Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
As virtually all aspects of our lives are increasingly impacted by algorithmic decision making systems, it is incumbent upon us as a society to ensure such systems do not become instruments of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. We consider the problem of determining whether the decisions made by such systems are discriminatory, through the lens of causal models. We introduce two definitions of group fairness grounded in causality: fair on average causal effect (FACE), and fair on average causal effect on the treated (FACT). We use the Rubin-Neyman potential outcomes framework for the analysis of cause-effect relationships to robustly estimate FACE and FACT. We demonstrate the effectiveness of our proposed approach on synthetic data. Our analyses of two real-world data sets, the Adult income data set from the UCI repository (with gender as the protected attribute), and the NYC Stop and Frisk data set (with race as the protected attribute), show that the evidence of discrimination obtained by FACE and FACT, or lack thereof, is often in agreement with the findings from other studies. We further show that FACT, being somewhat more nuanced compared to FACE, can yield findings of discrimination that differ from those obtained using FACE.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Estimating causal effects of treatments in randomized and nonrandomized studies
Rubin, D. B. (1974) · Journal of Educational Psychology · doi:10.1037/h0037350 · Cited by 9,436 · cited 1×
“ect(FACE), and in a protected group, faironaveragecausaleffectonthetreated(FACT), both with respect to a protected attribute (e.g., gender, race). We use the Rubin-Neyman potential outcomes framework [20, 45, 49] for robust estimation of FACE and FACT. We demonstrate the effectiveness of the proposed approach in detec…”
MethodMarginal Structural Models and Causal Inference in Epidemiology
Robins, J. M., Hernán, M. Á., & Brumback, B. (2000) · Epidemiology · doi:10.1097/00001648-200009000-00011 · Cited by 5,581 · cited 2×
“correctly specified, then β̂ is an unbiased estimator of the average causal effect [39].”
BackgroundMethodMatching Methods for Causal Inference: A Review and a Look Forward
Stuart, E. A. (2010) · Statistical Science · doi:10.1214/09-sts313 · Cited by 5,478 · cited 2×
“Among the graphical criteria, we use quantile-quantile (QQ), and jitter plots recommended by [17, 51].”
BackgroundMethodStatistics and Causal Inference
Holland, P. W. (1986) · Journal of the American Statistical Association · doi:10.1080/01621459.1986.10478354 · Cited by 5,293 · cited 1×
“1This is called the Fundamental Problem of Causal Inference (FPCI) from observational data [18].”
BackgroundMatchIt : Nonparametric Preprocessing for Parametric Causal Inference
Ho, D. E., Imai, K., King, G., & Stuart, E. A. (2011) · Journal of Statistical Software · doi:10.18637/jss.v042.i08 · Cited by 4,385 · cited 3×
“would be statistically consistent [17].”
MethodCausal Inference for Statistics, Social, and Biomedical Sciences: An Introduction
Imbens, G. W., & Rubin, D. B. (2015) · doi:10.1017/cbo9781139025751 · Cited by 4,210
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Barocas, S., & Selbst, A. D. (2014) · doi:10.2139/ssrn.2477899 · Cited by 3,048
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundBayesian inference for causal effects: The role of randomization
Rubin, D. B. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344064 · Cited by 2,503
Using Propensity Scores to Help Design Observational Studies: Application to the Tobacco Litigation
Rubin, D. B. (2001) · Health Services and Outcomes Research Methodology · doi:10.1023/a:1020363010465 · Cited by 2,228 · cited 3×
“atchIt (version 3.0.2) [17] with all parameters set to their default values unless otherwise noted: (i) Exact Matching (EM); (ii) Nearest Neighbor Matching (NNM) with propensity score [43]. Following [48], we estimated the propensity scores using the logit link and transformed them to the linear scale. Then, we ran NN…”
BackgroundMethodInfluentialCausal Inference Using Potential Outcomes: Design, Modeling, Decisions
Rubin, D. B. (2005) · Journal of the American Statistical Association · doi:10.1198/016214504000001880 · Cited by 2,173 · cited 1×
“ect(FACE), and in a protected group, faironaveragecausaleffectonthetreated(FACT), both with respect to a protected attribute (e.g., gender, race). We use the Rubin-Neyman potential outcomes framework [20, 45, 49] for robust estimation of FACE and FACT. We demonstrate the effectiveness of the proposed approach in detec…”
MethodFair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159 · cited 2×
“rotected attribute and data, enforcing certain definitions of fairness can actually increase discrimination [28]. Second, different definitions of fairness can be impossible to satisfy simultaneously [4, 8, 26]. Many of these difficulties can be attributed to the fact that fairness criteria are based solely on the joi…”
BackgroundCertifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundRandomization Analysis of Experimental Data: The Fisher Randomization Test Comment
Rubin, D. B. (1980) · Journal of the American Statistical Association · doi:10.2307/2287653 · Cited by 1,368
Kusner, M. J., Loftus, J. R., Russell, C., & Silva, R. (2017) · arXiv · doi:10.48550/arxiv.1703.06856 · Cited by 995 · cited 5×
“. We introduce two explicitly causal definitions for fairness “on average” in a population or a protected group (as opposed to causal definitions of individual fairness, e.g., counterfactual fairness [28]) with respect to a protected attribute (e.g., gender, race). Let Y(a) i andY(a ′) i be the potential outcomes of a…”
BackgroundMethodResultInfluentialFairness in Criminal Justice Risk Assessments: The State of the Art
Berk, R., Heidari, H., Jabbari, S., Kearns, M., & Roth, A. (2021) · Sociological Methods & Research · doi:10.1177/0049124118782533 · Cited by 988 · cited 3×
“, race, gender, on the basis of the legal notions of disparate treatment or disparate impact [3] (see [3, 4, 32, 40, 60] for reviews).”
