Item-based Variational Auto-encoder for Fair Music Recommendation
This work addresses fairness and accuracy in music recommendation, but it is incremental as it builds on existing methods like VAEs and BPRMF for a specific challenge.
The paper tackles the problem of building a fair music recommender system by proposing an ensemble of an item-based variational auto-encoder with fairness regularization and Bayesian personalized ranking matrix factorization, which reduces popularity bias and improves top-1 accuracy in the EvalRS DataChallenge.
We present our solution for the EvalRS DataChallenge. The EvalRS DataChallenge aims to build a more realistic recommender system considering accuracy, fairness, and diversity in evaluation. Our proposed system is based on an ensemble between an item-based variational auto-encoder (VAE) and a Bayesian personalized ranking matrix factorization (BPRMF). To mitigate the bias in popularity, we use an item-based VAE for each popularity group with an additional fairness regularization. To make a reasonable recommendation even the predictions are inaccurate, we combine the recommended list of BPRMF and that of item-based VAE. Through the experiments, we demonstrate that the item-based VAE with fairness regularization significantly reduces popularity bias compared to the user-based VAE. The ensemble between the item-based VAE and BPRMF makes the top-1 item similar to the ground truth even the predictions are inaccurate. Finally, we propose a `Coefficient Variance based Fairness' as a novel evaluation metric based on our reflections from the extensive experiments.