Learning for Counterfactual Fairness from Observational Data
- URL: http://arxiv.org/abs/2307.08232v1
- Date: Mon, 17 Jul 2023 04:08:29 GMT
- Title: Learning for Counterfactual Fairness from Observational Data
- Authors: Jing Ma, Ruocheng Guo, Aidong Zhang, Jundong Li
- Abstract summary: Fairness-aware machine learning aims to eliminate biases of learning models against certain subgroups described by certain protected (sensitive) attributes such as race, gender, and age.
A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data.
In this work, we address the problem of counterfactually fair prediction from observational data without given causal models by proposing a novel framework CLAIRE.
- Score: 62.43249746968616
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Fairness-aware machine learning has attracted a surge of attention in many
domains, such as online advertising, personalized recommendation, and social
media analysis in web applications. Fairness-aware machine learning aims to
eliminate biases of learning models against certain subgroups described by
certain protected (sensitive) attributes such as race, gender, and age. Among
many existing fairness notions, counterfactual fairness is a popular notion
defined from a causal perspective. It measures the fairness of a predictor by
comparing the prediction of each individual in the original world and that in
the counterfactual worlds in which the value of the sensitive attribute is
modified. A prerequisite for existing methods to achieve counterfactual
fairness is the prior human knowledge of the causal model for the data.
However, in real-world scenarios, the underlying causal model is often unknown,
and acquiring such human knowledge could be very difficult. In these scenarios,
it is risky to directly trust the causal models obtained from information
sources with unknown reliability and even causal discovery methods, as
incorrect causal models can consequently bring biases to the predictor and lead
to unfair predictions. In this work, we address the problem of counterfactually
fair prediction from observational data without given causal models by
proposing a novel framework CLAIRE. Specifically, under certain general
assumptions, CLAIRE effectively mitigates the biases from the sensitive
attribute with a representation learning framework based on counterfactual data
augmentation and an invariant penalty. Experiments conducted on both synthetic
and real-world datasets validate the superiority of CLAIRE in both
counterfactual fairness and prediction performance.
Related papers
- 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) - FairPFN: Transformers Can do Counterfactual Fairness [41.052676173417574]
Causal and counterfactual fairness provides an intuitive way to define fairness that closely aligns with legal standards.
This study builds upon recent work in in context learning (ICL) and prior fitted networks (PFNs) to learn a transformer called FairPFN.
This model is pretrained using synthetic fairness data to eliminate the causal effects of protected attributes directly from observational data.
arXiv Detail & Related papers (2024-07-08T08:36:44Z) - Counterfactual Fairness for Predictions using Generative Adversarial
Networks [28.65556399421874]
We develop a novel deep neural network called Generative Counterfactual Fairness Network (GCFN) for making predictions under counterfactual fairness.
Our method is mathematically guaranteed to ensure the notion of counterfactual fairness.
arXiv Detail & Related papers (2023-10-26T17:58:39Z) - Fast Model Debias with Machine Unlearning [54.32026474971696]
Deep neural networks might behave in a biased manner in many real-world scenarios.
Existing debiasing methods suffer from high costs in bias labeling or model re-training.
We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
arXiv Detail & Related papers (2023-10-19T08:10:57Z) - Fair Inference for Discrete Latent Variable Models [12.558187319452657]
Machine learning models, trained on data without due care, often exhibit unfair and discriminatory behavior against certain populations.
We develop a fair variational inference technique for the discrete latent variables, which is accomplished by including a fairness penalty on the variational distribution.
To demonstrate the generality of our approach and its potential for real-world impact, we then develop a special-purpose graphical model for criminal justice risk assessments.
arXiv Detail & Related papers (2022-09-15T04:54:21Z) - 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) - Prisoners of Their Own Devices: How Models Induce Data Bias in
Performative Prediction [4.874780144224057]
A biased model can make decisions that disproportionately harm certain groups in society.
Much work has been devoted to measuring unfairness in static ML environments, but not in dynamic, performative prediction ones.
We propose a taxonomy to characterize bias in the data, and study cases where it is shaped by model behaviour.
arXiv Detail & Related papers (2022-06-27T10:56:04Z) - Measuring Fairness of Text Classifiers via Prediction Sensitivity [63.56554964580627]
ACCUMULATED PREDICTION SENSITIVITY measures fairness in machine learning models based on the model's prediction sensitivity to perturbations in input features.
We show that the metric can be theoretically linked with a specific notion of group fairness (statistical parity) and individual fairness.
arXiv Detail & Related papers (2022-03-16T15:00:33Z) - Cross-model Fairness: Empirical Study of Fairness and Ethics Under Model Multiplicity [10.144058870887061]
We argue that individuals can be harmed when one predictor is chosen ad hoc from a group of equally well performing models.
Our findings suggest that such unfairness can be readily found in real life and it may be difficult to mitigate by technical means alone.
arXiv Detail & Related papers (2022-03-14T14:33:39Z) - Representative & Fair Synthetic Data [68.8204255655161]
We present a framework to incorporate fairness constraints into the self-supervised learning process.
We generate a representative as well as fair version of the UCI Adult census data set.
We consider representative & fair synthetic data a promising future building block to teach algorithms not on historic worlds, but rather on the worlds that we strive to live in.
arXiv Detail & Related papers (2021-04-07T09:19:46Z)
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.