RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback
This work addresses the need for improved recommendation systems for users, but it is incremental as it builds upon existing Mult-VAE with specific enhancements.
The authors tackled the problem of top-N recommendations with implicit feedback by proposing RecVAE, a new variational autoencoder model that significantly outperforms previous autoencoder-based models like Mult-VAE and RaCT across classical collaborative filtering datasets.
Recent research has shown the advantages of using autoencoders based on deep neural networks for collaborative filtering. In particular, the recently proposed Mult-VAE model, which used the multinomial likelihood variational autoencoders, has shown excellent results for top-N recommendations. In this work, we propose the Recommender VAE (RecVAE) model that originates from our research on regularization techniques for variational autoencoders. RecVAE introduces several novel ideas to improve Mult-VAE, including a novel composite prior distribution for the latent codes, a new approach to setting the $β$ hyperparameter for the $β$-VAE framework, and a new approach to training based on alternating updates. In experimental evaluation, we show that RecVAE significantly outperforms previously proposed autoencoder-based models, including Mult-VAE and RaCT, across classical collaborative filtering datasets, and present a detailed ablation study to assess our new developments. Code and models are available at https://github.com/ilya-shenbin/RecVAE.