Exploring Fairness Interventions in Open Source Projects

• URL: http://arxiv.org/abs/2507.07026v1
• Date: Wed, 09 Jul 2025 16:57:59 GMT
• Title: Exploring Fairness Interventions in Open Source Projects
• Abstract summary: bias in machine learning models can have adverse effects in sectors such as criminal justice and healthcare.<n>A range of machine learning fairness interventions have been developed, aiming to mitigate bias and promote the creation of more equitable models.<n>Despite the growing availability of these interventions, their adoption in real-world applications remains limited.
• Score: 4.637328271312331
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The deployment of biased machine learning (ML) models has resulted in adverse effects in crucial sectors such as criminal justice and healthcare. To address these challenges, a diverse range of machine learning fairness interventions have been developed, aiming to mitigate bias and promote the creation of more equitable models. Despite the growing availability of these interventions, their adoption in real-world applications remains limited, with many practitioners unaware of their existence. To address this gap, we systematically identified and compiled a dataset of 62 open source fairness interventions and identified active ones. We conducted an in-depth analysis of their specifications and features to uncover considerations that may drive practitioner preference and to identify the software interventions actively maintained in the open source ecosystem. Our findings indicate that 32% of these interventions have been actively maintained within the past year, and 50% of them offer both bias detection and mitigation capabilities, mostly during inprocessing.

Related papers

• From Awareness to Action: Understanding and Overcoming the Research-Practice Gap in Algorithmic Fairness for Public Health [3.4137115855910767]
  Algorithmic fairness is essential for responsible ML-driven public health research, yet its practical implementation remains limited.<n>We conduct a sequential mixed-methods study comprising expert interviews, an online survey, and systematic mapping.<n>Our analysis shows that fairness remains weakly institutionalized, translation mechanisms are externally driven, and system-level priorities continue to emphasize accuracy over fairness.
  arXiv  Detail & Related papers  (2026-05-02T10:00:21Z)
• Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents [1.1677624591989955]
  Small open-weight models perform poorly on automated Linux privilege escalation.<n>We present a systematic empirical study of whether targeted system-level and prompting interventions can bridge this performance gap.
  arXiv  Detail & Related papers  (2026-04-29T19:54:27Z)
• Partial Identification Approach to Counterfactual Fairness Assessment [50.88100567472179]
  We introduce a Bayesian approach to bound unknown counterfactual fairness measures with high confidence.<n>Our results reveal a positive (spurious) effect on the COMPAS score when changing race to African-American (from all others) and a negative (direct causal) effect when transitioning from young to old age.
  arXiv  Detail & Related papers  (2025-09-30T18:35:08Z)
• Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers [17.243744418309593]
  We assess the privacy risks of fairness-enhanced binary classifiers via membership inference attacks (MIAs) and attribute inference attacks (AIAs)<n>We uncover a potential threat mechanism that exploits prediction discrepancies between fair and biased models, leading to advanced attack results for both MIAs and AIAs.<n>Our study exposes the under-explored privacy threats in fairness studies, advocating for thorough evaluations of potential security vulnerabilities before model deployments.
  arXiv  Detail & Related papers  (2025-03-08T10:21:21Z)
• An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces [5.874782446136915]
  Pivotal to the success of transferring RL offline is mitigating overestimation bias in value estimates for state-action pairs absent from data. Factorised discrete action spaces have received relatively little attention, despite many real-world problems naturally having factorisable actions. We present the case for a factorised approach and conduct an extensive empirical evaluation of several offline techniques adapted to the factorised setting.
  arXiv  Detail & Related papers  (2024-11-17T14:31:14Z)
• DispaRisk: Auditing Fairness Through Usable Information [21.521208250966918]
  DispaRisk is a framework designed to assess the potential risks of disparities in datasets during the initial stages of the Machine Learning pipeline.<n>Our findings demonstrate DispaRisk's capabilities to identify datasets with a high risk of discrimination, detect model families prone to biases within an ML pipeline, and enhance the explainability of these bias risks.
  arXiv  Detail & Related papers  (2024-05-20T20:56:01Z)
• 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)
• Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability [82.29775890542967]
  Estimating personalized effects of treatments is a complex, yet pervasive problem. Recent developments in the machine learning literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools. We use post-hoc feature importance methods to identify features that influence the model's predictions.
  arXiv  Detail & Related papers  (2022-06-16T17:59:05Z)
• A Framework for Fairness: A Systematic Review of Existing Fair AI Solutions [4.594159253008448]
  A large portion of fairness research has gone to producing tools that machine learning practitioners can use to audit for bias while designing their algorithms. There is a lack of application of these fairness solutions in practice. This review provides an in-depth summary of the algorithmic bias issues that have been defined and the fairness solution space that has been proposed.
  arXiv  Detail & Related papers  (2021-12-10T17:51:20Z)
• SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data [83.50281440043241]
  We study the problem of inferring heterogeneous treatment effects from time-to-event data. We propose a novel deep learning method for treatment-specific hazard estimation based on balancing representations.
  arXiv  Detail & Related papers  (2021-10-26T20:13:17Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)
• Towards Unbiased Visual Emotion Recognition via Causal Intervention [63.74095927462]
  We propose a novel Emotion Recognition Network (IERN) to alleviate the negative effects brought by the dataset bias. A series of designed tests validate the effectiveness of IERN, and experiments on three emotion benchmarks demonstrate that IERN outperforms other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-07-26T10:40:59Z)
• Technical Challenges for Training Fair Neural Networks [62.466658247995404]
  We conduct experiments on both facial recognition and automated medical diagnosis datasets using state-of-the-art architectures. We observe that large models overfit to fairness objectives, and produce a range of unintended and undesirable consequences.
  arXiv  Detail & Related papers  (2021-02-12T20:36:45Z)

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.