DeBayes: a Bayesian Method for Debiasing Network Embeddings
This addresses fairness issues in network embedding applications such as social network analysis and recommender systems, representing an incremental advance over limited existing methods.
The authors tackled bias in network embeddings, proposing DeBayes, a Bayesian method that uses a biased prior to learn debiased embeddings, resulting in significantly fairer link prediction with improvements in metrics like demographic parity and equalized opportunity.
As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.