Certifying Some Distributional Fairness with Subpopulation Decomposition

• URL: http://arxiv.org/abs/2205.15494v2
• Date: Fri, 18 Nov 2022 19:44:04 GMT
• Title: Certifying Some Distributional Fairness with Subpopulation Decomposition
• Authors: Mintong Kang, Linyi Li, Maurice Weber, Yang Liu, Ce Zhang, Bo Li
• Abstract summary: We first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem. We then propose a general fairness certification framework and instantiate it for both sensitive shifting and general shifting scenarios. Our framework is flexible to integrate additional non-skewness constraints and we show that it provides even tighter certification under different real-world scenarios.
• Score: 20.009388617013986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Extensive efforts have been made to understand and improve the fairness of machine learning models based on observational metrics, especially in high-stakes domains such as medical insurance, education, and hiring decisions. However, there is a lack of certified fairness considering the end-to-end performance of an ML model. In this paper, we first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem based on the model performance loss bound on a fairness constrained distribution, which is within bounded distributional distance with the training distribution. We then propose a general fairness certification framework and instantiate it for both sensitive shifting and general shifting scenarios. In particular, we propose to solve the optimization problem by decomposing the original data distribution into analytical subpopulations and proving the convexity of the subproblems to solve them. We evaluate our certified fairness on six real-world datasets and show that our certification is tight in the sensitive shifting scenario and provides non-trivial certification under general shifting. Our framework is flexible to integrate additional non-skewness constraints and we show that it provides even tighter certification under different real-world scenarios. We also compare our certified fairness bound with adapted existing distributional robustness bounds on Gaussian data and demonstrate that our method is significantly tighter.

Related papers

• FADE: Towards Fairness-aware Augmentation for Domain Generalization via Classifier-Guided Score-based Diffusion Models [9.734351986961613]
  Fairness-aware domain generalization (FairDG) has emerged as a critical challenge for deploying trustworthy AI systems. Traditional methods for addressing fairness have failed in domain generalization due to their lack of consideration for distribution shifts. We propose Fairness-aware Score-Guided Diffusion Models (FADE) as a novel approach to effectively address the FairDG issue.
  arXiv  Detail & Related papers  (2024-06-13T17:36:05Z)
• Distribution-Free Fair Federated Learning with Small Samples [54.63321245634712]
  FedFaiREE is a post-processing algorithm developed specifically for distribution-free fair learning in decentralized settings with small samples. We provide rigorous theoretical guarantees for both fairness and accuracy, and our experimental results further provide robust empirical validation for our proposed method.
  arXiv  Detail & Related papers  (2024-02-25T17:37:53Z)
• Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework [12.734559823650887]
  In the presence of distribution shifts, fair machine learning models may behave unfairly on test data. Existing algorithms require full access to data and cannot be used when small batches are used. This paper proposes the first distributionally robust fairness framework with convergence guarantees that do not require knowledge of the causal graph.
  arXiv  Detail & Related papers  (2023-09-20T23:25:28Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach [72.19525160912943]
  We first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. We then analyze the sufficient conditions to guarantee fairness for the target dataset. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR)
  arXiv  Detail & Related papers  (2023-03-06T17:19:23Z)
• Transferring Fairness under Distribution Shifts via Fair Consistency Regularization [15.40257564187799]
  We study how to transfer model fairness under distribution shifts, a widespread issue in practice. Inspired by the success of self-training in transferring accuracy under domain shifts, we derive a sufficient condition for transferring group fairness.
  arXiv  Detail & Related papers  (2022-06-26T06:19:56Z)
• Certifying Out-of-Domain Generalization for Blackbox Functions [20.997611019445657]
  We propose a novel certification framework given bounded distance of mean and variance of two distributions. We experimentally validate our certification method on a number of datasets, ranging from ImageNet.
  arXiv  Detail & Related papers  (2022-02-03T16:47:50Z)
• Certifying Model Accuracy under Distribution Shifts [151.67113334248464]
  We present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution. We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under the transformation.
  arXiv  Detail & Related papers  (2022-01-28T22:03:50Z)
• Robust Generalization despite Distribution Shift via Minimum Discriminating Information [46.164498176119665]
  We introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribution. We employ the principle of minimum discriminating information to embed the available prior knowledge. We obtain explicit generalization bounds with respect to the unknown shifted distribution.
  arXiv  Detail & Related papers  (2021-06-08T15:25:35Z)
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation [61.317911756566126]
  We propose a Towards Fair Knowledge Transfer framework to handle the fairness challenge in imbalanced cross-domain learning. Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness. Our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.
  arXiv  Detail & Related papers  (2020-10-23T06:29:09Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.