The Frontiers of Fairness in Machine Learning

Chouldechova, Alexandra; Roth, Aaron

doi:10.48550/arxiv.1810.08810

Cited by 103 publications

(121 citation statements)

References 13 publications

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…Biases can enter an AI system at any point in its cycle. Empirical findings have shown that data-driven methods can unintentionally encode existing human biases and introduce new ones [Chouldechova and Roth, 2018]. According to [Ferrer et al, 2021], three causes of biases are:…”

Section: Causes Of Bias In Ai Systemsmentioning

confidence: 99%

Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems

Agarwal,

Agarwal

2022

Preprint

View full text Add to dashboard Cite

Decisions made by various Artificial Intelligence (AI) systems greatly influence our day-to-day lives. With the increasing use of AI systems, it becomes crucial to know that they are fair, identify the underlying biases in their decision-making, and create a standardized framework to ascertain their fairness. In this paper, we propose a novel Fairness Score to measure the fairness of a data-driven AI system and a Standard Operating Procedure (SOP) for issuing Fairness Certification for such systems. Fairness Score and audit process standardization will ensure quality, reduce ambiguity, enable comparison and improve the trustworthiness of the AI systems. It will also provide a framework to operationalise the concept of fairness and facilitate the commercial deployment of such systems. Furthermore, a Fairness Certificate issued by a designated third-party auditing agency following the standardized process would boost the conviction of the organizations in the AI systems that they intend to deploy. The Bias Index proposed in this paper also reveals comparative bias amongst the various protected attributes within the dataset. To substantiate the proposed framework, we iteratively train a model on biased and unbiased data using multiple datasets and check that the Fairness Score and the proposed process correctly identify the biases and judge the fairness.

show abstract

Section: Causes Of Bias In Ai Systemsmentioning

confidence: 99%

Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems

Agarwal,

Agarwal

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…There is a growing body of work on fairness in machine learning. Much of the research is on fair supervised methods; see, Chouldechova and Roth (2018); Barocas et al (2019); Donini et al…”

Section: Related Workmentioning

confidence: 99%

Fair Structure Learning in Heterogeneous Graphical Models

Tarzanagh¹,

Balzano²,

Hero³

2021

Preprint

View full text Add to dashboard Cite

Inference of community structure in probabilistic graphical models may not be consistent with fairness constraints when nodes have demographic attributes. Certain demographics may be over-represented in some detected communities and under-represented in others. This paper defines a novel 1 -regularized pseudo-likelihood approach for fair graphical model selection. In particular, we assume there is some community or clustering structure in the true underlying graph, and we seek to learn a sparse undirected graph and its communities from the data such that demographic groups are fairly represented within the communities. Our optimization approach uses the demographic parity definition of fairness, but the framework is easily extended to other definitions of fairness. We establish statistical consistency of the proposed method for both a Gaussian graphical model and an Ising model for, respectively, continuous and binary data, proving that our method can recover the graphs and their fair communities with high probability.

show abstract

“…Bias and fairness issues are crucial as machine learning systems are being increasingly used in sensitive applications (Chouldechova and Roth, 2018). Bias is caused due to pre-existing societal norms (Friedman and Nissenbaum, 1996), data source, data labeling, training algorithms, and postprocessing models.…”

Section: Related Workmentioning

confidence: 99%

“…For example, if we train a model on data that contain labels from two populations -a majority and a minority population -minimizing overall error will fit only the majority population ignoring the minority (Chouldechova and Roth, 2018). Data labeling bias exists when the distribution of the dependent variable in the data source diverges from the ideal distribution (Shah et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Toward Annotator Group Bias in Crowdsourcing

Liu¹,

Thekinen²,

Mollaoglu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Crowdsourcing has emerged as a popular approach for collecting annotated data to train supervised machine learning models. However, annotator bias can lead to defective annotations. Though there are a few works investigating individual annotator bias, the group effects in annotators are largely overlooked. In this work, we reveal that annotators within the same demographic group tend to show consistent group bias in annotation tasks and thus we conduct an initial study on annotator group bias. We first empirically verify the existence of annotator group bias in various real-world crowdsourcing datasets. Then, we develop a novel probabilistic graphical framework GroupAnno to capture annotator group bias with a new extended Expectation Maximization (EM) training algorithm. We conduct experiments on both synthetic and real-world datasets. Experimental results demonstrate the effectiveness of our model in modeling annotator group bias in label aggregation and model learning over competitive baselines.

show abstract

The Frontiers of Fairness in Machine Learning

Cited by 103 publications

References 13 publications

Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems

Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systems

Fair Structure Learning in Heterogeneous Graphical Models

Toward Annotator Group Bias in Crowdsourcing

Contact Info

Product

Resources

About