FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data
This addresses the vulnerability of fairness-aware learning methods to unreliable training data, which is crucial for deploying fair AI systems in real-world scenarios, though it is an incremental augmentation rather than a new paradigm.
The paper tackles the problem of fair learning from unreliable training data in a multisource setting, where some sources may not represent the true distribution, by introducing FLEA, a filtering algorithm that identifies and suppresses harmful sources to protect fairness and accuracy, with experiments showing effectiveness and a formal proof guaranteeing robustness against corruptions if less than half of sources are affected.
Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a fast-growing area of machine learning with far-reaching societal impact. However, existing fair learning methods are vulnerable to accidental or malicious artifacts in the training data, which can cause them to unknowingly produce unfair classifiers. In this work we address the problem of fair learning from unreliable training data in the robust multisource setting, where the available training data comes from multiple sources, a fraction of which might not be representative of the true data distribution. We introduce FLEA, a filtering-based algorithm that identifies and suppresses those data sources that would have a negative impact on fairness or accuracy if they were used for training. As such, FLEA is not a replacement of prior fairness-aware learning methods but rather an augmentation that makes any of them robust against unreliable training data. We show the effectiveness of our approach by a diverse range of experiments on multiple datasets. Additionally, we prove formally that -- given enough data -- FLEA protects the learner against corruptions as long as the fraction of affected data sources is less than half. Our source code and documentation are available at https://github.com/ISTAustria-CVML/FLEA.