Rawlsian Fair Adaptation of Deep Learning Classifiers

Shah, Kulin; Gupta, Pooja; Deshpande, Amit; Bhattacharyya, Chiranjib

doi:10.1145/3461702.3462592

Cited by 8 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hardness of adapting Rawlsian principles into algorithms is apparent from these works. For example, Shah et al [16] propose a classifier that minimises the error rate of the worst-off sensitive group; they call this a Rawls classifier. Hashimoto et al [7] employ Rawlsian ideas to mitigate the amplification of representation disparity Fig.…”

Section: Rawlsian Ideas Of Fairness In MLmentioning

confidence: 99%

Exploring Rawlsian Fairness for K-Means Clustering

Simoes

Deepak

MacCárthaigh

2022

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

We conduct an exploratory study that looks at incorporating John Rawls' ideas on fairness into existing unsupervised machine learning algorithms. Our focus is on the task of clustering, specifically the k-means clustering algorithm. To the best of our knowledge, this is the first work that uses Rawlsian ideas in clustering. Towards this, we attempt to develop a postprocessing technique i.e., one that operates on the cluster assignment generated by the standard k-means clustering algorithm. Our technique perturbs this assignment over a number of iterations to make it fairer according to Rawls' difference principle while minimally affecting the overall utility. As the first step, we consider two simple perturbation operators -R1 and R2 -that reassign examples in a given cluster assignment to new clusters; R1 assigning a single example to a new cluster, and R2 a pair of examples to new clusters. Our experiments on a sample of the Adult dataset demonstrate that both operators make meaningful perturbations in the cluster assignment towards incorporating Rawls' difference principle, with R2 being more efficient than R1 in terms of the number of iterations. However, we observe that there is still a need to design operators that make significantly better perturbations. Nevertheless, both operators provide good baselines for designing and comparing any future operator, and we hope our findings would aid future work in this direction.

show abstract

Section: Rawlsian Ideas Of Fairness In MLmentioning

confidence: 99%

Exploring Rawlsian Fairness for K-Means Clustering

Simoes

Deepak

MacCárthaigh

2022

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

show abstract

A guide to formulating fairness in an optimization model

Chen

Hooker

2023

Ann Oper Res

View full text Add to dashboard Cite

Optimization models typically seek to maximize overall benefit or minimize total cost. Yet fairness is an important element of many practical decisions, and it is much less obvious how to express it mathematically. We provide a critical survey of various schemes that have been proposed for formulating ethics-related criteria, including those that integrate efficiency and fairness concerns. The survey covers inequality measures, Rawlsian maximin and leximax criteria, convex combinations of fairness and efficiency, alpha fairness and proportional fairness (also known as the Nash bargaining solution), Kalai–Smorodinsky bargaining, and recently proposed utility-threshold and fairness-threshold schemes for combining utilitarian with maximin or leximax criteria. The paper also examines group parity metrics that are popular in machine learning. We present what appears to be the best practical approach to formulating each criterion in a linear, nonlinear, or mixed integer programming model. We also survey axiomatic and bargaining derivations of fairness criteria from the social choice literature while taking into account interpersonal comparability of utilities. Finally, we cite relevant philosophical and ethical literature where appropriate.

show abstract

Algorithmic fairness datasets: the story so far

Fabris

Messina

Silvello

et al. 2022

Data Min Knowl Disc

View full text Add to dashboard Cite

Data-driven algorithms are studied and deployed in diverse domains to support critical decisions, directly impacting people’s well-being. As a result, a growing community of researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of risks and opportunities of automated decision-making for historically disadvantaged populations. Progress in fair machine learning and equitable algorithm design hinges on data, which can be appropriately used only if adequately documented. Unfortunately, the algorithmic fairness community, as a whole, suffers from a collective data documentation debt caused by a lack of information on specific resources (opacity) and scatteredness of available information (sparsity). In this work, we target this data documentation debt by surveying over two hundred datasets employed in algorithmic fairness research, and producing standardized and searchable documentation for each of them. Moreover we rigorously identify the three most popular fairness datasets, namely Adult, COMPAS, and German Credit, for which we compile in-depth documentation. This unifying documentation effort supports multiple contributions. Firstly, we summarize the merits and limitations of Adult, COMPAS, and German Credit, adding to and unifying recent scholarship, calling into question their suitability as general-purpose fairness benchmarks. Secondly, we document hundreds of available alternatives, annotating their domain and supported fairness tasks, along with additional properties of interest for fairness practitioners and researchers, including their format, cardinality, and the sensitive attributes they encode. We summarize this information, zooming in on the tasks, domains, and roles of these resources. Finally, we analyze these datasets from the perspective of five important data curation topics: anonymization, consent, inclusivity, labeling of sensitive attributes, and transparency. We discuss different approaches and levels of attention to these topics, making them tangible, and distill them into a set of best practices for the curation of novel resources.

show abstract

Rawlsian Fair Adaptation of Deep Learning Classifiers

Cited by 8 publications

References 17 publications

Exploring Rawlsian Fairness for K-Means Clustering

Exploring Rawlsian Fairness for K-Means Clustering

A guide to formulating fairness in an optimization model

Algorithmic fairness datasets: the story so far

Contact Info

Product

Resources

About