The DOI matches its Crossref record; 10 of the 11 references it cites were found in a registry or an index.
Building Classifiers with Independency Constraints
Abstract
In this paper we study the problem of classifier learning where the input data contains unjustified dependencies between some data attributes and the class label. Such cases arise for example when the training data is collected from different sources with different labeling criteria or when the data is generated by a biased decision process. When a classifier is trained directly on such data, these undesirable dependencies will carry over to the classifier's predictions. In order to tackle this problem, we study the classification with independency constraints problem: find an accurate model for which the predictions are independent from a given binary attribute. We propose two solutions for this problem and present an empirical validation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Prior work on detecting discrimination has focused on measuring correlation or mutual information between inputs and outputs [79], discrepancies in the fractions of inputs that produce a given output [18, 19, 39-42, 87-89, 91], or discrepancies in output probability distributions [51].”
From Fairness testing: testing software for discrimination (2017) · cites this paper as [18]
In the citing paper
“Reducing discrimination (CV score) in classifiers [18, 40, 88, 91], as our evaluation has shown, often fails to remove causal discrimination and discrimination against certain groups.”
From Fairness testing: testing software for discrimination (2017) · cites this paper as [18]
Citations
Cites
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 24,190
The foundations of cost-sensitive learning
Elkan, C. (2001) · Cited by 1,945
Domingos, P. (1999) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/312129.312220 · Cited by 1,325
Discrimination-aware data mining
Pedreshi, D., Ruggieri, S., & Turini, F. (2008) · Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1401890.1401959 · Cited by 676
Chan, P. K., & Stolfo, S. J. (1998) · Cited by 452
Classifying 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
Self-citationMeasuring Discrimination in Socially-Sensitive Decision Records
Pedreschi, D., Ruggieri, S., & Turini, F. (2009) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972795.50 · Cited by 175
Nearest Neighbour Classification with Monotonicity Constraints
Duivesteijn, W., & Feelders, A. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87479-9_38 · Cited by 90
Statistical Model for Rough Set Approach to Multicriteria Classification
Dembczyński, K., Greco, S., Kotłowski, W., & Słowiński, R. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74976-9_18 · Cited by 32
Learning decision trees for loss minimization in multi-class problems
Margineantu, D. D., & Dietterich, T. G. (1999) · Cited by 18
Flagged first, then by citations
1 of the 11 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 101–200 of 456
Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment
Gao, Y., Sun, T., Zhao, L., & Hong, S.-S. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3555590 · Cited by 43
“The assumption is that if a model is trained on discrimination-free and “balanced” data, its predictions will not be discriminatory [Calders et al. 2009; Kamiran and Calders 2009].”
BackgroundDang, V. N., Cascarano, A., Mulder, R. H., Cecil, C. A. M., Zuluaga, M. A., Hernández-González, J., & Lekadir, K. (2024) · Scientific Reports · doi:10.1038/s41598-024-58427-7 · Cited by 48
“For instance, reweighing (RW) bias-mitigation technique 33 was used to minimize bias when forecasting future benzodiazepine administrations 30 .”
Techniques for Discrimination-Free Predictive Models
Kamiran, F., Calders, T., & Pechenizkiy, M. (2012) · Studies in applied philosophy, epistemology and rational ethics · doi:10.1007/978-3-642-30487-3_12 · Cited by 36
Self-citationEfficient fair principal component analysis
Kamani, M. M., Haddadpour, F., Forsati, R., & Mahdavi, M. (2022) · Machine Learning · doi:10.1007/s10994-021-06100-9 · Cited by 41
“Some scholars believe data itself could be biased, leading to unfair results; thus, they seek to solve this problem on data level and as a preprocessing step to the main learning task (Dwork et al., 2012; Feldman et al., 2015; Kamiran and Calders, 2009; Calders et al., 2009).”
Towards Fair Truth Discovery from Biased Crowdsourced Answers
Li, Y., Sun, H., & Wang, H. (2020) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3394486.3403102 · Cited by 38
Ensuring Fairness under Prior Probability Shifts
Biswas, A., & Mukherjee, S. (2021) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3461702.3462596 · Cited by 35
ASTRAEA: Grammar-based Fairness Testing
Soremekun, E., Udeshi, S., & Chattopadhyay, S. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2022.3141758 · Cited by 41
“Other approaches propose that classifiers are trained to be independent of sensitive attributes and dependencies in the training data [20], [48], [78].”
