Fairness in Learning-Based Sequential Decision Algorithms: A Survey

Zhang, Xueru; Liu, Mingyan

doi:10.48550/arxiv.2001.04861

Cited by 8 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is easy to see that αa,ŷ ∈ [0, 1], a ∈ {0, 1}, ŷ ∈ {0, 1}, and it is a feasible point for optimization problem (5). Moreover, we have, This implies that αa,ŷ , a ∈ {0, 1}, ŷ ∈ {0, 1} is not optimal for (5).…”

Section: A4 Restating Theorem 5 For the Statistical Parity (Sp) Fairn...mentioning

confidence: 95%

“…Then, αa,ŷ , a ∈ {0, 1}, ŷ ∈ {0, 1} is the solution to optimization (4). If linear program (5) does not have a solution, then optimization (4) has no solution.…”

Section: Fair Selection Without Privacy Guaranteementioning

confidence: 99%

“…In this section, we assume the applicants have privacy concerns, and their true sensitive attributes cannot be used directly in the decision-making process. 5 Such a scenario has been studied before in classification problems [30,31]. We adopt local differential privacy [16] as the privacy measure.…”

Section: Fair Selection Using Differentially Private Sensitive Attrib...mentioning

confidence: 99%

“…To measure and remedy the unfairness issues in ML, various fairness notions have been proposed. They can be roughly classified into two categories [5]: 1) Individual fairness: it implies that similar individuals should be treated similarly [6,7,8]. 2) Group fairness: it requires that certain statistical measures to be equal across different groups [9,10,11,12,13,14,15].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fair Sequential Selection Using Supervised Learning Models

Khalili¹,

Zhang²,

Abroshan³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We consider a selection problem where sequentially arrived applicants apply for a limited number of positions/jobs. At each time step, a decision maker accepts or rejects the given applicant using a pre-trained supervised learning model until all the vacant positions are filled. In this paper, we discuss whether the fairness notions (e.g., equal opportunity, statistical parity, etc.) that are commonly used in classification problems are suitable for the sequential selection problems. In particular, we show that even with a pre-trained model that satisfies the common fairness notions, the selection outcomes may still be biased against certain demographic groups. This observation implies that the fairness notions used in classification problems are not suitable for a selection problem where the applicants compete for a limited number of positions. We introduce a new fairness notion, "Equal Selection (ES)," suitable for sequential selection problems and propose a post-processing approach to satisfy the ES fairness notion. We also consider a setting where the applicants have privacy concerns, and the decision maker only has access to the noisy version of sensitive attributes. In this setting, we can show that the perfect ES fairness can still be attained under certain conditions.

show abstract

Section: A4 Restating Theorem 5 For the Statistical Parity (Sp) Fairn...mentioning

confidence: 95%

“…Then, αa,ŷ , a ∈ {0, 1}, ŷ ∈ {0, 1} is the solution to optimization (4). If linear program (5) does not have a solution, then optimization (4) has no solution.…”

Section: Fair Selection Without Privacy Guaranteementioning

confidence: 99%

Section: Fair Selection Using Differentially Private Sensitive Attrib...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fair Sequential Selection Using Supervised Learning Models

Khalili¹,

Zhang²,

Abroshan³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…2019; Klare et al, 2012;Ryu et al, 2017;Zhang & Liu, 2020;Zhao et al, 2018;2019b), illustrating the wide existence of unfairness and possible remedies. Algorithmic fairness, focusing on non-discrimination of decision outcomes, comes to the fore in the research community.…”

Section: Introductionmentioning

confidence: 99%

Fairness in Missing Data Imputation

Zhang¹,

Long²

2021

Preprint

View full text Add to dashboard Cite

Missing data are ubiquitous in the era of big data and, if inadequately handled, are known to lead to biased findings and have deleterious impact on data-driven decision makings. To mitigate its impact, many missing value imputation methods have been developed. However, the fairness of these imputation methods across sensitive groups has not been studied. In this paper, we conduct the first known research on fairness of missing data imputation. By studying the performance of imputation methods in three commonly used datasets, we demonstrate that unfairness of missing value imputation widely exists and may be associated with multiple factors. Our results suggest that, in practice, a careful investigation of related factors can provide valuable insights on mitigating unfairness associated with missing data imputation.

show abstract

Bias and Debias in Recommender System: A Survey and Future Directions

Chen¹,

Dong²,

Wang³

et al. 2020

Preprint

173

View full text Add to dashboard Cite

While recent years have witnessed a rapid growth of research papers on recommender system (RS), most of the papers focus on inventing machine learning models to better fit user behavior data. However, user behavior data is observational rather than experimental. This makes various biases widely exist in the data, including but not limited to selection bias, position bias, exposure bias, and popularity bias. Blindly fitting the data without considering the inherent biases will result in many serious issues, e.g., the discrepancy between offline evaluation and online metrics, hurting user satisfaction and trust on the recommendation service, etc. To transform the large volume of research models into practical improvements, it is highly urgent to explore the impacts of the biases and perform debiasing when necessary. When reviewing the papers that consider biases in RS, we find that, to our surprise, the studies are rather fragmented and lack a systematic organization. The terminology "bias" is widely used in the literature, but its definition is usually vague and even inconsistent across papers. This motivates us to provide a systematic survey of existing work on RS biases. In this paper, we first summarize seven types of biases in recommendation, along with their definitions and characteristics. We then provide a taxonomy to position and organize the existing work on recommendation debiasing. Finally, we identify some open challenges and envision some future directions, with the hope of inspiring more research work on this important yet less investigated topic.

show abstract

Fairness in Learning-Based Sequential Decision Algorithms: A Survey

Cited by 8 publications

References 21 publications

Fair Sequential Selection Using Supervised Learning Models

Fair Sequential Selection Using Supervised Learning Models

Fairness in Missing Data Imputation

Bias and Debias in Recommender System: A Survey and Future Directions

Contact Info

Product

Resources

About