Taking Advantage of Multitask Learning for Fair Classification

By Luca Oneto, Michele Donini, Amon Elders, Massimiliano Pontil. 2018

70 citations recorded by the source corpus.

A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information as part of a statistical model, and any commitment to protect these characteristics. Often, due to biases present in the data, using the sensitive information in the functional form of a classifier improves classification accuracy. In this paper we show how it is possible to get the best of both worlds: optimize model accuracy and fairness without explicitly using the sensitive feature in the functional form of the model, thereby treating different individuals equally. Our method is based on two key ideas. On the one hand, we propose to use Multitask Learning (MTL), enhanced with fairness constraints, to jointly learn group specific classifiers that leverage information between sensitive groups. On the other hand, since learning group specific models might not be permitted, we propose to first predict the sensitive features by any learning method and then to use the predicted sensitive feature to train MTL with fairness constraints. This enables us to tackle fairness with a three-pronged approach, that is, by increasing accuracy on each group, enforcing measures of fairness during training, and protecting sensitive information during testing. Experimental results on two real datasets support our proposal, showing substantial improvements in both accuracy and fairness.

Subfields: Artificial Intelligence, Safety Research, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In AI Ethics, Fairness & Society

Citations in the corpus

A Survey on Bias and Fairness in Machine Learning (2019, background): “[122] takes a new approach into fair classification by imposing fairness constraints into a Multitask learning (MTL) framework.”
Empirical Risk Minimization under Fairness Constraints (2018, methodology): “Finally our method can be extended to deal with other frameworks like the multitask learning one [31].”
Fairness in Machine Learning: A Survey (2020, unknown): “Synopsis: Within the sampling approaches, the application of decoupled classifiers and multitask learning has emerged (see References [9, 52, 90, 225, 283, 307]).”
A Framework for Understanding Unintended Consequences of Machine Learning (2019, background): “…learning meth-ods , such as multitask learning, that parameterize different groups differently in the model deﬁnition and facilitate learning multiple simpler functions that take into account group differences (Gelman, 2006; Dwork et al., 2017; Suresh, Gong, and Guttag, 2018; Oneto et al., 2018).”
Fairness in Machine Learning (2020, methodology): “Some methods transform the constrained optimization problem via the method of Lagrange multipliers [3, 15, 34, 37, 38, 59, 97, 135, 183, 185] or add penalties to the objective [5, 14, 22, 44, 46, 56, 58, 62, 73, 74, 75, 79, 82, 87, 88, 89, 93, 94, 95, 98, 104, 115, 119, 123, 133, 134, 135, 138, 139,”