BackgroundTowards objective and systematic evaluation of bias in artificial intelligence for medical imaging
Stanley, E. A. M., Souza, R., Winder, A. J., Gulve, V., Amador, K., Wilms, M., & Forkert, N. D. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae165 · Cited by 36
“Reweighing was implemented as proposed by Calders et al. 29 Equations used to calculate sample weight based on bias group and disease class are described in the Supplementary Material.”
MethodTesting Machine Learning Algorithms for Balanced Data Usage
Sharma, A., & Wehrheim, H. (2019) · IEEE International Conference on Software Testing, Verification and Validation (ICST) · doi:10.1109/icst.2019.00022 · Cited by 32
“[13] (called Fa1 and Fa2, respectively, in our tables).”
Pfohl, S., Xu, Y., Foryciarz, A., Ignatiadis, N., Genkins, J., & Shah, N. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533166 · Cited by 30
“Common instantiations of metric parity include equalized odds (Ŷ ⊥ A | Y or S ⊥ A | Y ) [42], which requires both the true positive rates and the false positive rates to be equal across subgroups, demographic parity (Ŷ ⊥ A or S ⊥ A) [43], which requires the rate at which patients are classified as belonging to the pos…”
BackgroundMethodPreCoF: counterfactual explanations for fairness
Goethals, S., Martens, D., & Calders, T. (2023) · Machine Learning · doi:10.1007/s10994-023-06319-8 · Cited by 38
“…metrics include individual fairness (Dwork et al., 2012), which states that similar individuals should be treated similarly, demographic parity (Calders et al., 2009) (which is also called disparate impact (Feldman et al., 2015) or statistical parity (Dwork et al., 2012)) which minimizes the…”
Self-citationFairness Feedback Loops: Training on Synthetic Data Amplifies Bias
Wyllie, S., Shumailov, I., & Papernot, N. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659029 · Cited by 57
“% ‘not male’ and 51.3% ‘attractive.”
InfluentialThrough the Data Management Lens: Experimental Analysis and Evaluation of Fair Classification
Islam, M. T., Fariha, A., Meliou, A., & Salimi, B. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3517841 · Cited by 33
“demographic parity† [24] disparate impact [85], CV score [12] ✓ ✓ ✓”
BackgroundMethodWhat-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
Tang, Z., Zhang, J., & Zhang, K. (2023) · ACM Computing Surveys · doi:10.1145/3597199 · Cited by 42
“Zhang et al. [209] consider Demographic Parity and Equal Opportunity notions of fairness with respect to the dynamics of group-level qualification, in the partially observed Markov decision process (POMDP) setup.”
BackgroundInfluentialAlgorithm Fairness in AI for Medicine and HealthcarePreprint
Chen, R. J., Chen, T., Lipková, J., Wang, J. J., Williamson, D. F. K., Lu, M. Y., Sahai, S., & Mahmood, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.00603 · Cited by 31
Fairness-Enhancing Interventions in Stream Classification
Iosifidis, V., Tran, T. N. H., & Ntoutsi, E. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-27615-7_20 · Cited by 29
“For the massaging techniques, we use NB as a ranker which according to [5] is the best ranker.”
BackgroundMethodA Variational Approach to Privacy and Fairness
Rodríguez-Gálvez, B., Thobaben, R., & Skoglund, M. (2021) · IEEE Information Theory Workshop (ITW) · doi:10.1109/itw48936.2021.9611429 · Cited by 31
Loi, M., & Christen, M. (2019) · Philosophy & Technology · doi:10.1007/s13347-021-00444-9 · Cited by 35
Fairness-Aware Online Meta-learning
Zhao, C., Chen, F., & Thuraisingham, B. M. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467389 · Cited by 28
“For group fairness constraints, two wildly used fair notion families are demographic parity [2] and equality of opportunity (a.”
BackgroundA Fairness-aware Hybrid Recommender SystemPreprint
Farnadi, G., Kouki, P., Thompson, S. K., Srinivasan, S., & Getoor, L. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.09030 · Cited by 28
“To measure the fairness (or unfairness) of the movie recommender system, we use the popular demographic parity measure [25] and a set of new metrics, recently introduced by Yao and Huang [8].”
