are difficult to interpret for end-users and engineers alike. Here, we sought to characterize public attitudes towards AI interpretability. Across seven studies (N = 2475), we demonstrate robust and positive attitudes towards interpretable AI among non-experts that generalize across a variety of real-world applications and follow predictable patterns. Participants value interpretability positively across different levels of AI autonomy and accuracy, and rate interpretability as more important for AI decisions involving high stakes and scarce resources. Crucially, when AI interpretability trades off against AI accuracy, participants prioritize accuracy over interpretability under the same conditions driving positive attitudes towards interpretability in the first place: amidst high stakes and scarce resources. These attitudes could drive a proliferation of AI systems making high-impact ethical decisions that are difficult to explain and understand.

Elections are the central institution of democratic processes, and often the elected body -- in either public or private governance -- is a committee of individuals. To ensure the legitimacy of elected bodies, the electoral processes should guarantee that diverse groups are represented, in particular members of groups that are marginalized due to gender, ethnicity, or other socially salient attributes. To address this challenge of representation, we have designed a novel participatory electoral process coined the Representation Pact, implemented with the support of a computational system. That process explicitly enables voters to flexibly decide on representation criteria in a first round, and then lets them vote for candidates in a second round. After the two rounds, a counting method is applied, which selects the committee of candidates that maximizes the number of votes received in the second round, conditioned on satisfying the criteria provided in the first round. With the help of a detailed use case that applied this process in a primary election of 96 representatives in Switzerland, we explain how this method contributes to fairness in political elections by achieving a better "descriptive representation". Further, based on this use case, we identify lessons learnt that are applicable to participatory computational systems used in societal or political contexts. Good practices are identified and presented.

In real-world classification settings, individuals respond to classifier predictions by updating their features to increase their likelihood of receiving a particular (positive) decision (at a certain cost). Yet, when different demographic groups have different feature distributions or different cost functions, prior work has shown that individuals from minority groups often pay a higher cost to update their features. Fair classification aims to address such classifier performance disparities by constraining the classifiers to satisfy statistical fairness properties. However, we show that standard fairness constraints do not guarantee that the constrained classifier reduces the disparity in strategic manipulation cost. To address such biases in strategic settings and provide equal opportunities for strategic manipulation, we propose a constrained optimization framework that constructs classifiers that lower the strategic manipulation cost for the minority groups. We develop our framework by studying theoretical connections between group-specific strategic cost disparity and standard selection rate fairness metrics (e.g., statistical rate and true positive rate). Empirically, we show the efficacy of this approach over multiple real-world datasets.