Page 63 - Read Online
P. 63
Su et al. Intell Robot 2022;2(3):24474 I http://dx.doi.org/10.20517/ir.2022.17 Page 256
Fair
Pre-processing eliminate bias Algorithm predict
Data
Algorithm
Causality-based In-processing Fair
methods predict
Data Fairness constraints
Fair
Post-processing Algorithm Prediction revision predict
Data
Figure 6. The categorization of causality-based fairness-enhancing approaches.
5.1. Preprocessing Causalitybased methods
Pre-processing methods update the training data before feeding them into a machine learning algorithm.
Specifically, one idea is to change the labels of some instances or reweigh them before training to limit the
causal effects of the sensitive attributes on the decision. As a result, the classifier can make a fairer predic-
tion [36] . On the other hand, some studies propose to reconstruct the feature representations of the data to
eliminate discrimination embedded in the data [38,39] .
Forexample,Zhangetal. [27] formalizedthepresenceofdiscriminationasthepresenceofacertainpath-specific
effect, and then framed the problem as one maximizing the likelihood subject to constraints that restrict the
magnitude of the . To deal with unidentifiable cases, they mathematically bound the . CFGAN [40] ,
which is based on Causal GAN [41] to learn the causal relationship between the attributes, adopts two gen-
erators to separately simulate the underlying causal model that generates the real data and the causal model
after the intervention and two discriminators to produce a close to real distribution and to achieve total ef-
fect fairness, counterfactual fairness, and path-specific fairness. Salimi et al. [42,43] leveraged the dependencies
between sensitive and other attributes, which is provided by the causal knowledge, to add or remove samples
from the collected datasets in order to eliminate the discrimination. Nabi et al. [44] only considered mapping
generative models for ( ,V \W|W) consisting of some attributes W to “’fair” versions of this distribution
∗ ( ,V \W|W) and ensured that ∗ (W) = (W). PSCF-VAE [45] achieves path-specific counterfactual
fairness by modifying the observed values of the descendant attribute of the sensitive attribute on the unfair
causal path during testing, leaving the underlying data-generation mechanism unaltered during training.
5.2. InProcessing Causalitybased methods
In-processing methods eliminate discrimination by adding constraints or regularization terms to machine
learning models [46–50] . If it is allowed to change the learning procedure for a machine learning model, then
in-processing can be used during the training of a model either by incorporating changes into the objective
function or imposing a constraint.
For example, multi-world fairness algorithms [12] add constraints to the classification model that require satis-
fying the counterfactual fairness. To address the unidentifiable situation and alleviate the difficulty of deter-
mining causal models, it combines multiple possible causal models to make approximately fair predictions. A
tuning parameter is used to modulate the trade-off between fairness and accuracy. Hu et al. [51] proposed
to learn multiple fair classifiers simultaneously from a static training dataset. Each classifier is considered to
perform soft interventions on the decision, whose influence is inferred as the post-intervention distributions
to formulate loss functions and fairness constraints. Garg et al. [52] proposed to penalize the discrepancy be-
tween real samples and their counterfactual samples by adding counterfactual logit pairing (CLP) to the loss
function of the algorithm. Similarly, the authors of [53] proposed to add constraints terms during the training
to eliminate the difference in outcome between two identical individuals, one from the real world and one