MethodIdentifying and handling data bias within primary healthcare data using synthetic data generators
Draghi, B., Wang, Z., Myles, P. R., & Tucker, A. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e24164 · Cited by 45
Adversarial learning for counterfactual fairness
Grari, V., Lamprier, S., & Detyniecki, M. (2022) · Machine Learning · doi:10.1007/s10994-022-06206-8 · Cited by 31
“For example, one of the most known objective Demographic parity ensures that the output prediction is not dependent of the sensitive feature [4, 5].”
BackgroundExplainable and Non-explainable Discrimination in Classification
Kamiran, F., & Žliobaitė, I. (2012) · Studies in applied philosophy, epistemology and rational ethics · doi:10.1007/978-3-642-30487-3_8 · Cited by 27
“In the existing discrimination-aware classification (Calders et al., 2009; Calders and Verwer, 2010; Kamiran et al., 2010; Kamiran and Calders, 2010) the discrimination is considered to be present if the acceptance rate for the favored community (denote m for males) and the deprived community (denote f for”
BackgroundInfluentialSelf-citationThe Fairness of Credit Scoring Models
Hurlin, C., Perignon, C., & Saurin, S. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3785882 · Cited by 26
Algorithmic decision making methods for fair credit scoring
Moldovan, D. (2023) · IEEE Access · doi:10.1109/access.2023.3286018 · Cited by 28
“It is centered on the idea of reweighing data without relabeling to remove discrimination (Calders et al., 2009; Kamiran and Calders, 2012).”
BackgroundAdomavičius, G., & Yang, M. (2019) · ACM Transactions on Management Information Systems · doi:10.1145/3519420 · Cited by 34
“Statistical Parity [38, 40, 103, 109] Pr(̂ Y = Good |v = Male ) = Pr(̂ Y = Good |v = Female ) Male and female candidates should be treated similarly on average.”
BackgroundMethodInfluentialBidding strategies with gender nondiscrimination constraints for online ad auctions
Nasr, M., & Tschantz, M. C. (2020) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3351095.3375783 · Cited by 26
“Prior works have looked at how to enforce (proportional) parity constraints on the classifications produced by ML algorithms [2, 3, 12, 20].”
BackgroundDeep fair models for complex data: Graphs labeling and explainable face recognition
Franco, D., Navarin, N., Donini, M., Anguita, D., & Oneto, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.109 · Cited by 26
“The groups are [0-2], [3-9], [10-19], [20-29], [30-39], [40-49], [50-59], [60-69], and [70+].”
BackgroundFranco, D., Oneto, L., Navarin, N., & Anguita, D. (2021) · Entropy · doi:10.3390/e23081047 · Cited by 28
“In our work, we require the representation vector to satisfy the DP constraint [78].”
MethodFair Decision-making Under Uncertainty
Zhang, W., & Weiss, J. C. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00100 · Cited by 29
“Reweighting [26], on the other hand, assigns different weights to the different communities, e.”
BackgroundAchieving Non-Discrimination in Prediction
Zhang, L., Wu, Y., & Wu, X. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/430 · Cited by 25
FACT: A Diagnostic for Group Fairness Trade-offsPreprint
Kim, J. S., Chen, J., & Talwalkar, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03424 · Cited by 32
“Fairness–performance trade-offs have been studied in many specific cases [2, 3, 7, 16, 24, 25, 26], for some definition of fairness, some definition of performance, and for some model.”
Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
Weerts, H., Pfisterer, F., Feurer, M., Eggensperger, K., Bergman, E., Awad, N. H., Vanschoren, J., Pechenizkiy, M., Bischl, B., & Hutter, F. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14747 · Cited by 37
“Constrained learning Constrained learning techniques directly incorporate a fairness constraint in the learning algorithm, either by adapting existing learning paradigms (e.g., Calders et al., 2009; Zafar et al., 2017) or through wrapper methods (e.g., Agarwal et al., 2018).”
MethodSelf-citationDesigning Fairly Fair Classifiers Via Economic Fairness Notions
Hossain, S., Mladenovic, A., & Shah, N. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380228 · Cited by 24
“Such concerns have led to a recent explosion in research on fairness in machine learning [13, 17, 20, 25, 30, 31, 34, 35].”
