An official website of the United States government
As artificial intelligence (AI) assisted search and recommender systems have become ubiquitous in workplaces and everyday lives, understanding and accounting for fairness has gained increasing attention in the design and evaluation of such systems. While there is a growing body of computing research on measuring system fairness and biases associated with data and algorithms, the impact of human biases that go beyond traditional machine learning (ML) pipelines still remain understudied. In this Perspective Paper, we seek to develop a two-sided fairness framework that not only characterizes data and algorithmic biases, but also highlights the cognitive and perceptual biases that may exacerbate system biases and lead to unfair decisions. Within the framework, we also analyze the interactions between human and system biases in search and recommendation episodes. Built upon the two-sided framework, our research synthesizes intervention and intelligent nudging strategies applied in cognitive and algorithmic debiasing, and also proposes novel goals and measures for evaluating the performance of systems in addressing and proactively mitigating the risks associated with biases in data, algorithms, and bounded rationality. This paper uniquely integrates the insights regarding human biases and system biases into a cohesive framework and extends the concept of fairness from human-centered perspective. The extended fairness framework better reflects the challenges and opportunities in users’ interactions with search and recommender systems of varying modalities. Adopting the two-sided approach in information system design has the potential to enhancing both the effectiveness in online debiasing and the usefulness to boundedly rational users engaging in information-intensive decision-making.
more »
« less
Goal Orientation for Fair Machine Learning Algorithms
A key challenge facing the use of machine learning (ML) in organizational selection settings (e.g., the processing of loan or job applications) is the potential bias against (racial and gender) minorities. To address this challenge, a rich literature of Fairness-Aware ML (FAML) algorithms has emerged, attempting to ameliorate biases while maintaining the predictive accuracy of ML algorithms. Almost all existing FAML algorithms define their optimization goals according to a selection task, meaning that ML outputs are assumed to be the final selection outcome. In practice, though, ML outputs are rarely used as-is. In personnel selection, for example, ML often serves a support role to human resource managers, allowing them to more easily exclude unqualified applicants. This effectively assigns to ML a screening rather than a selection task. It might be tempting to treat selection and screening as two variations of the same task that differ only quantitatively on the admission rate. This paper, however, reveals a qualitative difference between the two in terms of fairness. Specifically, we demonstrate through conceptual development and mathematical analysis that miscategorizing a screening task as a selection one could not only degrade final selection quality but also result in fairness problems such as selection biases within the minority group. After validating our findings with experimental studies on simulated and real-world data, we discuss several business and policy implications, highlighting the need for firms and policymakers to properly categorize the task assigned to ML in assessing and correcting algorithmic biases.
more »
« less
- Award ID(s):
- 2309853
- PAR ID:
- 10495931
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- Production and Operations Management
- ISSN:
- 1059-1478
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Ranking algorithms in online platforms serve not only users on the demand side, but also items on the supply side. While ranking has traditionally presented items in an order that maximizes their utility to users, the uneven interactions that different items receive as a result of such a ranking can pose item fairness concerns. Moreover, interaction is affected by various forms of bias, two of which have received considerable attention: position bias and selection bias. Position bias occurs due to lower likelihood of observation for items in lower ranked positions. Selection bias occurs because interaction is not possible with items below an arbitrary cutoff position chosen by the front-end application at deployment time (i.e., showing only the top-kitems). A less studied, third form of bias, trust bias, is equally important, as it makes interaction dependent on rank even after observation, by influencing the item’s perceived relevance. To capture interaction disparity in the presence of all three biases, in this paper we introduce a flexible fairness metric. Using this metric, we develop a post-processing algorithm that optimizes fairness in ranking through greedy exploration and allows a tradeoff between fairness and utility. Our algorithm outperforms state-of-the-art fair ranking algorithms on several datasets.more » « less
-
null (Ed.)Graph mining is an essential component of recommender systems and search engines. Outputs of graph mining models typically provide a ranked list sorted by each item's relevance or utility. However, recent research has identified issues of algorithmic bias in such models, and new graph mining algorithms have been proposed to correct for bias. As such, algorithm developers need tools that can help them uncover potential biases in their models while also exploring the impacts of correcting for biases when employing fairness-aware algorithms. In this paper, we present FairRankVis, a visual analytics framework designed to enable the exploration of multi-class bias in graph mining algorithms. We support both group and individual fairness levels of comparison. Our framework is designed to enable model developers to compare multi-class fairness between algorithms (for example, comparing PageRank with a debiased PageRank algorithm) to assess the impacts of algorithmic debiasing with respect to group and individual fairness. We demonstrate our framework through two usage scenarios inspecting algorithmic fairness.more » « less
-
Deep neural networks (DNNs) are increasingly used in real-world applications (e.g. facial recognition). This has resulted in concerns about the fairness of decisions made by these models. Various notions and measures of fairness have been proposed to ensure that a decision-making system does not disproportionately harm (or benefit) particular subgroups of the population. In this paper, we argue that traditional notions of fairness that are only based on models' outputs are not sufficient when the model is vulnerable to adversarial attacks. We argue that in some cases, it may be easier for an attacker to target a particular subgroup, resulting in a form of robustness bias. We show that measuring robustness bias is a challenging task for DNNs and propose two methods to measure this form of bias. We then conduct an empirical study on state-of-the-art neural networks on commonly used real-world datasets such as CIFAR-10, CIFAR-100, Adience, and UTKFace and show that in almost all cases there are subgroups (in some cases based on sensitive attributes like race, gender, etc) which are less robust and are thus at a disadvantage. We argue that this kind of bias arises due to both the data distribution and the highly complex nature of the learned decision boundary in the case of DNNs, thus making mitigation of such biases a non-trivial task. Our results show that robustness bias is an important criterion to consider while auditing real-world systems that rely on DNNs for decision making. Code to reproduce all our results can be found here: https://github.com/nvedant07/Fairness-Through-Robustnessmore » « less
-
As machine learning becomes more widely adopted across domains, it is critical that researchers and ML engineers think about the inherent biases in the data that may be perpetuated by the model. Recently, many studies have shown that such biases are also imbibed in Graph Neural Network (GNN) models if the input graph is biased, potentially to the disadvantage of underserved and underrepresented communities. In this work, we aim to mitigate the bias learned by GNNs by jointly optimizing two different loss functions: one for the task of link prediction and one for the task of demographic parity. We further implement three different techniques inspired by graph modification approaches: the Global Fairness Optimization (GFO), Constrained Fairness Optimization (CFO), and Fair Edge Weighting (FEW) models. These techniques mimic the effects of changing underlying graph structures within the GNN and offer a greater degree of interpretability over more integrated neural network methods. Our proposed models emulate microscopic or macroscopic edits to the input graph while training GNNs and learn node embeddings that are both accurate and fair under the context of link recommendations. We demonstrate the effectiveness of our approach on four real world datasets and show that we can improve the recommendation fairness by several factors at negligible cost to link prediction accuracy.more » « less
