Multi-Output Distributional Fairness via Post-Processing
Not on the map. Why?
Abstract (arXiv)
The post-processing approaches are becoming prominent techniques to enhance machine learning models' fairness because of their intuitiveness, low computational cost, and excellent scalability. However, most existing post-processing methods are designed for task-specific fairness measures and are limited to single-output models. In this paper, we introduce a post-processing method for multi-output models, such as the ones used for multi-task/multi-class classification and representation learning, to enhance a model's distributional parity, a task-agnostic fairness measure. Existing methods for achieving distributional parity rely on the (inverse) cumulative density function of a model's output, restricting their applicability to single-output models. Extending previous works, we propose to employ optimal transport mappings to move a model's outputs across different groups towards their empirical Wasserstein barycenter. An approximation technique is applied to reduce the complexity of computing the exact barycenter and a kernel regression method is proposed to extend this process to out-of-sample data. Our empirical studies evaluate the proposed approach against various baselines on multi-task/multi-class classification and representation learning tasks, demonstrating the effectiveness of the proposed approach.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 52 of its 79 references that are in the map. First posted on arXiv 31 Aug 2024.
Builds on
52 of 79 references.
References · 52
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2016Equality of Opportunity in Supervised Learningcited by 2,007
- 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
- 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
- 2018Computational Optimal Transportcited by 780
- 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
- 2018A Reductions Approach to Fair Classificationcited by 587
- 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
- 2017Algorithmic decision making and the cost of fairnesscited by 403
38 more
- 2018Learning Adversarially Fair and Transferable Representationscited by 353
- 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
- 2015The Variational Fair Autoencodercited by 223
- 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
- 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
- 2019Wasserstein Fair Classificationcited by 131
- 2017Controllable Invariance through Adversarial Feature Learningcited by 127
- 2020Fair Attribute Classification through Latent Space De-biasingcited by 125
- 2021Fair Mixup: Fairness via Interpolationcited by 109
- 2020Fair Regression with Wasserstein Barycenterscited by 100
- 2014Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discriminationcited by 83
- 2020Fairness by Learning Orthogonal Disentangled Representationscited by 76
- 2018Bias Mitigation Post-processing for Individual and Group Fairnesscited by 72
- 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
- 2016Satisfying Real-world Goals with Dataset Constraintscited by 68
- 2021Fairness via Representation Neutralizationcited by 63
- 2021Post-processing for Individual Fairnesscited by 61
- 2019Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classificationcited by 60
- 2019Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classificationcited by 55
- 2022Fair and Optimal Classification via Post-Processingcited by 51
- 2019Equalized odds postprocessing under imperfect group informationcited by 48
- 2018Fairness Under Compositioncited by 43
- 2022Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performancecited by 43
- 2021Object-aware Contrastive Learning for Debiased Scene Representationcited by 35
- 2021Wasserstein barycenters are NP-hard to computecited by 28
- 2021Classification with abstention but without disparitiescited by 28
- 2022Bayes-Optimal Classifiers under Group Fairnesscited by 24
- 2022Fair learning with Wasserstein barycenters for non-decomposable performance measurescited by 24
- 2015Discrete Wasserstein Barycenters: Optimal Transport for Discrete Datacited by 20
- 2022Minimax AUC Fairness: Efficient Algorithm with Provable Convergencecited by 16
- 2023FRAPPE: A Group Fairness Framework for Post-Processing Everythingcited by 16
- 2023Fairness in Multi-Task Learning via Wasserstein Barycenterscited by 14
- 2022Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraintscited by 9
- 2022Repairing Regressors for Fair Binary Classification at Any Decision Thresholdcited by 8
- 2023SimFair: A Unified Framework for Fairness-Aware Multi-Label Classificationcited by 7
- 2023DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervisioncited by 6
- 2023Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustmentcited by 5
- 2023f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimizationcited by 4
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.