BackgroundProviding Item-side Individual Fairness for Deep Recommender Systems
Wang, X., & Wang, H. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533079 · Cited by 23
“Group fairness [Calders et al. 2009; Calders and Verwer 2010; Feldman et al. 2015; Kamishima et al. 2011] defines specific groups and require that particular statistics, computed based on model decisions, should be equal for all groups.”
BackgroundReducing Sentiment Bias in Language Models via Counterfactual EvaluationPreprint
Huang, P.-S., Zhang, H., Jiang, R., Stanforth, R., Welbl, J., Rae, J. W., Maini, V., Yogatama, D., & Kohli, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.03064 · Cited by 98
“, 2016) and enforcing independence between sensitive attributes and prediction outputs (Calders et al., 2009; Lemoine et al., 2018; Jiang et al., 2019).”
BackgroundRecent advances in deep learning theoryPreprint
He, F., & Tao, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.10931 · Cited by 51
“They can be roughly categorized into three parts: (1) pre-processing methods, which aims to “rectify” data" before processed by learning algorithms [36, 84, 119, 76, 37, 100, 243, 154]; (2) post-processing methods redress the outputs of learning systems to remove the potential discrimination [233]; and (3) in-processi…”
Prediction performance and fairness heterogeneity in cardiovascular risk models
Kartoun, U., Khurshid, S. S., Kwon, B. C., Patel, A. P., Batra, P., Philippakis, A., Khera, A. V., Ellinor, P. T., Lubitz, S. A., & Ng, K. (2022) · Scientific Reports · doi:10.1038/s41598-022-16615-3 · Cited by 22
Learning Customised Decision Trees for Domain-knowledge Constraints
Nanfack, G., Temple, P., & Frénay, B. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109610 · Cited by 23
Accurate Fairness: Improving Individual Fairness without Trading Accuracy
Li, X., Wu, P., & Su, J. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26674 · Cited by 26
Avoiding Disparity Amplification under Different Worldviews
Yeom, S., & Tschantz, M. C. (2021) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3442188.3445892 · Cited by 36
“ork of Feldman et al. [10] and Zafar et al. [30], who deal with a generalization of the fourfifths rule, called thep% rule, in their efforts to remove disparate impact. On the other hand, many others [2, 3, 16, 31] consider the difference, rather than the ratio, of the positive classification rates. Our discrimination…”
ResultExplainability for fair machine learningPreprint
Begley, T., Schwedes, T., Frye, C., & Feige, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.07389 · Cited by 54
“This set of fairness criteria includes both demographic parity (Calders et al., 2009; Feldman et al., 2015; Kamiran & Calders, 2012; Zafar et al., 2017), which calls for f ( x ) to be unconditionally independent of a , and equalised odds (Hardt et al., 2016), which requires f ( x ) to be…”
BackgroundRaftopoulos, G., Davrazos, G., & Kotsiantis, S. B. (2025) · Electronics · doi:10.3390/electronics14091856 · Cited by 23
Learning Fair and Transferable Representations with Theoretical Guarantees
Oneto, L., Donini, M., Pontil, M., & Maurer, A. (2020) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa49011.2020.00015 · Cited by 20
“We measure fairness according to demographic parity [18] (for an extended analysis of the different fairness definitions see [9], [19]) that requires the probability of possible model decisions to be independent of the sensitive information.”
BackgroundPreventing Discriminatory Decision-making in Evolving Data Streams
Wang, Z., Saxena, N. A., Yu, T., Karki, S., Zetty, T., Haque, I., Zhou, S., KC, D. B., Stockwell, I., Wang, X., et al. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3593984 · Cited by 20
“The most popular ones include massaging [24] and reweighting [6], which have also been extended for addressing bias in the input data before updating the online model in [22].”
