Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Bounds

• URL: http://arxiv.org/abs/2004.12332v1
• Date: Sun, 26 Apr 2020 09:45:45 GMT
• Title: Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Bounds
• Authors: Kawin Ethayarajh
• Abstract summary: We use Bernstein bounds to represent uncertainty about the bias estimate as a confidence interval. We provide empirical evidence that a 95% confidence interval consistently bounds the true bias. Our findings suggest that the datasets currently used to measure bias are too small to conclusively identify bias except in the most egregious cases.
• Score: 21.598196899084268
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most NLP datasets are not annotated with protected attributes such as gender, making it difficult to measure classification bias using standard measures of fairness (e.g., equal opportunity). However, manually annotating a large dataset with a protected attribute is slow and expensive. Instead of annotating all the examples, can we annotate a subset of them and use that sample to estimate the bias? While it is possible to do so, the smaller this annotated sample is, the less certain we are that the estimate is close to the true bias. In this work, we propose using Bernstein bounds to represent this uncertainty about the bias estimate as a confidence interval. We provide empirical evidence that a 95% confidence interval derived this way consistently bounds the true bias. In quantifying this uncertainty, our method, which we call Bernstein-bounded unfairness, helps prevent classifiers from being deemed biased or unbiased when there is insufficient evidence to make either claim. Our findings suggest that the datasets currently used to measure specific biases are too small to conclusively identify bias except in the most egregious cases. For example, consider a co-reference resolution system that is 5% more accurate on gender-stereotypical sentences -- to claim it is biased with 95% confidence, we need a bias-specific dataset that is 3.8 times larger than WinoBias, the largest available.

Related papers

• Revisiting the Dataset Bias Problem from a Statistical Perspective [72.94990819287551]
  We study the "dataset bias" problem from a statistical standpoint. We identify the main cause of the problem as the strong correlation between a class attribute u and a non-class attribute b. We propose to mitigate dataset bias via either weighting the objective of each sample n by frac1p(u_n|b_n) or sampling that sample with a weight proportional to frac1p(u_n|b_n).
  arXiv  Detail & Related papers  (2024-02-05T22:58:06Z)
• Hybrid Sample Synthesis-based Debiasing of Classifier in Limited Data Setting [5.837881923712393]
  This paper focuses on a more practical setting with no prior information about the bias. In this setting, there are a large number of bias-aligned samples that cause the model to produce biased predictions. If the training data is limited, the influence of the bias-aligned samples may become even stronger on the model predictions.
  arXiv  Detail & Related papers  (2023-12-13T17:04:16Z)
• Mitigating Bias for Question Answering Models by Tracking Bias Influence [84.66462028537475]
  We propose BMBI, an approach to mitigate the bias of multiple-choice QA models. Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance. We show that our method could be applied to multiple QA formulations across multiple bias categories.
  arXiv  Detail & Related papers  (2023-10-13T00:49:09Z)
• On Fairness and Stability: Is Estimator Variance a Friend or a Foe? [6.751310968561177]
  We propose a new family of performance measures based on group-wise parity in variance. We develop and release an open-source library that reconciles uncertainty quantification techniques with fairness analysis.
  arXiv  Detail & Related papers  (2023-02-09T09:35:36Z)
• Unbiased Supervised Contrastive Learning [10.728852691100338]
  In this work, we tackle the problem of learning representations that are robust to biases. We first present a margin-based theoretical framework that allows us to clarify why recent contrastive losses can fail when dealing with biased data. We derive a novel formulation of the supervised contrastive loss (epsilon-SupInfoNCE), providing more accurate control of the minimal distance between positive and negative samples. Thanks to our theoretical framework, we also propose FairKL, a new debiasing regularization loss, that works well even with extremely biased data.
  arXiv  Detail & Related papers  (2022-11-10T13:44:57Z)
• Bias Mimicking: A Simple Sampling Approach for Bias Mitigation [57.17709477668213]
  We introduce a new class-conditioned sampling method: Bias Mimicking. Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks.
  arXiv  Detail & Related papers  (2022-09-30T17:33:00Z)
• Improving Evaluation of Debiasing in Image Classification [29.711865666774017]
  Our study indicates several issues need to be improved when conducting evaluation of debiasing in image classification. Based on such issues, this paper proposes an evaluation metric Align-Conflict (AC) score' for the tuning criterion. We believe our findings and lessons inspire future researchers in debiasing to further push state-of-the-art performances with fair comparisons.
  arXiv  Detail & Related papers  (2022-06-08T05:24:13Z)
• The SAME score: Improved cosine based bias score for word embeddings [49.75878234192369]
  We introduce SAME, a novel bias score for semantic bias in embeddings. We show that SAME is capable of measuring semantic bias and identify potential causes for social bias in downstream tasks.
  arXiv  Detail & Related papers  (2022-03-28T09:28:13Z)
• SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression [68.66245730450915]
  We develop an improved method for debiasing predictions and estimating frequentist uncertainty for practical datasets. Our main contribution is SLOE, an estimator of the signal strength with convergence guarantees that reduces the computation time of estimation and inference by orders of magnitude.
  arXiv  Detail & Related papers  (2021-03-23T17:48:56Z)
• The Gap on GAP: Tackling the Problem of Differing Data Distributions in Bias-Measuring Datasets [58.53269361115974]
  Diagnostic datasets that can detect biased models are an important prerequisite for bias reduction within natural language processing. undesired patterns in the collected data can make such tests incorrect. We introduce a theoretically grounded method for weighting test samples to cope with such patterns in the test data.
  arXiv  Detail & Related papers  (2020-11-03T16:50:13Z)

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.