Providing Previously Unseen Users Fair Recommendations Using Variational Autoencoders

TL;DR

This paper introduces methods to ensure fairness in variational autoencoder-based recommender systems by limiting demographic information encoding, enabling fair recommendations for unseen users.

Contribution

It proposes novel techniques to mitigate demographic bias in VAEs, allowing fair recommendations for users not present in training data.

Findings

Effective reduction of demographic bias in recommendations

Successful provision of fair recommendations to unseen users

Demonstrated improvements over baseline models

Abstract

An emerging definition of fairness in machine learning requires that models are oblivious to demographic user information, e.g., a user's gender or age should not influence the model. Personalized recommender systems are particularly prone to violating this definition through their explicit user focus and user modelling. Explicit user modelling is also an aspect that makes many recommender systems incapable of providing hitherto unseen users with recommendations. We propose novel approaches for mitigating discrimination in Variational Autoencoder-based recommender systems by limiting the encoding of demographic information. The approaches are capable of, and evaluated on, providing users that are not represented in the training data with fair recommendations.