BackgroundDiscrimination-aware classification
Kamiran, F. (2011) · doi:10.6100/ir717576 · Cited by 19
“The discrimination-aware techniques discussed in this chapter are published in: IEEE conference on computer, control and communication [46]; Benelux conference on artificial intelligence [47]; the annual machine learning conference of Belgium and The Netherlands [48], and domain driven data mining workshop of IEEE int…”
BackgroundMethodSelf-citationAutomatic Fairness Testing of Machine Learning Models
Sharma, A., & Wehrheim, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64881-7_16 · Cited by 19
Rényi Fair InferencePreprint
Baharlouei, S., Nouiehed, M., Beirami, A., & Razaviyayn, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.12005 · Cited by 19
“Pre-processing methods modify the training data to remove discriminatory information before passing data to the decision-making process Calders et al. (2009); Feldman et al. (2015); Kamiran & Calders (2010; 2009; 2012); Dwork et al. (2012); Calmon et al. (2017); Ruggieri (2014).”
BackgroundMethodInfluentialExposing and Correcting the Gender Bias in Image Captioning Datasets and ModelsPreprint
Bhargava, S., & Forsyth, D. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.00578 · Cited by 49
“Some works [Calders et al., 2009], [Kamiran and Calders, 2009] modify/re-weight the class labels to reduce the influence of biased data.”
BackgroundBayesboost: Identifying and Handling Bias Using Synthetic Data GeneratorsPreprint
Draghi, B., Wang, Z., Myles, P. R., & Tucker, A. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4052302 · Cited by 19
“Existing approaches to deal with these imbalances include de-biasing methods, like Reweighing (Calders et al., 2009), Adversarial Debiasing (Zhang et al.”
MethodVerifying Fairness in Quantum Machine Learning
Guan, J., Fang, W. S., & Ying, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13188-2_20 · Cited by 18
Ferrari, E., Retico, A., & Bacciu, D. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101804 · Cited by 18
“ethnicity) does not influence the outcome of a predictor [19, 20, 21, 22].”
BackgroundNon-Discriminatory Machine Learning Through Convex Fairness Criteria
Goel, N., Yaghini, M., & Faltings, B. V. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11662 · Cited by 18
Classifying Socially Sensitive Data Without Discrimination: An Analysis of a Crime Suspect Dataset
Kamiran, F., Karim, A., Verwer, S., & Goudriaan, H. (2012) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2012.117 · Cited by 18
“In [18], [19], [20], [9], data sampling and massaging techniques are presented for removing discrimination w.”
BackgroundSelf-citationFairness in Ranking under UncertaintyPreprint
Singh, A., Kempe, D., & Joachims, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.06720 · Cited by 23
“The group fairness perspective imposes constraints like demographic parity (Calders et al., 2009; Zliobaite, 2015) and equalized odds (Hardt et al.”
BackgroundTraining Fair Models in Federated Learning without Data Privacy InfringementPreprint
Che, X., Hu, J., Zhou, Z., Zhang, Y., & Chu, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05662 · Cited by 18
“AgnosticFair [15] and FedFB [19] attempt to train models that are fair with respect to demographic parity [22]– [24].”
BackgroundDid You Do Your Homework? Raising Awareness on Software Fairness and Discrimination
Hort, M., & Sarro, F. (2021) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase51524.2021.9678568 · Cited by 19
“In particular, we choose Reweighing [24], [35] and Equalized Odds Post-processing (EqualizedOdds) [30] due to their ability to reduce bias on the Adult dataset and their ease of use (both are publicly available in AIF360 [37]).”
BackgroundMethodUnderstanding Disparate Effects of Membership Inference Attacks and their Countermeasures
Zhong, D., Sun, H., Xu, J., Gong, N. Z., & Wang, H. (2022) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3488932.3501279 · Cited by 20
“Group fairness [7, 9, 10, 23, 36] is concerned with a small number of protected groups (e.”
BackgroundAlgorithmic bias and racial inequality: a critical review
Kasy, M. (2024) · Oxford Review of Economic Policy · doi:10.1093/oxrep/grae031 · Cited by 22
FEAT: A Fairness-Enhancing and Concept-Adapting Decision Tree Classifier
Zhang, W., & Bifet, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61527-7_12 · Cited by 17
Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems
Wang, X., Thain, N., Sinha, A., Prost, F., Ed, H., Chen, J., & Beutel, A. (2021) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3437963.3441732 · Cited by 18
“Demographic parity [14, 50, 54] is a common way of addressing discrimination against protected attributes.”
BackgroundReview of Mathematical frameworks for Fairness in Machine LearningPreprint
del Barrio, E., Gordaliza, P., & Loubes, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.13755 · Cited by 50
“[12, 15, 17, 19, 31, 33, 34, 36, 42, 49, 50, 51, 52, 65, 86, 97]), which can then be used as input to a standard machine learning model.”
