More Data Can Lead Us Astray: Active Data Acquisition in the Presence of Label Bias

An increased awareness concerning risks of algorithmic bias has driven a surge of efforts around bias mitigation strategies. A vast majority of the proposed approaches fall under one of two categories: (1) imposing algorithmic fairness constraints on predictive models, and (2) collecting additional training samples. Most recently and at the intersection of these two categories, methods that propose active learning under fairness constraints have been developed. However, proposed bias mitigation strategies typically overlook the bias presented in the observed labels. In this work, we study fairness considerations of active data collection strategies in the presence of label bias. We first present an overview of different types of label bias in the context of supervised learning systems. We then empirically show that, when overlooking label bias, collecting more data can aggravate bias, and imposing fairness constraints that rely on the observed labels in the data collection process may not address the problem. Our results illustrate the unintended consequences of deploying a model that attempts to mitigate a single type of bias while neglecting others, emphasizing the importance of explicitly differentiating between the types of bias that fairness-aware algorithms aim to address, and highlighting the risks of neglecting label bias during data collection.

Doubting AI Predictions: Influence-Driven Second Opinion Recommendation

Effective human-AI collaboration requires a system design that provides humans with meaningful ways to make sense of and critically evaluate algorithmic recommendations. In this paper, we propose a way to augment human-AI collaboration by building on a common organizational practice: identifying experts who are likely to provide complementary opinions. When machine learning algorithms are trained to predict human-generated assessments, experts' rich multitude of perspectives is frequently lost in monolithic algorithmic recommendations. The proposed approach aims to leverage productive disagreement by (1) identifying whether some experts are likely to disagree with an algorithmic assessment and, if so, (2) recommend an expert to request a second opinion from.

Justice in Misinformation Detection Systems: An Analysis of Algorithms, Stakeholders, and Potential Harms

Faced with the scale and surge of misinformation on social media, many platforms and fact-checking organizations have turned to algorithms for automating key parts of misinformation detection pipelines. While offering a promising solution to the challenge of scale, the ethical and societal risks associated with algorithmic misinformation detection are not well-understood. In this paper, we employ and extend upon the notion of informational justice to develop a framework for explicating issues of justice relating to representation, participation, distribution of benefits and burdens, and credibility in the misinformation detection pipeline. Drawing on the framework: (1) we show how injustices materialize for stakeholders across three algorithmic stages in the pipeline; (2) we suggest empirical measures for assessing these injustices; and (3) we identify potential sources of these harms. This framework should help researchers, policymakers, and practitioners reason about potential harms or risks associated with these algorithms and provide conceptual guidance for the design of algorithmic fairness audits in this domain.

On the Relationship Between Explanations, Fairness Perceptions, and Decisions

It is known that recommendations of AI-based systems can be incorrect or unfair. Hence, it is often proposed that a human be the final decision-maker. Prior work has argued that explanations are an essential pathway to help human decision-makers enhance decision quality and mitigate bias, i.e., facilitate human-AI complementarity. For these benefits to materialize, explanations should enable humans to appropriately rely on AI recommendations and override the algorithmic recommendation when necessary to increase distributive fairness of decisions. The literature, however, does not provide conclusive empirical evidence as to whether explanations enable such complementarity in practice. In this work, we (a) provide a conceptual framework to articulate the relationships between explanations, fairness perceptions, reliance, and distributive fairness, (b) apply it to understand (seemingly) contradictory research findings at the intersection of explanations and fairness, and (c) derive cohesive implications for the formulation of research questions and the design of experiments.

Social Norm Bias: Residual Harms of Fairness-Aware Algorithms

Many modern learning algorithms mitigate bias by enforcing fairness across coarsely-defined groups related to a sensitive attribute like gender or race. However, the same algorithms seldom account for the within-group biases that arise due to the heterogeneity of group members. In this work, we characterize Social Norm Bias (SNoB), a subtle but consequential type of discrimination that may be exhibited by automated decision-making systems, even when these systems achieve group fairness objectives. We study this issue through the lens of gender bias in occupation classification from biographies. We quantify SNoB by measuring how an algorithm's predictions are associated with conformity to gender norms, which is measured using a machine learning approach. This framework reveals that for classification tasks related to male-dominated occupations, fairness-aware classifiers favor biographies written in ways that align with masculine gender norms. We compare SNoB across fairness intervention techniques and show that post-processing interventions do not mitigate this type of bias at all.

The effect of differential victim crime reporting on predictive policing systems

Police departments around the world have been experimenting with forms of place-based data-driven proactive policing for over two decades. Modern incarnations of such systems are commonly known as hot spot predictive policing. These systems predict where future crime is likely to concentrate such that police can allocate patrols to these areas and deter crime before it occurs. Previous research on fairness in predictive policing has concentrated on the feedback loops which occur when models are trained on discovered crime data, but has limited implications for models trained on victim crime reporting data. We demonstrate how differential victim crime reporting rates across geographical areas can lead to outcome disparities in common crime hot spot prediction models. Our analysis is based on a simulation patterned after district-level victimization and crime reporting survey data for Bogot\'a, Colombia. Our results suggest that differential crime reporting rates can lead to a displacement of predicted hotspots from high crime but low reporting areas to high or medium crime and high reporting areas. This may lead to misallocations both in the form of over-policing and under-policing.

Leveraging Expert Consistency to Improve Algorithmic Decision Support

Due to their promise of superior predictive power relative to human assessment, machine learning models are increasingly being used to support high-stakes decisions. However, the nature of the labels available for training these models often hampers the usefulness of predictive models for decision support. In this paper, we explore the use of historical expert decisions as a rich--yet imperfect--source of information, and we show that it can be leveraged to mitigate some of the limitations of learning from observed labels alone. We consider the problem of estimating expert consistency indirectly when each case in the data is assessed by a single expert, and propose influence functions based methodology as a solution to this problem. We then incorporate the estimated expert consistency into the predictive model meant for decision support through an approach we term label amalgamation. This allows the machine learning models to learn from experts in instances where there is expert consistency, and learn from the observed labels elsewhere. We show how the proposed approach can help mitigate common challenges of learning from observed labels alone, reducing the gap between the construct that the algorithm optimizes for and the construct of interest to experts. After providing intuition and theoretical results, we present empirical results in the context of child maltreatment hotline screenings. Here, we find that (1) there are high-risk cases whose risk is considered by the experts but not wholly captured in the target labels used to train a deployed model, and (2) the proposed approach improves recall for these cases.

What's in a Name? Reducing Bias in Bios without Access to Protected Attributes

There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two significant challenges: (1) protected attributes may not be available or it may not be legal to use them, and (2) it is often desirable to simultaneously consider multiple protected attributes, as well as their intersections. In the context of mitigating bias in occupation classification, we propose a method for discouraging correlation between the predicted probability of an individual's true occupation and a word embedding of their name. This method leverages the societal biases that are encoded in word embeddings, eliminating the need for access to protected attributes. Crucially, it only requires access to individuals' names at training time and not at deployment time. We evaluate two variations of our proposed method using a large-scale dataset of online biographies. We find that both variations simultaneously reduce race and gender biases, with almost no reduction in the classifier's overall true positive rate.

Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting

We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic representation bias. To do so, we study the impact on occupation classification of including explicit gender indicators---such as first names and pronouns---in different semantic representations of online biographies. Additionally, we quantify the bias that remains when these indicators are "scrubbed," and describe proxy behavior that occurs in the absence of explicit gender indicators. As we demonstrate, differences in true positive rates between genders are correlated with existing gender imbalances in occupations, which may compound these imbalances.