SLIDE: a surrogate fairness constraint to ensure fairness consistency
Not on the map. Why?
Abstract (arXiv)
As they have a vital effect on social decision makings, AI algorithms should be not only accurate and but also fair. Among various algorithms for fairness AI, learning a prediction model by minimizing the empirical risk (e.g., cross-entropy) subject to a given fairness constraint has received much attention. To avoid computational difficulty, however, a given fairness constraint is replaced by a surrogate fairness constraint as the 0-1 loss is replaced by a convex surrogate loss for classification problems. In this paper, we investigate the validity of existing surrogate fairness constraints and propose a new surrogate fairness constraint called SLIDE, which is computationally feasible and asymptotically valid in the sense that the learned model satisfies the fairness constraint asymptotically and achieves a fast convergence rate. Numerical experiments confirm that the SLIDE works well for various benchmark datasets.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 63 references that are in the map. First posted on arXiv 7 Feb 2022.
Builds on
30 of 63 references.
References · 30
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Equality of Opportunity in Supervised Learningcited by 2,000
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
- 2014Certifying and removing disparate impactcited by 715
- 2018A Reductions Approach to Fair Classificationcited by 585
- 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
- 2017On Fairness and Calibrationcited by 406
- 2017Algorithmic decision making and the cost of fairnesscited by 402
- 2018Learning Adversarially Fair and Transferable Representationscited by 353
- 2018Empirical Risk Minimization under Fairness Constraintscited by 226
- 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
18 more
- 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
- 2018Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionalitycited by 160
- 2018Classification with Fairness Constraints: A Meta-Algorithm with Provable Guaranteescited by 146
- 2020Algorithmic Fairnesscited by 143
- 2019Wasserstein Fair Classificationcited by 131
- 2021Fair Mixup: Fairness via Interpolationcited by 109
- 2016A Confidence-Based Approach for Balancing Fairness and Accuracycited by 73
- 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
- 2016Satisfying Real-world Goals with Dataset Constraintscited by 68
- 2019Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classificationcited by 60
- 2018Two-Player Games for Efficient Non-Convex Constrained Optimizationcited by 55
- 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
- 2020SenSeI: Sensitive Set Invariance for Enforcing Individual Fairnesscited by 37
- 2021Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Informationcited by 33
- 2018Probably Approximately Metric-Fair Learningcited by 29
- 2017Penalizing Unfairness in Binary Classificationcited by 25
- 2021Statistical inference for individual fairnesscited by 13
- 2020Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraintscited by 7
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.