MethodTowards Gender Fairness for Mental Health Prediction
Cheong, J., Kuzucu, S., Kalkan, S., & Güneş, H. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/658 · Cited by 17
Individual Fairness Under Uncertainty
Zhang, W., Wang, Z., Kim, J.-Y., Cheng, C., Oommen, T., Ravikumar, P., & Weiss, J. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230621 · Cited by 21
“Examples of this group include data massaging [21], which changes data distribution, an extension called local massag-ing [55], and reweighing [6], which assigns different weights to the communities.”
BackgroundFair Federated Learning with Opposite GAN
Han, M., Zhu, T., & Zhou, W. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111420 · Cited by 17
Horesh, Y., Haas, N., Mishraky, E., Resheff, Y. S., & Lador, S. M. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-43823-4_47 · Cited by 17
“The simplest notion of fairness is demographic parity [4] (Table 1).”
BackgroundFairness of Classification Using Users’ Social Relationships in Online Peer-To-Peer Lending
Li, Y., Ning, Y., Liu, R., Wu, Y., & Wang, H. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366424.3383557 · Cited by 17
“Broadly, the bias mitigation algorithms fall into three categories: (1) pre-processing : the bias in the training data is mitigated [4, 10, 19]; (2) in-processing : the machine learning model is modified by adding fairness as additional constraint [5, 13, 35]; and (3) post-processing : the results…”
BackgroundTuning Fairness by Balancing Target Labels
Kehrenberg, T., Chen, Z., & Quadrianto, N. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.00033 · Cited by 20
“There are many existing models for enforcing demographic parity and equalized odds (Calders et al., 2009; Kamishima et al., 2012; Zafar et al., 2017a,b; Agarwal et al., 2018; Creager et al., 2019).”
BackgroundFairness and privacy preservation for facial images: GAN-based methods
Tian, H., Zhu, T., & Zhou, W. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102902 · Cited by 16
Comprehensive Validation on Reweighting Samples for Bias Mitigation via AIF360
Blow, C. H., Qian, L., Gibson, C. A., Obiomon, P., & Dong, X. (2024) · Applied Sciences · doi:10.3390/app14093826 · Cited by 15
The Long Arc of Fairness: Formalisations and Ethical Discourse
Schwöbel, P., & Remmers, P. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3534635 · Cited by 16
“ness propose outcome-based criteria such as demographic parity [7] or equality of opportunity [22] (see Table 1 for formalisations of these and other metrics).”
BackgroundSearch-based Automatic Repair for Fairness and Accuracy in Decision-making Software
Hort, M., Zhang, J. M., Sarro, F., & Harman, M. (2024) · Empirical Software Engineering · doi:10.1007/s10664-023-10419-3 · Cited by 15
MLCHECK– Property-Driven Testing of Machine Learning Classifiers
Sharma, A., Demir, C., Ngomo, A.-C. N., & Wehrheim, H. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00123 · Cited by 20
Fairness with censorship and group constraints
Zhang, W., & Weiss, J. C. (2023) · Knowledge and Information Systems · doi:10.1007/s10115-023-01842-5 · Cited by 13
“Reweighting [15], on the other hand, assigns different weights to the different communities, e.”
BackgroundBest practices for responsible machine learning in credit scoring
Valdrighi, G., Ribeiro, A. M., Pereira, J. S. B., Guardieiro, V., Hendricks, A., Filho, D. M., Garcia, J. D. N., Bocca, F. F., Veronese, T. B., Wanner, L., et al. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11520-y · Cited by 24
“Proposed by Calders et al. [2009], consists of adding weights to each training data sample according to the sensitive attribute.”
Oneto, L., Donini, M., Pontil, M., & Shawe-Taylor, J. S. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.12.137 · Cited by 13
“Several measures of fairness of a classifier have been studied in the literature [59, 60] like the Demographic Parity (DPa) [61], the Equal Odds (EOd) and the Equal Opportunity (EOp) [47], the Disparate Treatment, Impact, and Mistreatment [48], among others.”
