Mitigating Bias in Federated Learning
This work addresses the problem of algorithmic bias in federated learning, which is an increasingly important concern for organizations deploying collaborative machine learning models.
This paper explores the causes of bias in federated learning (FL) and proposes three pre-processing and in-processing methods to mitigate this bias. The methods are shown to be effective even with skewed data distributions or when only 20% of parties employ them, without compromising data privacy.
As methods to create discrimination-aware models develop, they focus on centralized ML, leaving federated learning (FL) unexplored. FL is a rising approach for collaborative ML, in which an aggregator orchestrates multiple parties to train a global model without sharing their training data. In this paper, we discuss causes of bias in FL and propose three pre-processing and in-processing methods to mitigate bias, without compromising data privacy, a key FL requirement. As data heterogeneity among parties is one of the challenging characteristics of FL, we conduct experiments over several data distributions to analyze their effects on model performance, fairness metrics, and bias learning patterns. We conduct a comprehensive analysis of our proposed techniques, the results demonstrating that these methods are effective even when parties have skewed data distributions or as little as 20% of parties employ the methods.