Provably Fair Representations

By Daniel McNamara, Cheng Soon Ong, Robert C. Williamson. 2017

59 citations recorded by the source corpus.

Machine learning systems are increasingly used to make decisions about people's lives, such as whether to give someone a loan or whether to interview someone for a job. This has led to considerable interest in making such machine learning systems fair. One approach is to transform the input data used by the algorithm. This can be achieved by passing each input data point through a representation function prior to its use in training or testing. Techniques for learning such representation functions from data have been successful empirically, but typically lack theoretical fairness guarantees. We show that it is possible to prove that a representation function is fair according to common measures of both group and individual fairness, as well as useful with respect to a target task. These provable properties can be used in a governance model involving a data producer, a data user and a data regulator, where there is a separation of concerns between fairness and target task utility to ensure transparency and prevent perverse incentives. We formally define the 'cost of mistrust' of using this model compared to the setting where there is a single trusted party, and provide bounds on this cost in particular cases. We present a practical approach to learning fair representation functions and apply it to financial and criminal justice datasets. We evaluate the fairness and utility of these representation functions using measures motivated by our theoretical results.

Subfields: Artificial Intelligence, Information Systems, Safety Research

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 Information Systems

In Safety Research

Citations in the corpus

The Frontiers of Fairness in Machine Learning (2018, background): “[FFM + 15] and [MOW17] formalize this idea by showing how the disparate impact of a decision rule is bounded in terms of its balanced error rate as a predictor of the sensitive attribute.”
On the Fairness of Disentangled Representations (2019, methodology): “On the fairness perspective, representation learning has been used as a mean to separate the detrimental effects that labeled sensitive factors could have on the classification task [67, 34].”
Fairness in Machine Learning (2020, methodology): “…21, 22, 23, 25, 28, 29, 31, 34, 44, 45, 46, 52, 53, 54, 55, 56, 59, 66, 69, 71, 72, 73, 74, 75, 82, 84, 87, 89, 90, 94, 95, 97, 98, 99, 103, 104, 106, 114, 115, 116, 121, 123, 126, 138, 139, 141, 148, 149, 153, 156, 159, 165, 174, 176, 177, 178, 179, 180, 182, 183, 184, 186, 187, 191, 192, 193].”
Hierarchical VampPrior Variational Fair Auto-Encoder (2018, background): “In these cases it is not sufﬁcient to prevent the decision maker from having access to the sensitive variable since this information has already been leaked into other features (Dwork et al., 2012; McNamara et al., 2017; Menon & Williamson, 2017; Zafar et al., 2017).”
Think Locally, Act Globally: Federated Learning with Local and Global Representations (2020, background): “A recent focus has been on learning fair representations [82], including using adversarial training [30] to learn representations that are not informative of predeﬁned private attributes [25, 16, 50, 54, 60] such as demographics [24] and gender [78].”