Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing

• URL: http://arxiv.org/abs/2312.03867v2
• Date: Sat, 25 May 2024 15:42:29 GMT
• Title: Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing
• Authors: Lucas Monteiro Paes, Ananda Theertha Suresh, Alex Beutel, Flavio P. Calmon, Ahmad Beirami,
• Abstract summary: We propose an approach to test for performance disparities based on Conditional Value-at-Risk. We show that the sample complexity required for discovering performance violations is reduced exponentially to be at most upper bounded by the square root of the number of groups.
• Score: 24.553384023323332
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning (ML) models used in prediction and classification tasks may display performance disparities across population groups determined by sensitive attributes (e.g., race, sex, age). We consider the problem of evaluating the performance of a fixed ML model across population groups defined by multiple sensitive attributes (e.g., race and sex and age). Here, the sample complexity for estimating the worst-case performance gap across groups (e.g., the largest difference in error rates) increases exponentially with the number of group-denoting sensitive attributes. To address this issue, we propose an approach to test for performance disparities based on Conditional Value-at-Risk (CVaR). By allowing a small probabilistic slack on the groups over which a model has approximately equal performance, we show that the sample complexity required for discovering performance violations is reduced exponentially to be at most upper bounded by the square root of the number of groups. As a byproduct of our analysis, when the groups are weighted by a specific prior distribution, we show that R\'enyi entropy of order 2/3 of the prior distribution captures the sample complexity of the proposed CVaR test algorithm. Finally, we also show that there exists a non-i.i.d. data collection strategy that results in a sample complexity independent of the number of groups.

Related papers

• A structured regression approach for evaluating model performance across intersectional subgroups [53.91682617836498]
  Disaggregated evaluation is a central task in AI fairness assessment, where the goal is to measure an AI system's performance across different subgroups. We introduce a structured regression approach to disaggregated evaluation that we demonstrate can yield reliable system performance estimates even for very small subgroups.
  arXiv  Detail & Related papers  (2024-01-26T14:21:45Z)
• Sample Complexity Bounds for Estimating Probability Divergences under Invariances [31.946304450935628]
  Group-invariant probability distributions appear in many data-generative models in machine learning. In this work, we study how the inherent invariances, with respect to any smooth action of a Lie group on a manifold, improve sample complexity. Results are completely new for groups of positive dimension and extend recent bounds for finite group actions.
  arXiv  Detail & Related papers  (2023-11-06T04:45:21Z)
• Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model [79.46465138631592]
  We devise an efficient algorithm that recovers clusters using the observed labels. We present Instance-Adaptive Clustering (IAC), the first algorithm whose performance matches these lower bounds both in expectation and with high probability.
  arXiv  Detail & Related papers  (2023-06-18T08:46:06Z)
• Simplicity Bias Leads to Amplified Performance Disparities [8.60453031364566]
  We show that SGD-trained models have a bias towards simplicity, leading them to prioritize learning a majority class. A model may prioritize any class or group of the dataset that it finds simple-at the expense of what it finds complex.
  arXiv  Detail & Related papers  (2022-12-13T15:24:41Z)
• Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation [72.92329724600631]
  We propose a pseudo-attribute-based algorithm, coined Spread Spurious Attribute, for improving the worst-group accuracy. Our experiments on various benchmark datasets show that our algorithm consistently outperforms the baseline methods. We also demonstrate that the proposed SSA can achieve comparable performances to methods using full (100%) spurious attribute supervision.
  arXiv  Detail & Related papers  (2022-04-05T09:08:30Z)
• Optimal Clustering with Bandit Feedback [57.672609011609886]
  This paper considers the problem of online clustering with bandit feedback. It includes a novel stopping rule for sequential testing that circumvents the need to solve any NP-hard weighted clustering problem as its subroutines. We show through extensive simulations on synthetic and real-world datasets that BOC's performance matches the lower boundally, and significantly outperforms a non-adaptive baseline algorithm.
  arXiv  Detail & Related papers  (2022-02-09T06:05:05Z)
• Towards Group Robustness in the presence of Partial Group Labels [61.33713547766866]
  spurious correlations between input samples and the target labels wrongly direct the neural network predictions. We propose an algorithm that optimize for the worst-off group assignments from a constraint set. We show improvements in the minority group's performance while preserving overall aggregate accuracy across groups.
  arXiv  Detail & Related papers  (2022-01-10T22:04:48Z)
• Group-matching algorithms for subjects and items [6.739368462094944]
  We consider the problem of constructing matched groups such that the resulting groups are statistically similar with respect to their average values. We show that the ldamatch package produces high-quality matches using artificial and real-world data sets.
  arXiv  Detail & Related papers  (2021-10-09T02:44:31Z)
• Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
  We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
  arXiv  Detail & Related papers  (2021-06-14T05:39:09Z)

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.