Neutralized Empirical Risk Minimization with Generalization Neutrality Bound
This work addresses fairness in supervised learning for applications where discrimination or bias must be avoided, representing an incremental advancement with a new method for a known bottleneck.
The authors tackled the problem of ensuring fairness in machine learning by introducing a novel empirical risk minimization framework called neutralized ERM (NERM), which guarantees classifiers are neutral to a viewpoint hypothesis, and they demonstrated improved classification performance without sacrificing neutrality in real datasets.
Currently, machine learning plays an important role in the lives and individual activities of numerous people. Accordingly, it has become necessary to design machine learning algorithms to ensure that discrimination, biased views, or unfair treatment do not result from decision making or predictions made via machine learning. In this work, we introduce a novel empirical risk minimization (ERM) framework for supervised learning, neutralized ERM (NERM) that ensures that any classifiers obtained can be guaranteed to be neutral with respect to a viewpoint hypothesis. More specifically, given a viewpoint hypothesis, NERM works to find a target hypothesis that minimizes the empirical risk while simultaneously identifying a target hypothesis that is neutral to the viewpoint hypothesis. Within the NERM framework, we derive a theoretical bound on empirical and generalization neutrality risks. Furthermore, as a realization of NERM with linear classification, we derive a max-margin algorithm, neutral support vector machine (SVM). Experimental results show that our neutral SVM shows improved classification performance in real datasets without sacrificing the neutrality guarantee.