BackgroundInherent trade-offs in the fair determination of risk scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2017) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2017.43 · Cited by 943 · cited 1×
“Second, different definitions of fairness can be impossible to satisfy simultaneously [4, 8, 26].”
BackgroundInherent Trade-Offs in the Fair Determination of Risk Scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2016) · arXiv · doi:10.48550/arxiv.1609.05807 · Cited by 941
Fairness-Aware Classifier with Prejudice Remover Regularizer
Kamishima, T., Akaho, S., Asoh, H., & Sakuma, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33486-3_3 · Cited by 694 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundFairness Constraints: Mechanisms for Fair Classification
Zafar, M. B., Valera, I., Rodriguez, M. G., & Gummadi, K. P. (2015) · arXiv · doi:10.48550/arxiv.1507.05259 · Cited by 645 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundZafar, M. B., Valera, I., Gomez Rodriguez, M., & Gummadi, K. P. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052660 · Cited by 632 · cited 1×
“e legal notions of disparate treatment or disparate impact [3] (see [3, 4, 32, 40, 60] for reviews). Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], re…”
BackgroundVanderWeele, T. J., & Robinson, W. R. (2014) · Epidemiology · doi:10.1097/ede.0000000000000105 · Cited by 567
Building Classifiers with Independency Constraints
Calders, T., Kamiran, F., & Pechenizkiy, M. (2009) · 2009 IEEE International Conference on Data Mining Workshops · doi:10.1109/icdmw.2009.83 · Cited by 468 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundClassifying without discriminating
Kamiran, F., & Calders, T. (2009) · 2009 2nd International Conference on Computer, Control and Communication · doi:10.1109/ic4.2009.4909197 · Cited by 409 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundAvoiding Discrimination through Causal Reasoning
Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., & Schölkopf, B. (2017) · arXiv · doi:10.48550/arxiv.1706.02744 · Cited by 358 · cited 1×
“, [25, 28] have sought to design machine learning algorithms that yield predictive models that are demonstrably fair.”
BackgroundA multidisciplinary survey on discrimination analysis
Romei, A., & Ruggieri, S. (2014) · The Knowledge Engineering Review · doi:10.1017/s0269888913000039 · Cited by 288 · cited 1×
“finitions that quantify fairness to avoid discrimination with respect to protectedattributes, e.g., race, gender, on the basis of the legal notions of disparate treatment or disparate impact [3] (see [3, 4, 32, 40, 60] for reviews). Some examples include: fairness through unawareness [14], individual fairness [11], eq…”
BackgroundJohndrow, J. E., & Lum, K. (2019) · The Annals of Applied Statistics · doi:10.1214/18-aoas1201 · Cited by 141 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundDwork, C., & Ilvento, C. (2019) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2019.33 · Cited by 91 · cited 1×
“Some examples include: fairness through unawareness [14], individual fairness [11], equalized odds [15, 54], calibration [8], demographic (or statistical) parity [6, 21–23], the 80% rule (disparate impact) [13, 55], representational fairness [33, 56], and fairness under composition [12].”
BackgroundInterventions over Predictions: Reframing the Ethical Debate for Actuarial Risk Assessment
Barabas, C., Dinakar, K., Ito, J., Virza, M., & Zittrain, J. (2017) · arXiv · doi:10.48550/arxiv.1712.08238 · Cited by 87 · cited 2×
“at depends merely on the joint probability distribution is not necessarily capable of detecting discrimination. Hence, it is tempting to approach the problem of fairness through the lens of causality [1]. Answering questions of fairness through the lens of causality entails replacing the question “Is the decision disc…”
BackgroundMethodPath-Specific Counterfactual Fairness
Chiappa, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017801 · Cited by 16 · cited 1×
“This assumption, used in existing literature [7, 34, 35, 38], is a rather natural one to make in our setting.”
Method
Cited by
Data collection and quality challenges in deep learning: a data-centric AI perspective
Whang, S. E., Roh, Y., Song, H., & Lee, J.-G. (2023) · The VLDB Journal · doi:10.1007/s00778-022-00775-9 · Cited by 573
Recent Advancements in Emerging Technologies for Healthcare Management Systems: A Survey
Junaid, S. B., Imam, A. A., Balogun, A. O., De Silva, L. C., Surakat, Y. A., Kumar, G., Abdulkarim, M., Shuaibu, A. N., Garba, A., Sahalu, Y., et al. (2022) · Healthcare · doi:10.3390/healthcare10101940 · Cited by 353
Secure and robust machine learning for healthcare: A survey
Qayyum, A., Qadir, J., Bilal, M., & Al-Fuqaha, A. (2021) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2020.3013489 · Cited by 59
Secure and Robust Machine Learning for Healthcare: A Survey
Qayyum, A., Qadir, J., Bilal, M., & Al-Fuqaha, A. (2020) · arXiv · doi:10.48550/arxiv.2001.08103 · Cited by 59
COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation
Wang, N., Wang, Q., Wang, Y.-C., Sanjabi, M., Liu, J., Firooz, H., Wang, H., & Nie, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.819 · Cited by 2
Metadata
- Authors
- Khademi, A., Lee, S., Foley, D., & Honavar, V.
- Venue
- The World Wide Web Conference
- Publisher
- ACM
- Published
- 2019-05-13
- Pages
- 2907-2914
- OpenAlex
- W2912887944
- Cited by
- 83
- References
- 31
- FWCI
- 11.46
- Type
- conference paper
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.