Faking Fairness via Stealthily Biased Sampling
Fukuchi, K., Hara, S., & Maehara, T. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i01.5377 · Cited by 13
“In the experiments, we adopted the demographic parity (DP) [6] as the fairness metric for auditing.”
BackgroundMethodFast and Efficient MMD-Based Fair PCA via Optimization over Stiefel Manifold
Lee, J.-H., Kim, G., Olfat, M., Hasegawa‐Johnson, M., & Yoo, C. D. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i7.20699 · Cited by 14
A Stochastic Alternating Balance k-Means Algorithm for Fair Clustering
Liu, S., & Vicente, L. N. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-24866-5_6 · Cited by 13
On Fairness-Aware Learning for Non-discriminative Decision-Making
Zhang, W., Tang, X., & Wang, J. (2019) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2019.00157 · Cited by 13
“Instead of intrusively relabeling the instances, reweighting [4] assigns different weights to different communities to alleviate the bias towards favored communities for the sake of benefiting the classification of deprived communities.”
BackgroundFlexible and Adaptive Fairness-aware Learning in Non-stationary Data Streams
Zhang, W., Zhang, M., Zhang, J., Liu, Z., Chen, Z., Wang, J., Raff, E., & Messina, E. (2020) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai50040.2020.00069 · Cited by 15
“These studies can be broadly categorized into pre-processing approaches [6], [7], in-processing approaches [8], [9] and post-processing approaches [10], [11] based on whether the elimination of discrimination are focusing on the data level, the algorithm level and the output of model, respectively.”
BackgroundInformation-Theoretic Bias Reduction via Causal View of Spurious Correlation
Seo, S., Lee, J., & Han, B. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20115 · Cited by 16
Data Management for Causal Algorithmic FairnessPreprint
Salimi, B., Howe, B., & Suciu, D. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.07924 · Cited by 20
“Fairness Metric Description Demographic Parity (DP) [7] S⊥⊥O a.”
BackgroundFair Classification with Noisy Protected Attributes: A Framework with Provable GuaranteesPreprint
Celis, L. E., Huang, L., Keswani, V., & Vishnoi, N. K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04778 · Cited by 13
“An alternate approach considers changing the composition of the dataset itself in order to correct for known biases in representation, and popular methods include re-labeling/re-weighting approach of [9, 24, 25], the repair methods of [19, 35], or optimization based methods such as [13].”
MethodFAC-fed: Federated adaptation for fairness and concept drift aware stream classification
Badar, M., Nejdl, W., & Fisichella, M. (2023) · Machine Learning · doi:10.1007/s10994-023-06360-7 · Cited by 12
“…in issues of fairness and trustworthiness of learning algorithms, a substantial body of work already exists in this domain (Calders et al., 2009; Chakraborty et al., 2021; Hajian et al., 2015; Iosifidis & Ntoutsi, 2020; Kamiran & Calders, 2009, 2012; Kamiran et al., 2012; Zhang et al., 2019).”
BackgroundMaximum Entropy Policy for Long-Term Fairness in Interactive Recommender Systems
Shi, X., Liu, Q., Xie, H. L., Bai, Y., & Shang, M. (2024) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2024.3349636 · Cited by 13
Lazy Data Practices Harm Fairness Research
Simson, J., Fabris, A., & Kern, C. A. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658931 · Cited by 13
“Comparing model fairness under different data processing scenarios yields completely different results.”
ResultInteligencia artificial y Administración de Justicia: ¿Quo vadis, justitia?
Castellano, P. S. (2021) · IDP Revista de Internet Derecho y Política · doi:10.7238/idp.v0i33.373817 · Cited by 19
Application of fairness to healthcare, organizational justice, and finance: A survey
Birzhandi, P., & Cho, Y.-S. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119465 · Cited by 16
FairLP: Towards Fair Link Prediction on Social Network Graphs
Li, Y., Wang, X., Ning, Y., & Wang, H. (2022) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v16i1.19321 · Cited by 12
“…the existing bias mitigation methods fall broadly into three categories: (1) pre-processing : the bias in the training data is mitigated (Calders, Kamiran, and Pechenizkiy 2009; Kamiran and Calders 2009; Feld-man et al. 2015); (2) in-processing : the machine learning model is modified by…”
BackgroundBipartite Ranking Fairness Through a Model Agnostic Ordering Adjustment
Cui, S., Pan, W., Zhang, C., & Wang, F. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3290949 · Cited by 13
“Examples of such proxies include the proportion of examples classified as positive [24], [25], as well as the prediction performance metrics such as true/false positive rates and error rates [7], [11], [26], [27], [28].”
