A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms

• URL: http://arxiv.org/abs/2204.10233v2
• Date: Tue, 13 Dec 2022 18:00:46 GMT
• Title: A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms
• Authors: Nil-Jana Akpinar, Manish Nagireddy, Logan Stapleton, Hao-Fei Cheng, Haiyi Zhu, Steven Wu, Hoda Heidari
• Abstract summary: We present the conceptual idea and a first implementation of a bias-injection sandbox tool to investigate fairness consequences of various biases. Unlike existing toolkits, ours provides a controlled environment to counterfactually inject biases in the ML pipeline. In particular, we can test whether a given remedy can alleviate the injected bias by comparing the predictions resulting after the intervention with true labels in the unbiased regime-that is, before any bias injection.
• Score: 19.86635585740634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Motivated by the growing importance of reducing unfairness in ML predictions, Fair-ML researchers have presented an extensive suite of algorithmic 'fairness-enhancing' remedies. Most existing algorithms, however, are agnostic to the sources of the observed unfairness. As a result, the literature currently lacks guiding frameworks to specify conditions under which each algorithmic intervention can potentially alleviate the underpinning cause of unfairness. To close this gap, we scrutinize the underlying biases (e.g., in the training data or design choices) that cause observational unfairness. We present the conceptual idea and a first implementation of a bias-injection sandbox tool to investigate fairness consequences of various biases and assess the effectiveness of algorithmic remedies in the presence of specific types of bias. We call this process the bias(stress)-testing of algorithmic interventions. Unlike existing toolkits, ours provides a controlled environment to counterfactually inject biases in the ML pipeline. This stylized setup offers the distinct capability of testing fairness interventions beyond observational data and against an unbiased benchmark. In particular, we can test whether a given remedy can alleviate the injected bias by comparing the predictions resulting after the intervention in the biased setting with true labels in the unbiased regime-that is, before any bias injection. We illustrate the utility of our toolkit via a proof-of-concept case study on synthetic data. Our empirical analysis showcases the type of insights that can be obtained through our simulations.

Related papers

• Outlier Detection Bias Busted: Understanding Sources of Algorithmic Bias through Data-centric Factors [28.869581543676947]
  unsupervised outlier detection (OD) has numerous applications in finance, security, etc. This work aims to shed light on the possible sources of unfairness in OD by auditing detection models under different data-centric factors. We find that the OD algorithms under the study all exhibit fairness pitfalls, although differing in which types of data bias they are more susceptible to.
  arXiv  Detail & Related papers  (2024-08-24T20:35:32Z)
• Editable Fairness: Fine-Grained Bias Mitigation in Language Models [52.66450426729818]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases. FAST surpasses state-of-the-art baselines with superior debiasing performance. This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Inference-Time Selective Debiasing [27.578390085427156]
  We propose selective debiasing -- an inference-time safety mechanism that aims to increase the overall quality of models. We identify the potentially biased model predictions and, instead of discarding them, we debias them using LEACE -- a post-processing debiasing method. Experiments with text classification datasets demonstrate that selective debiasing helps to close the performance gap between post-processing methods and at-training and pre-processing debiasing techniques.
  arXiv  Detail & Related papers  (2024-07-27T21:56:23Z)
• Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations [12.248793742165278]
  We bridge the gap between fairness and explainability by presenting a novel perspective of procedure-oriented fairness based on explanations. We propose a Comprehensive Fairness Algorithm (CFA), which simultaneously fulfills multiple objectives - improving traditional fairness, satisfying explanation fairness, and maintaining the utility performance.
  arXiv  Detail & Related papers  (2022-12-07T18:35:54Z)
• Systematic Evaluation of Predictive Fairness [60.0947291284978]
  Mitigating bias in training on biased datasets is an important open problem. We examine the performance of various debiasing methods across multiple tasks. We find that data conditions have a strong influence on relative model performance.
  arXiv  Detail & Related papers  (2022-10-17T05:40:13Z)
• D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias [57.87117733071416]
  We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases. A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
  arXiv  Detail & Related papers  (2022-08-10T03:41:48Z)
• Information-Theoretic Bias Reduction via Causal View of Spurious Correlation [71.9123886505321]
  We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation. We present a novel debiasing framework against the algorithmic bias, which incorporates a bias regularization loss. The proposed bias measurement and debiasing approaches are validated in diverse realistic scenarios.
  arXiv  Detail & Related papers  (2022-01-10T01:19:31Z)
• A Statistical Test for Probabilistic Fairness [11.95891442664266]
  We propose a statistical hypothesis test for detecting unfair classifiers. We show both theoretically as well as empirically that the proposed test is correct. In addition, the proposed framework offers interpretability by identifying the most favorable perturbation of the data.
  arXiv  Detail & Related papers  (2020-12-09T00:20:02Z)
• Towards causal benchmarking of bias in face analysis algorithms [54.19499274513654]
  We develop an experimental method for measuring algorithmic bias of face analysis algorithms. Our proposed method is based on generating synthetic transects'' of matched sample images. We validate our method by comparing it to a study that employs the traditional observational method for analyzing bias in gender classification algorithms.
  arXiv  Detail & Related papers  (2020-07-13T17:10:34Z)
• Mitigating Gender Bias Amplification in Distribution by Posterior Regularization [75.3529537096899]
  We investigate the gender bias amplification issue from the distribution perspective. We propose a bias mitigation approach based on posterior regularization. Our study sheds the light on understanding the bias amplification.
  arXiv  Detail & Related papers  (2020-05-13T11:07:10Z)

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.