An official website of the United States government
AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protected group, explanations may include features that demonstrate this bias, but when biases are realized through proxy features, the relationship between this proxy feature and the protected one may be less clear to a human. In this work, we study the effect of the presence of protected and proxy features on participants’ perception of model fairness and their ability to improve demographic parity over an AI alone. Further, we examine how different treatments—explanations, model bias disclosure and proxy correlation disclosure—affect fairness perception and parity. We find that explanations help people detect direct but not indirect biases. Additionally, regardless of bias type, explanations tend to increase agreement with model biases. Disclosures can help mitigate this effect for indirect biases, improving both unfairness recognition and decision-making fairness. We hope that our findings can help guide further research into advancing explanations in support of fair human-AI decision-making.
more »
« less
This content will become publicly available on June 30, 2025
Leveraging Simulation Data to Understand Bias in Predictive Models of Infectious Disease Spread
The spread of infectious diseases is a highly complex spatiotemporal process, difficult to understand, predict, and effectively respond to. Machine learning and artificial intelligence (AI) have achieved impressive results in other learning and prediction tasks; however, while many AI solutions are developed for disease prediction, only a few of them are adopted by decision-makers to support policy interventions. Among several issues preventing their uptake, AI methods are known to amplify the bias in the data they are trained on. This is especially problematic for infectious disease models that typically leverage large, open, and inherently biased spatiotemporal data. These biases may propagate through the modeling pipeline to decision-making, resulting in inequitable policy interventions. Therefore, there is a need to gain an understanding of how the AI disease modeling pipeline can mitigate biased input data, in-processing models, and biased outputs. Specifically, our vision is to develop a large-scale micro-simulation of individuals from which human mobility, population, and disease ground-truth data can be obtained. From this complete dataset—which may not reflect the real world—we can sample and inject different types of bias. By using the sampled data in which bias is known (as it is given as the simulation parameter), we can explore how existing solutions for fairness in AI can mitigate and correct these biases and investigate novel AI fairness solutions. Achieving this vision would result in improved trust in such models for informing fair and equitable policy interventions.
more »
« less
- PAR ID:
- 10545700
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM Transactions on Spatial Algorithms and Systems
- Volume:
- 10
- Issue:
- 2
- ISSN:
- 2374-0353
- Page Range / eLocation ID:
- 1 to 22
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
With an increased focus on incorporating fairness in machine learning models, it becomes imperative not only to assess and mitigate bias at each stage of the machine learning pipeline but also to understand the downstream impacts of bias across stages. Here we consider a general, but realistic, scenario in which a predictive model is learned from (potentially biased) training data, and model predictions are assessed post-hoc for fairness by some auditing method. We provide a theoretical analysis of how a specific form of data bias, differential sampling bias, propagates from the data stage to the prediction stage. Unlike prior work, we evaluate the downstream impacts of data biases quantitatively rather than qualitatively and prove theoretical guarantees for detection. Under reasonable assumptions, we quantify how the amount of bias in the model predictions varies as a function of the amount of differential sampling bias in the data, and at what point this bias becomes provably detectable by the auditor. Through experiments on two criminal justice datasets– the well-known COMPAS dataset and historical data from NYPD’s stop and frisk policy– we demonstrate that the theoretical results hold in practice even when our assumptions are relaxed.more » « less
-
The increased availability of datasets during the COVID-19 pandemic enabled machine-learning approaches for modeling and forecasting infectious diseases. However, such approaches are known to amplify the bias in the data they are trained on. Bias in such input data like clinical case data for COVID-19 is difficult to measure due to disparities in testing availability, reporting standards, and healthcare access among different populations and regions. Furthermore, the way such biases may propagate through the modeling pipeline to decision-making is relatively unknown. Therefore, we present a system that leverages a highly detailed agent-based model (ABM) of infectious disease spread in a city to simulate the collection of biased clinical case data where the bias is known. Our system allows users to load either a pre-selected region or select their own (using OpenStreetMap data for the environment and census data for the population), specify population and infectious disease parameters, and the degree(s) to which different populations will be overrepresented or underrepresented in the case data. In addition to the system, we provide a large number of benchmark datasets that produce case data at different levels of bias for different regions. Wehope that infectious disease modelers will use these datasets to investigate how well their models are robust to data bias or whether their model is overfit to biased data.more » « less
-
Biased AI models result in unfair decisions. In response, a number of algorithmic solutions have been engineered to mitigate bias, among which the Synthetic Minority Oversampling Technique (SMOTE) has been studied, to an extent. Although the SMOTE technique and its variants have great potentials to help improve fairness, there is little theoretical justification for its success. In addition, formal error and fairness bounds are not clearly given. This paper attempts to address both issues. We prove and demonstrate that synthetic data generated by oversampling underrepresented groups can mitigate algorithmic bias in AI models, while keeping the predictive errors bounded. We further compare this technique to the existing state-of-the-art fair AI techniques on five datasets using a variety of fairness metrics. We show that this approach can effectively improve fairness even when there is a significant amount of label and selection bias, regardless of the baseline AI algorithm.more » « less
-
Datasets can be biased due to societal inequities, human biases, under-representation of minorities, etc. Our goal is to certify that models produced by a learning algorithm are pointwise-robust to dataset biases. This is a challenging problem: it entails learning models for a large, or even infinite, number of datasets, ensuring that they all produce the same prediction. We focus on decision-tree learning due to the interpretable nature of the models. Our approach allows programmatically specifying \emph{bias models} across a variety of dimensions (e.g., label-flipping or missing data), composing types of bias, and targeting bias towards a specific group. To certify robustness, we use a novel symbolic technique to evaluate a decision-tree learner on a large, or infinite, number of datasets, certifying that each and every dataset produces the same prediction for a specific test point. We evaluate our approach on datasets that are commonly used in the fairness literature, and demonstrate our approach's viability on a range of bias models.more » « less
