Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond

• URL: http://arxiv.org/abs/2507.08866v1
• Date: Wed, 09 Jul 2025 15:52:11 GMT
• Title: Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond
• Authors: Marina Ceccon, Giandomenico Cornacchia, Davide Dalle Pezze, Alessandro Fabris, Gian Antonio Susto,
• Abstract summary: We present three common data biases and study their individual and joint effect on algorithmic discrimination.<n>We develop dedicated mechanisms to detect specific types of bias, and combine them into a preliminary construct we refer to as the Data Bias Profile (DBP)<n>This initial formulation serves as a proof of concept for how different bias signals can be systematically documented.
• Score: 42.710392315326104
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legislation and standards on anti-discrimination in AI. Despite this recognition, data biases remain understudied, hindering the development of computational best practices for their detection and mitigation. In this work, we present three common data biases and study their individual and joint effect on algorithmic discrimination across a variety of datasets, models, and fairness measures. We find that underrepresentation of vulnerable populations in training sets is less conducive to discrimination than conventionally affirmed, while combinations of proxies and label bias can be far more critical. Consequently, we develop dedicated mechanisms to detect specific types of bias, and combine them into a preliminary construct we refer to as the Data Bias Profile (DBP). This initial formulation serves as a proof of concept for how different bias signals can be systematically documented. Through a case study with popular fairness datasets, we demonstrate the effectiveness of the DBP in predicting the risk of discriminatory outcomes and the utility of fairness-enhancing interventions. Overall, this article bridges algorithmic fairness research and anti-discrimination policy through a data-centric lens.

Related papers

• Biased Heritage: How Datasets Shape Models in Facial Expression Recognition [13.77824359359967]
  We study bias propagation from datasets to trained models in image-based Facial Expression Recognition systems.<n>We introduce new bias metrics specifically designed for multiclass problems with multiple demographic groups.<n>Our findings suggest that preventing emotion-specific demographic patterns should be prioritized over general demographic balance in FER datasets.
  arXiv  Detail & Related papers  (2025-03-05T12:25:22Z)
• Outlier Detection Bias Busted: Understanding Sources of Algorithmic Bias through Data-centric Factors [28.869581543676947]
  unsupervised outlier detection (OD) has numerous applications in finance, security, etc. This work aims to shed light on the possible sources of unfairness in OD by auditing detection models under different data-centric factors. We find that the OD algorithms under the study all exhibit fairness pitfalls, although differing in which types of data bias they are more susceptible to.
  arXiv  Detail & Related papers  (2024-08-24T20:35:32Z)
• Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations [63.52709761339949]
  We first contribute a dedicated dataset called the Fair Forgery Detection (FairFD) dataset, where we prove the racial bias of public state-of-the-art (SOTA) methods.<n>We design novel metrics including Approach Averaged Metric and Utility Regularized Metric, which can avoid deceptive results.<n>We also present an effective and robust post-processing technique, Bias Pruning with Fair Activations (BPFA), which improves fairness without requiring retraining or weight updates.
  arXiv  Detail & Related papers  (2024-07-19T14:53:18Z)
• Measuring and Mitigating Bias for Tabular Datasets with Multiple Protected Attributes [0.0]
  We focus on datasets that contain multiple protected attributes, such as nationality, age, and sex. New discrimination measures are introduced, guiding researchers and practitioners in choosing the right measure to assess the fairness of the underlying dataset. A novel application of an existing bias mitigation method, FairDo, is presented.
  arXiv  Detail & Related papers  (2024-05-29T17:27:08Z)
• The Impact of Differential Feature Under-reporting on Algorithmic Fairness [86.275300739926]
  We present an analytically tractable model of differential feature under-reporting. We then use to characterize the impact of this kind of data bias on algorithmic fairness. Our results show that, in real world data settings, under-reporting typically leads to increasing disparities.
  arXiv  Detail & Related papers  (2024-01-16T19:16:22Z)
• D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias [57.87117733071416]
  We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases. A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
  arXiv  Detail & Related papers  (2022-08-10T03:41:48Z)
• Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairness [0.0]
  We consider calls to collect more data on demographics to enable algorithmic fairness. We show how these techniques largely ignore broader questions of data governance and systemic oppression.
  arXiv  Detail & Related papers  (2022-04-18T04:50:09Z)
• Information-Theoretic Bias Reduction via Causal View of Spurious Correlation [71.9123886505321]
  We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation. We present a novel debiasing framework against the algorithmic bias, which incorporates a bias regularization loss. The proposed bias measurement and debiasing approaches are validated in diverse realistic scenarios.
  arXiv  Detail & Related papers  (2022-01-10T01:19:31Z)
• Statistical discrimination in learning agents [64.78141757063142]
  Statistical discrimination emerges in agent policies as a function of both the bias in the training population and of agent architecture. We show that less discrimination emerges with agents that use recurrent neural networks, and when their training environment has less bias.
  arXiv  Detail & Related papers  (2021-10-21T18:28:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.