人工智能的难点之一是确保模型决策是公平的,没有偏见。在研究中,数据集,指标,技术和工具被应用于检测和减轻算法的不公平性和偏见。本研究的目的是检查现有的知识偏见和不公平的机器学习模型,确定缓解方法,公平性指标和支持工具。一项系统性文献综述发现,2017年至2022年间在Scopus、IEEE Xplore、Web of Science和Google Scholar知识库中发表了40篇合格文章。结果显示,ML技术有许多偏见和不公平的检测和缓解方法,在文献中有明确定义的指标,并且可以突出显示不同的指标。我们建议进一步研究,以定义在每种情况下应采用的技术和指标,以标准化和确保机器学习模型的公正性,从而允许最合适的指标在给定的上下文中检测偏见和不公平。
英文摘要:
One of the difficulties of artificial intelligence is to ensure that model decisions are fair and free of bias. In research, datasets, metrics, techniques, and tools are applied to detect and mitigate algorithmic unfairness and bias. This study aims to examine existing knowledge on bias and unfairness in Machine Learning models, identifying mitigation methods, fairness metrics, and supporting tools. A Systematic Literature Review found 40 eligible articles published between 2017 and 2022 in the Scopus, IEEE Xplore, Web of Science, and Google Scholar knowledge bases. The results show numerous bias and unfairness detection and mitigation approaches for ML technologies, with clearly defined metrics in the literature, and varied metrics can be highlighted. We recommend further research to define the techniques and metrics that should be employed in each case to standardize and ensure the impartiality of the machine learning model, thus, allowing the most appropriate metric to detect bias and unfairness in a given context.
Revealing Unfair Models by Mining Interpretable Evidence
Huawei Technologies Canada(华为技术加拿大公司);McMaster University(麦克马斯特大学);University of British Columbia(不列颠哥伦比亚大学);Simon Fraser University(西蒙弗雷泽大学);Tianjin University(天津大学)
Bias-inducing geometries: an exactly solvable data model with fairness implications
University College London(伦敦大学学院);Gatsby Computational Neuroscience Unit(盖茨比计算神经科学中心);Sainsbury Wellcome Centre(桑斯伯里惠康中心);Scuola Internazionale Superiore di Studi Avanzati(国际高等研究学院);Google(谷歌);Bocconi University(博科尼大学)
Adversarial Reweighting Guided by Wasserstein Distance for Bias Mitigation
SCHUFA Holding AG(舒法控股公司);The Open University(开放大学);L3S research center Hannover(汉诺威L3S研究中心);University of Stuttgart(斯图加特大学);Technical University of Munich(慕尼黑工业大学)
Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
Barnard College, Columbia University(哥伦比亚大学巴纳德学院);Georgia Institute of Technology(佐治亚理工学院);Carnegie Mellon University(卡内基梅隆大学);Stanford University(斯坦福大学)
Towards Trustworthy Audio Deepfake Detection: A Systematic Framework for Diagnosing and Mitigating Gender Bias
School of Computing, Wichita State University(维克托利亚州立大学计算机学院);Institut national de la recherche scientifique (INRS-EMT)(国家科学研究机构(INRS-EMT));INRS-UQO Mixed Research Unit on Cybersecurity(INRS-UQO网络安全混合研究单位)
A Systematic Bias of Machine Learning Regression Models and Its Correction: an Application to Imaging-based Brain Age Prediction
University of Maryland(马里兰大学);School of Medicine(医学院);Maryland Psychiatric Research Center(马里兰精神病研究中心);The University of Maryland Institute for Health Computing (UM-IHC)(马里兰大学健康计算研究所)