BackgroundUnderstanding and mitigating multi-sided exposure bias in recommender systems
Mansoury, M. (2022) · ACM SIGWEB Newsletter · doi:10.1145/3566100.3566103 · Cited by 13
The Influences of Task Design on Crowdsourced Judgement: A Case Study of Recidivism Risk Evaluation
Duan, X., Ho, C.-J., & Yin, M. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3512239 · Cited by 12
“In particular, when a participant’s ∆POS is zero, her recidivism judgements satisfy the fairness definition of demographic parity [8].”
BackgroundCapuchin: Causal Database Repair for Algorithmic FairnessPreprint
Salimi, B., Rodriguez, L., Howe, B., & Suciu, D. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.08283 · Cited by 12
“Fairness Metric Description Demographic Parity (DP) [5] S⊥⊥O a.”
BackgroundFairness Assessment for Artificial Intelligence in Financial IndustryPreprint
Zhang, Y., & Zhou, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.07211 · Cited by 12
Zhang, B., Yu, R., Sun, H., Li, Y., Xu, J., & Wang, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.08855 · Cited by 15
“Methodologically, they fall broadly into three categories: (1) pre-processing: the bias in the training data is mitigated [7, 21, 35]; (2) in-processing: the machine learning model is modified by adding fairness as additional constraint [8, 26, 61]; and (3) post-processing: the results of a previously trained classifi…”
BackgroundInfluentialFairness guarantee in multi-class classificationPreprint
Denis, C., Élie, R., Hebiri, M., & Hu, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.13642 · Cited by 20
“We consider DP constraint [Calders et al., 2009] that asks for independence of the prediction function from the sensitive feature S.”
BackgroundMethodInfluentialFair Assortment PlanningPreprint
Chen, Q., Golrezaei, N., & Susan, F. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4072912 · Cited by 12
Evaluating and mitigating unfairness in multimodal remote mental health assessments
Jiang, Z., Seyedi, S. S., Griner, E. L., Abbasi, A., Rad, A. B., Kwon, H., Cotes, R. O., & Clifford, G. D. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000413 · Cited by 13
“Another type of fairness metric defines fairness as the fair prediction/classification performance of privileged and unprivileged groups, among which equality of odds (EO) and equality of opportunity [30] are the most adopted, which gauge fairness by examining disparities in true positive rates and…”
BackgroundBias audit laws: how effective are they at preventing bias in automated employment decision tools?
Hilliard, A., Gulley, A., Koshiyama, A., & Kazim, E. (2024) · International Review of Law Computers & Technology · doi:10.1080/13600869.2024.2403053 · Cited by 14
“For example, Calders, Kamiran, and Pechenizkiy (2009) proposed a post-processing approach to achieving independence of predictions and protected attributes where some data labels in the training are changed, or mas-saged , such that the model makes predictions that are no longer dependent on the…”
Metadata
- Authors
- Calders, T., Kamiran, F., & Pechenizkiy, M.
- Affiliations
- Eindhoven University of Technology (NL)
- Venue
- 2009 IEEE International Conference on Data Mining Workshops
- Publisher
- IEEE
- Published
- 2009-12
- Pages
- 13-18
- ISSN
- 2375-9259 (ISSN-L)
- OpenAlex
- W2116666691
- Cited by
- 468
- References
- 11
- Citations by year
- 2026: 16 · 2025: 45 · 2024: 64 · 2023: 51 · 2022: 65 · 2021: 79 · 2020: 60 · 2019: 48 · 2018: 17 · 2017: 5 · 2016: 2 · 2015: 2 · 2014: 1 · 2012: 5
- FWCI
- 2.58
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE ... International Conference on Data Mining workshops (publishedVersion)
- TU/e Research Portal (publishedVersion)
- TU/e Research Portal (submittedVersion)
- Dépôt institutionnel de l'Université libre de Bruxelles (Université Libre de Bruxelles) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Physical Sciences › Computer Science › Information Systems › Data Mining and Machine Learning Applications
- Keywords
- biased training data, classifier training
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
